convez.ai
MCP Server
tassiovale

claude-code-kit

tassiovale/claude-code-kit

Ver no GitHub
InicialPluginScore · de 0 a 100

A curated collection of agents, skills, and settings that supercharge Claude Code. Drop them into their local Claude Code environment and immediately boost productivity.

Instalação

$npx convez-ai tassiovale/claude-code-kit

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
12
Forks
4
Acompanhando
1
Saúde
28%
Último commit
há 3 meses
Versão
v1.3.0
Issues abertas
0
Contribuidores
2

README

A tradução para o português deste README ainda está na fila.

Claude Code Kit

A curated collection of agents, skills, and settings that supercharge Claude Code. The goal of this kit is to gather battle-tested subagents, reusable skills, and sensible default settings in one place so practitioners can drop them into their local Claude Code environment and immediately boost productivity.

🚀 What's Inside

ComponentCountLocationInstalls to
Agents133 specialized subagentsagents/~/.claude/agents/
Skills197 reusable skillsskills/~/.claude/skills/
SettingsGlobal config + permissionssettings/~/.claude/
Hooks4 automation hookshooks/~/.claude/hooks/
  • Agents are role-focused subagents (language experts, reviewers, architects, etc.) that Claude Code can delegate work to.
  • Skills are self-contained capability packages (each with a SKILL.md) that teach Claude how to use a specific tool, library, or workflow.
  • Settings provide a ready-to-use settings.json with environment tuning, permission guardrails, and a status line.

🔧 Installation (user-level / global)

These steps install everything at the user level so the agents, skills, and settings are available across all your projects (Claude Code reads from ~/.claude/ on Linux/macOS and %USERPROFILE%\.claude\ on Windows).

Run the commands from the root of this repository.


Linux / macOS

Dependencies: node ≥ 18 (for hooks) and jq (for the status line). Both are optional if you skip hooks or the status line.

# Debian/Ubuntu
sudo apt install nodejs jq

# macOS
brew install node jq
# 1. Create the target directories if they don't exist
mkdir -p ~/.claude/agents ~/.claude/skills ~/.claude/hooks/pre-tool-use ~/.claude/hooks/post-tool-use ~/.claude/hooks/notification

# 2. Copy all agents
cp -v agents/*.md ~/.claude/agents/

# 3. Copy all skills (each skill is its own directory)
cp -rv skills/* ~/.claude/skills/

# 4. Copy hooks
cp -v hooks/pre-tool-use/*.js ~/.claude/hooks/pre-tool-use/
cp -v hooks/post-tool-use/*.js ~/.claude/hooks/post-tool-use/
cp -v hooks/notification/*.js  ~/.claude/hooks/notification/

# 5. Copy the status line script and make it executable
cp settings/statusline.sh ~/.claude/statusline.sh
chmod +x ~/.claude/statusline.sh

# 6. Copy the platform settings (already points to ~/.claude/statusline.sh)
cp -v settings/settings-bash.json ~/.claude/settings.json

Re-syncing / updates (recommended)

rsync is idempotent — re-run it anytime to pick up updates without clobbering unrelated files:

rsync -av agents/  ~/.claude/agents/
rsync -av skills/  ~/.claude/skills/
rsync -av hooks/   ~/.claude/hooks/
cp settings/statusline.sh ~/.claude/statusline.sh && chmod +x ~/.claude/statusline.sh
rsync -av settings/settings-bash.json ~/.claude/settings.json

Requires jq (brew install jq / apt install jq). git is optional — the script degrades gracefully when not in a repo.


Windows (PowerShell)

Dependencies: node ≥ 18 (for hooks). Install via nodejs.org or:

winget install OpenJS.NodeJS
# 1. Create the target directories if they don't exist
New-Item -ItemType Directory -Force `
  "$env:USERPROFILE\.claude\agents", `
  "$env:USERPROFILE\.claude\skills", `
  "$env:USERPROFILE\.claude\hooks\pre-tool-use", `
  "$env:USERPROFILE\.claude\hooks\post-tool-use", `
  "$env:USERPROFILE\.claude\hooks\notification"

# 2. Copy all agents
Copy-Item agents\*.md "$env:USERPROFILE\.claude\agents\"

# 3. Copy all skills (each skill is its own directory)
Copy-Item skills\* "$env:USERPROFILE\.claude\skills\" -Recurse

# 4. Copy hooks
Copy-Item hooks\pre-tool-use\*.js "$env:USERPROFILE\.claude\hooks\pre-tool-use\"
Copy-Item hooks\post-tool-use\*.js "$env:USERPROFILE\.claude\hooks\post-tool-use\"
Copy-Item hooks\notification\*.js  "$env:USERPROFILE\.claude\hooks\notification\"

