convez.ai
SkillDesenvolvimento WebIntermediário
nicholashidalgo

Claude Skillforge

nicholashidalgo/claude-skillforge

Biblioteca modular de skills battle-tested para Claude com carregamento sob demanda

Ver no GitHub
InicialPluginScore · de 0 a 100

Biblioteca de production-ready de Claude Skills modulares e reutilizáveis, cobrindo engenharia de dados, escrita profissional e ferramentas de carreira. Cada skill é uma pasta auto-contida com instruções YAML que Claude carrega dinamicamente sob demanda, economizando tokens através de divulgação progressiva.

Instalação

$npx convez-ai nicholashidalgo/claude-skillforge

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
1
Forks
0
Acompanhando
0
Saúde
57%
Último commit
há 6 meses
Versão
v1.0.0
Issues abertas
2
Contribuidores
4

Casos de uso

  • Estender capacidades do Claude com instruções especializadas reutilizáveis
  • Implementar workflows profissionais padronizados (escrita, análise de dados, career coaching)
  • Gerenciar contexto eficientemente com skills que carregam apenas quando relevantes

Veredito

Skillforge é uma abordagem estruturada e pragmática para composição de comportamentos no Claude. O foco em production-readiness e economia de tokens via progressive disclosure diferencia de listas ad-hoc, mas carece de documentação abrangente no README para onboarding rápido de novos usuários.

README

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


What is this?

Claude Skillforge is a multi-category library of production-ready Claude Skills. It is not a writing-skills repo. It spans foundational operating standards, data engineering, professional writing, and career tools - every skill battle-tested in real workflows, not written as a demo.

Skills are instruction files that teach Claude how to perform specific tasks in a repeatable, high-quality way. They load on demand and cost roughly 100 tokens until activated.


What are Claude Skills?

Claude Skills are specialized instruction folders that Claude dynamically discovers and loads when relevant to a task. Each skill contains a SKILL.md file with YAML frontmatter (name and description for routing) and detailed execution instructions.

Skills use progressive disclosure: Claude scans metadata first (~100 tokens), loads full instructions only when the skill matches (~2-5K tokens), and accesses bundled resources only as needed. Multiple skills can be active simultaneously without overwhelming the context window.


How to install

Claude.ai (Web/Desktop)

  1. Go to Settings > Capabilities > Skills
  2. Upload skill folders or point to this repository

Claude Code (CLI)

git clone https://github.com/nicholasjh-work/claude-skillforge.git
# Copy desired skill folders into your project's .claude/skills/ directory

Manual Copy any skill folder into your Claude skills directory. Each folder is self-contained.


Spotlight

Skill of the Week

claude-token-watchdog

Watches conversation length and auto-fires a continuation handoff before you hit the token limit. Companion to claude-session-handoff.

Skill of the Month

scholar-editor

Detects and removes 38 documented AI writing patterns. Two modes: CLEAN for professional docs, VOICE for creative writing.

Updating the spotlight: edit this section in README.md. Replace the badge label-name-color and the description paragraph. Keep the for-the-badge style and category color (Core 0550ae, Data Engineering 0d6e3f, Writing b35900, Career 6f42c1).


Core

Foundational operating standards that govern how Claude behaves across all tasks.

SkillWhat it does
claude-operator-standardUniversal operating standard for Claude sessions. Governs communication style, troubleshooting method, output format, session behavior, and handoff protocol.
claude-code-standardTechnical execution standard for coding, SQL, Python, dbt, and data engineering. Covers stack preferences, documentation rules, testing, and analytics engineering guidance.
claude-session-handoffGenerates a structured handoff block that captures full technical state so a conversation can continue in a new window with zero re-explanation.
claude-token-watchdogWatches conversation length and fires a continuation handoff at three thresholds (15 / 20 / 25 messages). Delegates to claude-session-handoff at the forced threshold to avoid hitting Claude token or context limits. Manual command: /watchdog-check.

Data Engineering

Tools for data quality, SQL, reporting, KPI governance, and analytics engineering.