# 5. Copy the status line script
Copy-Item settings\statusline.ps1 "$env:USERPROFILE\.claude\statusline.ps1"

# 6. Copy the platform settings and inject your username into path placeholders
$settings = Get-Content settings\settings-powershell.json -Raw
$settings = $settings -replace '<YourName>', $env:USERNAME
$settings | Set-Content "$env:USERPROFILE\.claude\settings.json" -Encoding utf8

Re-syncing / updates (recommended)

robocopy is the Windows equivalent of rsync — safe to re-run, only copies changed files:

robocopy agents  "$env:USERPROFILE\.claude\agents"  *.md /NFL /NDL
robocopy skills  "$env:USERPROFILE\.claude\skills"  /E   /NFL /NDL
robocopy hooks   "$env:USERPROFILE\.claude\hooks"   /E   /NFL /NDL
Copy-Item settings\statusline.ps1 "$env:USERPROFILE\.claude\statusline.ps1" -Force
$settings = Get-Content settings\settings-powershell.json -Raw
$settings = $settings -replace '<YourName>', $env:USERNAME
$settings | Set-Content "$env:USERPROFILE\.claude\settings.json" -Encoding utf8

If you have PowerShell 7 installed, open ~/.claude/settings.json after install and swap powershell for pwsh in the statusLine.command value. Windows Terminal is recommended for correct ANSI / UTF-8 rendering. No jq required — the script uses PowerShell's native JSON parser.


Heads up — settings. Copying settings.json overwrites your existing global Claude Code settings. If you already have a customized file, back it up first:

  • Linux/macOS: cp ~/.claude/settings.json ~/.claude/settings.json.bak
  • Windows: Copy-Item "$env:USERPROFILE\.claude\settings.json" "$env:USERPROFILE\.claude\settings.json.bak"

Then merge by hand instead of overwriting.

Note. The agents/ folder also contains a CLAUDE.md and an AGENTS-REFERENCE.md. These are reference/instruction docs, not agents — you can skip copying them, or copy them deliberately if you want their guidance.

After installing, restart Claude Code (or start a new session). The agents become available for delegation, and skills trigger automatically based on their descriptions.


🤖 Agents

133 subagents grouped by domain. Each links to its definition file.

Meta / Orchestration

AgentDescription
grand-architectMeta-orchestrator that plans complex features, breaks down large tasks, and coordinates multiple agents.
tech-lead-orchestratorSenior tech lead that analyzes projects and returns structured task breakdowns for agent coordination.
project-analystAnalyzes unfamiliar codebases to detect frameworks, tech stacks, and architecture for routing.
code-archaeologistExplores and documents unfamiliar, legacy, or complex codebases with full risk/action reports.

Languages & Runtimes

AgentDescription
python-proType-safe, production-ready Python with modern async patterns and extensive typing.
typescript-proAdvanced TypeScript type system, full-stack development, and build optimization.
javascript-proModern ES2023+ JavaScript for browser, Node.js, and full-stack apps.
golang-proIdiomatic Go for concurrent, high-performance, cloud-native systems.
rust-engineerRust systems programming with memory safety and zero-cost abstractions.
cpp-proHigh-performance modern C++20/23 and template metaprogramming.
java-proModern Java 21+ with virtual threads, pattern matching, and Spring Boot 3.x.
java-architectEnterprise Java architecture across the Spring ecosystem and microservices.
csharp-developerASP.NET Core APIs and cloud-native .NET with clean architecture.
dotnet-core-expertCloud-native .NET Core microservices with minimal APIs.
dotnet-framework-4.8-expertLegacy .NET Framework 4.8 maintenance and modernization.
php-proModern PHP 8.3+ with strong typing and enterprise frameworks.
kotlin-specialistKotlin coroutines, multiplatform, and Android development.
swift-expertNative iOS/macOS/server-side Swift with advanced concurrency.
elixir-expertFault-tolerant concurrent systems with OTP and Phoenix.
sql-proComplex SQL query optimization and schema design across major engines.

Frameworks (Frontend / Backend / Mobile)

AgentDescription
react-specialistReact 18+ patterns, performance optimization, and server components.
react-coderSimplicity-first React 19 components using internal UI packages.
vue-expertVue 3 Composition API, reactivity, and Nuxt 3 development.
angular-architectEnterprise Angular 15+ with complex state and micro-frontends.
nextjs-developerProduction Next.js 14+ with App Router and server components.
frontend-developerRobust, scalable React frontend components and UX.
fullstack-developerEnd-to-end feature delivery from database to UI.
backend-developerScalable API development and microservices.
django-developerDjango 4+ apps and REST APIs with async views.
rails-expertRails apps with Hotwire reactivity and idiomatic patterns.
laravel-specialistLaravel 10+ with Eloquent, queues, and enterprise features.
laravel-backend-expertLaravel backend controllers, services, and Eloquent models.
laravel-eloquent-expertLaravel Eloquent schemas, relationships, and query tuning.
spring-boot-engineerEnterprise Spring Boot 3+ microservices and reactive patterns.
wordpress-masterWordPress themes, plugins, headless APIs, and scaling.
mobile-developerCross-platform mobile with React Native and Flutter.
mobile-app-developerNative and cross-platform iOS/Android development.
flutter-expertCross-platform Flutter 3+ with custom UI and state management.
electron-proElectron desktop apps with native OS integration and distribution.
cli-developerCommand-line tools with intuitive design and cross-platform support.

Architecture & API Design

AgentDescription
architect-reviewerSystem design validation, architectural patterns, and scalability analysis.
api-designerScalable, developer-friendly REST and GraphQL API design.
graphql-architectGraphQL schema design, federation, and query performance.
microservices-architectDistributed microservice ecosystems and communication patterns.
websocket-engineerScalable real-time WebSocket architectures and low-latency messaging.
database-architectData layer design, technology selection, and schema modeling.

Data & Databases

AgentDescription
database-administratorHigh-availability DBs, performance tuning, and disaster recovery.
database-optimizerQuery optimization, indexing, caching, and partitioning.
postgres-proPostgreSQL performance, replication, and advanced features.
data-engineerScalable data pipelines, ETL/ELT, and data infrastructure.
data-analystBusiness data insights, dashboards, and statistical analysis.
data-scientistStatistical analysis, ML, and data storytelling.
data-researcherDiscover, collect, and validate data from multiple sources.

AI / ML

AgentDescription
ai-engineerAI system design, model implementation, and production deployment.
ml-engineerProduction ML training pipelines, serving, and retraining.
machine-learning-engineerModel deployment, serving infrastructure, and edge inference.
mlops-engineerML infrastructure, CI/CD, versioning, and experiment tracking.
llm-architectProduction LLM systems, fine-tuning, RAG, and inference serving.
nlp-engineerNLP/NLU/NLG with transformer models and production pipelines.
prompt-engineerDesign, optimize, and evaluate prompts for production LLMs.
mcp-developerModel Context Protocol server and client development.

Infrastructure / DevOps / Cloud

AgentDescription
cloud-architectMulti-cloud (AWS/Azure/GCP) IaC, FinOps, and architecture.
devops-engineerCI/CD, containerization, monitoring, and automation.
deployment-engineerCI/CD pipelines and zero-downtime deployment strategies.
platform-engineerInternal developer platforms, golden paths, and self-service.
kubernetes-architectCloud-native K8s, GitOps, service mesh, and multi-tenancy.
kubernetes-specialistProduction-grade K8s deployments and cluster management.
docker-expertContainer image building, optimization, and orchestration.
terraform-engineerMulti-cloud Terraform IaC and state management.
terragrunt-expertTerragrunt orchestration and DRY multi-environment IaC.
azure-infra-engineerAzure infrastructure, Entra ID, Bicep, and PowerShell automation.
network-engineerCloud/hybrid network design, security, and troubleshooting.
cost-optimizerCloud cost analysis, resource optimization, and scaling plans.
windows-infra-adminWindows Server, Active Directory, DNS, DHCP, and Group Policy.
iot-engineerConnected device architectures, edge computing, and IoT platforms.

PowerShell / Windows Automation

AgentDescription
powershell-5.1-expertPowerShell 5.1 Windows automation with RSAT modules.
powershell-7-expertCross-platform PowerShell 7+ cloud automation and CI/CD.
powershell-module-architectPowerShell module architecture and reusable automation libraries.
powershell-security-hardeningHardening PowerShell automation and remoting security.
powershell-ui-architectWinForms/WPF/TUI interfaces for PowerShell tools.