SkillWhat it does
data-defect-investigatorInvestigates data defects, mismatches, duplicates, null issues, broken joins, and reconciliation failures.
data-file-profilerProfiles CSV/Excel files: schema inspection, duplicate detection, null analysis, outliers, and data mismatches.
dataset-reconcilerCompares two datasets and explains count, amount, and field-level differences. Source vs target, old vs new, ERP vs DW.
report-output-validatorValidates report outputs, totals, grain, subtotals, and regression changes before release.
sql-join-risk-reviewerReviews schemas, joins, and SQL logic for grain violations, duplicate risk, orphan rows, and aggregation errors.
sql-report-query-builderBuilds production-grade SQL for reporting. Translates business requests into safe, auditable query logic.
kpi-definition-standardDefines KPIs with precise formulas, grain, source logic, exclusions, and governance notes.
report-requirements-translatorConverts messy business requests into clean report or dashboard specifications.

Writing

Professional and editorial writing tools for business communication, technical documentation, and AI prose cleanup.

SkillWhat it does
business-email-drafterDrafts natural business emails that are direct, specific, and free of canned language.
correction-email-drafterWrites correction, clarification, and reset emails that are precise, calm, and not defensive.
cover-letter-drafterWrites cover letters grounded in real experience and specific to the role.
linkedin-message-drafterWrites concise LinkedIn messages for recruiters, hiring managers, and networking.
executive-brief-drafterWrites short executive briefs: issue, impact, risk, and next step.
technical-to-business-summarizerTranslates technical findings into concise business-facing summaries for leadership.
stakeholder-status-updateWrites concise stakeholder updates on project status, issues, risks, and next steps.
internal-technical-doc-writerWrites internal technical documents, SOPs, incident notes, and decision memos.
incident-root-cause-writerWrites incident summaries separating facts, impact, root cause, and corrective action.
requirements-doc-drafterWrites requirements documents with scope, logic, assumptions, dependencies, and acceptance criteria.
meeting-to-decision-memoConverts meeting notes into decision memos with outcomes, owners, and next actions.
ai-writing-pattern-removerDetects and removes AI writing patterns based on Wikipedia's "Signs of AI writing" guide.
ai-prose-humanizerRemoves AI patterns and adds human voice to prose. Two modes: CLEAN for professional docs, VOICE for creative writing.

Career

Resume optimization, salary negotiation, and job application tools.

SkillWhat it does
resume-bullet-rewriterRewrites a single resume bullet to be metric-backed, action-verb-led, and free of banned phrases.
resume-bullet-editorEdits existing resume bullets to remove banned language, add metrics, and strengthen impact.
resume-section-writerWrites resume sections from raw notes, brain dumps, or bullet lists.
resume-one-page-optimizerATS-optimized one-page resume evaluator and rewriter. Scores, gaps, and full rewrite against a job description.
resume-two-page-optimizerATS-optimized two-page resume evaluator for senior/director/VP roles.
salary-negotiation-frameworkData-driven salary and total compensation negotiation framework. Covers tech, finance, PE/VC, healthcare, and B2B.

Design philosophy

These skills follow two layers of standards:

Standards-backed rules grounded in published engineering guidance (PEP 8, Twelve-Factor App, OWASP, dbt best practices, Microsoft Power BI documentation). See docs/rationale-and-references.md.

House operating conventions that are intentional working preferences for AI-assisted engineering: lead with the answer, sparse comments, no AI-style clutter, fixed output structures. These are not claimed as universal standards. See docs/adr/0001-ai-session-operating-standard.md.


Documentation

DocumentPurpose
docs/rationale-and-references.mdStandards-backed justification for skill rules with source citations
docs/adr/0001-ai-session-operating-standard.mdArchitecture Decision Record explaining why these standards exist

Contributing

Contributions welcome. See CONTRIBUTING.md for guidelines.


License

MIT License. See LICENSE for details.


Ver o original no GitHub

Bom para

Relacionados