Reliability / Operations / Incident Response

AgentDescription
sre-engineerSLOs, automation, and resilient self-healing systems.
observability-engineerMonitoring, logging, tracing, and SLI/SLO management.
incident-responderActive security breach and outage response and recovery.
devops-incident-responderProduction incident diagnosis and postmortems.
chaos-engineerControlled failure experiments and resilience validation.
error-detectiveDiagnose errors, correlate across services, and find root causes.
debuggerDiagnose and fix bugs from error logs and stack traces.

Security

AgentDescription
security-engineerDevSecOps, cloud security, and zero-trust architecture.
security-auditorSecurity assessments, compliance validation, and risk management.
security-specialistMobile (RN/Expo) security audits and OWASP Mobile Top 10.
penetration-testerAuthorized offensive testing and vulnerability exploitation.
ad-security-reviewerActive Directory security posture and privilege escalation audit.
compliance-auditorGDPR, HIPAA, PCI DSS, SOC 2, and ISO compliance.

Quality / Review / Testing

AgentDescription
code-reviewerCode quality, security, and best-practice review across languages.
senior-code-reviewerComprehensive senior-level fullstack code review.
qa-expertTest strategy, manual/automated testing, and quality metrics.
test-automatorAutomated test frameworks and CI/CD test integration.
test-generatorSmart test generation for RN/Expo with ROI prioritization.
refactoring-specialistTransform complex/duplicated code while preserving behavior.
legacy-modernizerIncremental legacy migration and technical-debt reduction.
dependency-managerDependency auditing, conflict resolution, and bundle optimization.

Performance & Build

AgentDescription
performance-engineerSystem optimization, profiling, and scalability engineering.
performance-optimizerBottleneck identification and workload optimization.
performance-enforcerBundle size and performance budget tracking for RN/Expo.
performance-prophetPredictive performance analysis for RN/Expo before deployment.
build-engineerBuild performance optimization and faster compilation.
dx-optimizerDeveloper workflow, feedback loops, and DX metrics.
tooling-engineerDeveloper tools, CLIs, code generators, and IDE extensions.
git-workflow-managerGit workflows, branching strategies, and merge management.

UI / UX / Accessibility / Design

AgentDescription
ui-designerVisual interfaces, design systems, and component libraries.
ux-researcherUser research, usability testing, and persona development.
accessibility-testerWCAG compliance and assistive-technology testing.
a11y-enforcerWCAG 2.2 accessibility enforcement for RN/Expo apps.
design-token-guardianDetect hardcoded styles and enforce design tokens in RN/Expo.

Documentation

AgentDescription
documentation-engineerDocumentation-as-code systems and automated generation.
documentation-specialistREADMEs, API specs, architecture guides, and user manuals.
technical-writerAPI references, user guides, and SDK documentation.

Specialized Engineering

AgentDescription
fintech-engineerFinancial systems, payments, and regulatory compliance.
slack-expertSlack apps, API integrations, and bot security review.

Product / Business / Research

AgentDescription
product-managerProduct strategy, feature prioritization, and roadmaps.
project-managerProject plans, risk management, and stakeholder coordination.
scrum-masterAgile facilitation, ceremonies, and velocity improvement.
business-analystBusiness process analysis and requirements gathering.
customer-success-managerCustomer health, retention, and lifetime value.
sales-engineerTechnical pre-sales, solution architecture, and POCs.
content-marketerSEO content strategy and multi-channel campaigns.
legal-advisorContracts, compliance, IP strategy, and legal risk.
market-researcherMarket analysis, consumer behavior, and opportunity sizing.
competitive-analystCompetitor analysis and competitive positioning.
research-analystMulti-source research synthesis and trend identification.
trend-analystEmerging patterns, industry shifts, and future scenarios.
search-specialistAdvanced search strategies and targeted information retrieval.
scientific-literature-researcherEvidence-grounded answers from full-text research papers.

🧩 Skills

197 skills, each packaged as a directory containing a SKILL.md (and supporting scripts/templates). Skills trigger automatically based on their descriptions. Grouped below by domain.

SkillDescription
cavemanUltra-compressed communication mode (~75% token reduction). Lite / full / ultra / wenyan variants. Trigger: /caveman.
caveman-commitTerse Conventional Commits messages. ≤50-char subject, body only when "why" isn't obvious. Trigger: /caveman-commit.
caveman-compressCompress .md memory files to caveman prose (~46% input-token savings). Backs up originals. Trigger: /caveman-compress <file>.
caveman-helpQuick-reference card for all caveman modes, skills, and commands. One-shot display. Trigger: /caveman-help.
caveman-reviewUltra-compressed PR review: one line per finding — location, problem, fix. Trigger: /caveman-review.
caveman-statsShow real token usage and estimated savings for the current session via hook. Trigger: /caveman-stats.
cavecrewDecision guide for delegating to caveman-style subagents (~60% smaller tool results vs vanilla agents).
SkillDescription
brainstormingExplore intent, requirements, and design before any creative/build work.
writing-plansTurn a spec into a multi-step implementation plan before coding.
executing-plansExecute a written plan in a separate session with review checkpoints.
subagent-driven-developmentExecute plans with independent tasks in the current session.
dispatching-parallel-agentsHandle 2+ independent tasks with no shared state in parallel.
test-driven-developmentTDD before writing implementation code for features/bugfixes.
systematic-debuggingStructured debugging before proposing fixes.
verification-before-completionRequire verification commands before claiming work is done.
requesting-code-reviewVerify work meets requirements before merging.
receiving-code-reviewRigorously evaluate review feedback before implementing.
finishing-a-development-branchDecide how to integrate completed work (merge/PR/cleanup).
using-git-worktreesCreate isolated workspaces via git worktrees.
using-superpowersEstablish how to find and use skills at conversation start.
writing-skillsCreate, edit, and verify skills before deployment.
skill-creatorCreate, improve, eval, and benchmark skills.
autoskillObserve workflows via screenpipe and draft new skills.
pi-agentBuild with and use the Pi minimal terminal coding harness.
mcp-builderBuild high-quality MCP servers (Python FastMCP / TS SDK).
claude-apiReference for the Claude API / Anthropic SDK: model IDs, pricing, params, streaming, tool use.
SkillDescription
building-native-uiBuild apps with Expo Router: styling, navigation, animations.
native-data-fetchingNetwork requests, React Query/SWR, caching, and offline support.
add-app-clipAdd an iOS App Clip target to an Expo app.
expo-api-routesCreate API routes in Expo Router with EAS Hosting.
expo-brownfieldIntegrate Expo/React Native into existing native apps.
expo-cicd-workflowsAuthor EAS workflow YAML for build/deploy pipelines.
expo-deploymentDeploy Expo apps to App Store, Play Store, and web.
expo-dev-clientBuild and distribute Expo development clients.
expo-moduleBuild Expo native modules/views (Swift, Kotlin, TS).
expo-observeAdd and query EAS Observe performance metrics.
expo-tailwind-setupSet up Tailwind v4 / NativeWind v5 in Expo.
expo-ui-jetpack-composeUse Jetpack Compose views via @expo/ui.
expo-ui-swift-uiUse SwiftUI views via @expo/ui.
eas-update-insightsCheck EAS Update health: crash rates, installs, payload size.
upgrading-expoUpgrade Expo SDK versions and fix dependency issues.
use-domRun web code in a webview via Expo DOM components.
SkillDescription
frontend-designDistinctive, intentional visual design for new/existing UI.
web-artifacts-builderBuild complex multi-component HTML artifacts (React/Tailwind/shadcn).
web-asset-generatorGenerate favicons, app icons (PWA), and Open Graph images.
canvas-designCreate visual art in PNG/PDF using design philosophy.
algorithmic-artGenerative/algorithmic art with p5.js.
theme-factoryStyle artifacts (slides, docs, HTML) with preset/custom themes.
brand-guidelinesApply Anthropic brand colors and typography to artifacts.
generate-imageGenerate/edit images with AI (FLUX, Nano Banana 2).
infographicsCreate professional infographics with AI and iterative refinement.
slack-gif-creatorCreate animated GIFs optimized for Slack.
playwright-test-automationBrowser automation and testing with Playwright.
webapp-testingTest/debug local web apps with Playwright.
SkillDescription
docxCreate, read, and edit Word (.docx) documents.
pptxCreate, read, and edit PowerPoint (.pptx) presentations.
xlsxOpen, read, edit, and create spreadsheets (.xlsx/.csv/.tsv).
pdfRead, merge, split, fill, OCR, and create PDF files.
markitdownConvert office/media files to Markdown.
liteparseLocal PDF/DOC parsing with bounding boxes and OCR for RAG.
doc-coauthoringStructured workflow for co-authoring documentation.
markdown-mermaid-writingMarkdown + Mermaid diagram writing standards.
slides-generatorBuild animation-rich HTML presentations (or convert PPT).
internal-commsWrite internal communications (status reports, updates, FAQs).
SkillDescription
research-lookupLook up current research via parallel-cli / Parallel Chat / Perplexity.
paper-lookupSearch 10 academic paper databases via REST APIs.
database-lookupSearch 78 public scientific/biomedical/economic database APIs.
literature-reviewSystematic literature reviews across academic databases.
citation-managementSearch, validate, and format citations / BibTeX.
pyzoteroManage Zotero reference libraries via the Web API.
exa-searchWeb/scholarly search and URL extraction via Exa.
parallel-webWeb search, extraction, enrichment, and deep research via parallel-cli.
bgpt-paper-searchSearch papers with structured experimental data via BGPT MCP.
open-notebookSelf-hosted NotebookLM alternative for research/document analysis.
paperzillaProject/paper recommendations and summaries in Paperzilla.
scholar-evaluationEvaluate scholarly work with the ScholarEval framework.
peer-reviewStructured, checklist-based manuscript/grant review.
scientific-critical-thinkingEvaluate scientific claims and evidence quality.
scientific-brainstormingCreative research ideation and interdisciplinary exploration.
hypothesis-generationFormulate testable hypotheses from observations.
hypogenicAutomated LLM-driven hypothesis generation/testing on data.
consciousness-councilMulti-perspective "Mind Council" deliberation on decisions.
what-if-oracleStructured What-If scenario branch analysis.
dhdna-profilerExtract cognitive/thinking patterns from text.
SkillDescription
scientific-writingWrite scientific manuscripts in IMRAD prose with citations.
scientific-slidesBuild research talk decks (PowerPoint / Beamer).
scientific-schematicsPublication-quality scientific diagrams via AI.
scientific-visualizationPublication-ready multi-panel figures with journal styling.
latex-postersResearch posters in LaTeX (beamerposter/tikzposter/baposter).
pptx-postersResearch posters in HTML/CSS exported to PDF/PPTX.
venue-templatesLaTeX templates for journals, conferences, posters, grants.
research-grantsWrite competitive NSF/NIH/DOE/DARPA/NSTC proposals.
market-research-reportsConsulting-style market research reports (50+ pages).
SkillDescription
exploratory-data-analysisEDA across 200+ scientific file formats with reports.
statistical-analysisGuided test selection, assumptions, and APA reporting.
statsmodelsStatistical models (OLS, GLM, mixed, ARIMA) with diagnostics.
scikit-learnSupervised/unsupervised ML, pipelines, and tuning.
shapModel interpretability/explainability with SHAP.
umap-learnNonlinear dimensionality reduction and embeddings.
matplotlibLow-level fully customizable plotting.
seabornStatistical visualization with pandas integration.
polarsHigh-performance DataFrame ETL/analytics.
daskDistributed/larger-than-RAM pandas/NumPy workflows.
vaexOut-of-core DataFrames for billions of rows.
networkxCreate, analyze, and visualize graphs/networks.
sympyExact symbolic math (algebra, calculus, solving).
matlabMATLAB/Octave numerical computing and visualization.
pymcBayesian modeling and MCMC/variational inference.
pymooMulti-objective optimization (NSGA-II/III, MOEA/D).
simpyProcess-based discrete-event simulation.
aeonTime series ML (classification, forecasting, clustering).
timesfm-forecastingZero-shot time series forecasting with TimesFM.
scikit-survivalSurvival analysis and time-to-event modeling.
usfiscaldataQuery the U.S. Treasury Fiscal Data REST API.
get-available-resourcesDetect CPU/GPU/memory/disk and recommend a compute strategy.
SkillDescription
transformersHugging Face Transformers inference and fine-tuning.
pytorch-lightningOrganize PyTorch with Lightning for scalable training.
torch-geometricGraph neural networks with PyTorch Geometric.
stable-baselines3Standard RL algorithms with a scikit-learn-like API.
pufferlibHigh-performance parallel/multi-agent RL.
optimize-for-gpuGPU-accelerate Python (CuPy, Numba, cuDF, cuML, etc.).
modalServerless cloud GPU compute with the Modal SDK.
hugging-scienceDiscover scientific datasets/models/Spaces on Hugging Face.
SkillDescription
biopythonMolecular biology toolkit: sequences, parsing, NCBI access.
bioservicesUnified interface to 40+ bioinformatics services.
ggetFast CLI/Python queries to 20+ bioinformatics databases.
pysamRead/write SAM/BAM/CRAM/VCF/FASTA for NGS pipelines.
scanpyStandard single-cell RNA-seq analysis pipeline.
anndataAnnotated matrix data structure for single-cell.
scvi-toolsDeep generative models for single-cell omics.
scveloRNA velocity analysis for single-cell trajectories.
cellxgene-censusQuery CZ CELLxGENE Census for single-cell data.
bulk-rnaseqEnd-to-end bulk RNA-seq orchestration (FASTQ to DEG).
pydeseq2Differential gene expression for bulk RNA-seq.
pathway-enrichmentPathway/gene-set enrichment analysis (ORA/GSEA).
arboretoInfer gene regulatory networks (GRNBoost2, GENIE3).
genimlML on genomic interval data (region embeddings, scATAC).
gtarsHigh-performance genomic interval analysis (Rust).
polars-bioGenomic interval ops and bioinformatics I/O on Polars.
deeptoolsNGS analysis: bigWig, QC, heatmaps for ChIP/RNA/ATAC-seq.
pyopenmsMass spectrometry / proteomics analysis platform.
matchmsSpectral similarity and compound ID for metabolomics.
flowioParse FCS flow cytometry files.
scikit-bioMicrobiome analysis: alignments, diversity, ordination.
phylogeneticsBuild/analyze phylogenetic trees (MAFFT, IQ-TREE, FastTree).
etetoolkitPhylogenetic tree manipulation and visualization (ETE).
cobrapyConstraint-based metabolic modeling (FBA/FVA).
esmESM3/ESMC protein models and ESMFold folding.
glycoengineeringAnalyze/engineer protein glycosylation.
tiledbvcfScalable genomic variant storage/query with TileDB.
lamindbLineage-native lakehouse for biological datasets/models.
depmapCancer Dependency Map gene/drug dependency queries.
primekgQuery the Precision Medicine Knowledge Graph.
nextflowBuild/run Nextflow and nf-core bioinformatics pipelines.
pacsomaticOperate nf-core/pacsomatic tumor-normal workflows.
SkillDescription
rdkitCheminformatics toolkit for fine-grained molecular control.
datamolPythonic RDKit wrapper for standard drug discovery.
deepchemMolecular ML with featurizers and MoleculeNet datasets.
torchdrugPyTorch GNNs for molecules and proteins.
molfeatMolecular featurization for ML (100+ featurizers).
medchemMedicinal chemistry filters and compound triage.
pytdcTherapeutics Data Commons AI-ready drug datasets.
diffdockDiffDock molecular docking and pose prediction.
molecular-dynamicsMD simulations with OpenMM and MDAnalysis.
rowanCloud-native molecular modeling workflow platform.
SkillDescription
astropyAstronomy/astrophysics workflows with Astropy.
pymatgenMaterials science: structures, phase diagrams, band structure.
fluidsimComputational fluid dynamics simulations.
qiskitIBM quantum computing framework.
cirqGoogle quantum computing framework.
pennylaneHardware-agnostic quantum ML with autodiff.
qutipOpen quantum systems simulation.
zarr-pythonChunked N-D arrays for cloud storage.
geomasterRemote sensing, GIS, and spatial ML.
geopandasGeospatial vector data analysis.
SkillDescription
pydicomRead/write/anonymize DICOM medical imaging files.
pyhealthClinical/healthcare deep-learning pipelines.
neurokit2Biosignal processing (ECG, EEG, EDA, PPG, EMG).
neuropixels-analysisNeuropixels extracellular recording analysis.
clinical-decision-supportCDS documents: cohort analyses and treatment reports.
clinical-reportsCase/diagnostic/trial reports (CARE, ICH-E3, SOAP).
treatment-plansFocused medical treatment plans in LaTeX/PDF.
iso-13485-certificationISO 13485 medical device QMS documentation.
imaging-data-commonsQuery/download NCI Imaging Data Commons.
histolabWSI tile extraction and preprocessing.
pathmlFull-featured computational pathology toolkit.
bidsBrain Imaging Data Structure (BIDS) tooling.
SkillDescription
opentrons-integrationOpentrons OT-2/Flex protocol API.
pylabrobotVendor-agnostic lab automation framework.
ginkgo-cloud-labSubmit/manage protocols on Ginkgo Bioworks Cloud Lab.
benchling-integrationBenchling SDK/API for registry, inventory, and ELN.
labarchive-integrationLabArchives electronic lab notebook API.
protocolsio-integrationprotocols.io API for scientific protocol management.
omero-integrationOMERO microscopy data management platform.
dnanexus-integrationDNAnexus cloud genomics platform.
latchbio-integrationLatch bioinformatics workflow platform.
adaptyvAdaptyv Bio Foundry API for protein experiments.

⚙️ Settings

The settings/ directory contains platform-specific Claude Code configuration files:

FilePlatformStatus Line Script
settings-bash.jsonLinux / macOS~/.claude/statusline.sh
settings-powershell.jsonWindowspowershell … statusline.ps1 (username injected at install time)
settings.jsonGeneric fallback~/.claude/statusline.sh

All three files share the same base configuration and include a hooks.PreToolUse section that wires the two pre-tool-use hooks (see Hooks below).

env — environment variables that tune the Claude Code harness:

VariableValueWhat it does
CLAUDE_AUTOCOMPACT_PCT_OVERRIDE70Triggers automatic context compaction once the context window reaches 70% usage (instead of the higher default), keeping more room before the limit.
BASH_MAX_OUTPUT_LENGTH20000Maximum number of characters captured from a Bash command's output before it is truncated. Raised so long command outputs aren't cut short.
MAX_MCP_OUTPUT_TOKENS8000Caps the number of tokens returned by MCP (Model Context Protocol) tool calls, preventing a single MCP response from flooding the context.
CLAUDE_CODE_EFFORT_LEVELmediumSets the default reasoning/effort level Claude applies to tasks (low / medium / high), balancing speed against thoroughness.

Other keys:

  • permissions.deny — read guardrails that block sensitive/noisy paths (./secrets/**, node_modules, build/dist/coverage/.next, logs, *.log).
  • statusLine — runs the platform-specific status line script (model, dir, git branch, context bar, cost, rate limits).
  • theme — dark.
  • model — sonnet[1m] (Sonnet with 1 million token context window).

Adjust model, theme, and the permission lists to match your own environment before relying on them.

A settings.local.json (machine-local permission overrides) is intentionally not tracked in this repo — it is git-ignored. Create your own at ~/.claude/settings.local.json if you need per-machine permission allowlists.


🪝 Hooks

The hooks/ directory contains Node.js scripts that Claude Code executes automatically at defined lifecycle events. Only the pre-tool-use hooks are wired into settings.json — the others (post-tool-use, notification) must be added manually if you want them.

Requirement: Node.js ≥ 18 must be on your PATH. The hooks use only built-in Node.js modules (fs, path, child_process) — no npm install needed.

Pre-Tool-Use hooks (active by default)

These run before Claude executes a tool call and can block the action entirely.

HookMatcherWhat it blocks
block-dangerous-commands.jsBashCatastrophic shell commands: rm -rf ~, dd to disk, fork bombs, force-push to main, git reset --hard, chmod 777, env dumps, and more. Configurable via SAFETY_LEVEL (critical / high / strict).
protect-secrets.jsRead|Edit|Write|BashAccess to sensitive files (.env, SSH keys, AWS/GCP/Azure credentials, keystores, .netrc, .npmrc, etc.) and bash commands that expose or exfiltrate secrets. Same SAFETY_LEVEL knob.

Post-Tool-Use hooks (optional)

Run after a tool call succeeds. Not wired into settings.json by default.

HookMatcherWhat it does
auto-stage.jsEdit|WriteAutomatically runs git add <file> after every file edit so git status always reflects exactly what Claude changed.

Notification hooks (optional)

Run when Claude Code fires a notification event (permission prompts, idle, MCP dialogs). Not wired into settings.json by default.

HookWhat it does
notify-permission.jsSends a Slack message when Claude needs user input. Set CCH_SLA_WEBHOOK to your Slack Incoming Webhook URL.

Hook logs

All hooks write structured JSONL entries to ~/.claude/hooks-logs/YYYY-MM-DD.jsonl for audit and debugging.


📁 Repository Layout

claude-code-kit/
├── agents/      # 133 subagent .md definitions (+ CLAUDE.md, AGENTS-REFERENCE.md)
├── skills/      # 197 skill directories, each with a SKILL.md
├── hooks/
│   ├── pre-tool-use/   # block-dangerous-commands.js, protect-secrets.js
│   ├── post-tool-use/  # auto-stage.js
│   └── notification/   # notify-permission.js
├── settings/    # settings.json (global config)
└── README.md
Ver o original no GitHub

Bom para

Relacionados