convez.ai
SkillAutomaçãoAvançado
shimo4228

Claude Harness — Coleção de Skills e Agents

shimo4228/claude-harness

Kit completo de skills e agents para Claude Code — pesquisa, documentação e auditoria

Ver no GitHub
InicialPluginScore · de 0 a 100

Snapshot público de skills, agents e rules que shimo4228 usa diariamente no Claude Code. Inclui 10 skills especializadas (search-first, skill-stocktake, llms-txt-writer, adr-writer, paper-ecosystem, etc.) e 5 agents para fluxos de pesquisa, escrita, auditoria e documentação. Exportação via script de sincronização a partir de ~/.claude/.

Instalação

$npx convez-ai shimo4228/claude-harness

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
4
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 4 dias
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Automatizar fluxos de pesquisa antes de codificar (search-first)
  • Auditar qualidade de skills e conformidade com rules (skill-stocktake, skill-comply)
  • Gerar documentação AI-facing (llms.txt, JSON-LD, ADRs)
  • Orquestração de escrita técnica e acadêmica com múltiplos agents revisores
  • Extrair padrões reutilizáveis e elevar princípios a rules (rules-distill)

Veredito

Repositório maduro e bem-estruturado com 10+ skills prontos para produção em Python. Ideal para quem já usa Claude Code CLI/IDE e busca automação sofisticada de pesquisa, documentação e auditoria — exige familiaridade com o ecossistema Claude e boas práticas de engenharia de prompts.

README

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

Language: English | 日本語

claude-harness

Public snapshot of the Claude Code harness (skills / agents / rules) that shimo4228 uses day-to-day.

A mechanical aggregation of assets tagged origin: shimo4228 from ~/.claude/. ECC-derived material (origin: ECC / ECC-customized) and auto-extracted artifacts (origin: auto-extracted) are excluded.

Positioning

  • Audience: Claude Code (CLI + IDE extensions) users, and developers researching agent skill / rule ecosystems
  • Source of truth: ~/.claude/ is canonical; this repo is a one-way export produced by scripts/sync-from-local.sh (origin filter → secret scan → subtree replacement)
  • License: MIT. Free to copy, modify, and redistribute. Forking and customizing for personal use is encouraged

Contents

Skills

SkillPurpose
search-firstResearch-before-coding workflow. Invokes the scout agent to discover existing tools
signal-first-researchDesign guide for a research intake filter that admits only information likely to change your next action
learn-evalExtracts reusable patterns from sessions, evaluates quality, and decides where to save
skill-stocktakeSkill quality audit. Quick Scan / Full Stocktake modes with parallel evaluation
rules-distillExtracts cross-cutting principles from skills and promotes them to rules
skill-complyMeasures actual compliance of skills / rules / agents. Classifies behavioral sequences across 3 prompt strictness levels
context-syncAudits and fixes project documentation. Detects role overlap, checks freshness, creates missing docs
llms-txt-writerWrites AI-facing docs (llms.txt / llms-full.txt). Answer.AI standard + GEO/AEO static analysis
jsonld-knowledge-graphDesigns and ships a companion JSON-LD knowledge graph (graph.jsonld) next to llms.txt. Encodes domain entities and relationships as schema.org triples for LLM citation
writing-ecosystemOrchestrator for human-facing writing & review. Coordinates editor / essay-reviewer / fact-checker
write-promptGenerates concise prompts via the lightweight prompt-writer agent
collect-contextGathers in-session and external context into source material for article writing
authorship-strategy4-layer framework (Authenticity / Attribution diffusion / Idea-vs-scaffold / Tactics) for DOI-registered idea-rescue research repos
release-doiCuts a versioned release of a DOI-registered research repo (Zenodo concept DOI semantics, CHANGELOG / tag / asset packaging)
adr-writerRecords design decisions as numbered ADRs — directory detection, sequence numbering, index update; prose delegated to the adr-writer agent
paper-ecosystemOrchestrator for academic paper writing & review — role boundaries for paper-writing plus five reviewer agents; holds Source Fidelity / Vocabulary / Voice / Clarity / Citation rules
paper-writingDrafting procedure for academic papers — title, outline, section drafting, abstract, references with claim-cite 1:1 mapping
paper-depositDeposits a finished, reviewed paper to Zenodo as a standalone DOI record, optionally cross-posts to SSRN, cross-links the DOI back into the research repo
readme-writerWrites human-facing READMEs — deterministic structural lint plus holistic LLM review (no scores)
ja-to-en-translationVoice-preserving JA→EN translation for essays, research docs, and READMEs — term-lock, 2-pass, back-translation QA
substack-publishingPublishes reviewed essays to Substack and mirrors them to a corpus repo for LLM discovery
hf-syncMirrors graph.jsonld-bearing research repos to Hugging Face Datasets
wikidata-federationCreates Wikidata items for researchers / papers / repos and cross-links QIDs with ORCID, DOI, and graph.jsonld
citation-syncAudits the four citation layers of a research repo (docs / .zenodo.json / graph.jsonld / Wikidata P2860) and syncs them bottom-up
when-code-when-llmDecision framework for deterministic code vs LLM processing — structural-vs-semantic axis, false-positive test
spawn-sessionLaunches a new detached Claude Code Remote Control session via tmux, visible in the mobile app session list
harness-syncOne-way export of origin-filtered components from the live harness into this repo — collection, secret scan, subtree replacement

The first six (search-first, learn-eval, skill-stocktake, rules-distill, skill-comply, context-sync) are components of the Agent Knowledge Cycle (AKC). Each is also published as its own standalone repo, but they are bundled here so the harness can be read end-to-end.

Agents

AgentPurpose
scoutPre-implementation solution discovery. Searches npm / PyPI / MCP registries / GitHub for existing solutions
prompt-writerGenerates concise prompts using a lightweight model. Creates and rewrites LLM prompt templates
editorStrict technical article editor. Rigorously reviews code accuracy, AI slop, narrative flow, and terminology consistency
essay-reviewerStrict essay editor. Targets idea pieces mixing social theory / organizational analysis / design philosophy / personal narrative
fact-checkerFact verification specialist. Extracts verifiable claims from articles and verifies them via web sources
adr-writerGenerates the 6-section ADR body from supplied input only — never invents context or alternatives
codemap-writerGenerates / refreshes docs/CODEMAPS/ — token-lean architecture documentation, ~1000 tokens per map
paper-reviewerAcademic paper structure review — argument flow, section transitions, claim sharpness, evidence-claim alignment
source-fidelity-checkerReads each cited primary source directly and flags drift between paper claims and source content
vocabulary-consistency-checkerVerifies term definitions stay consistent and sub-classifications are explicit at introduction
clarity-reviewerFirst-contact reader clarity review — coined-term budget, title-axis alignment, meta-commentary, insider-context dependency
citation-formatterVerifies in-text citations against the reference list — format consistency, DOI / arXiv ID validity

Rules

Behavioral principles auto-loaded every session (under rules/common/):

RulePurpose
agentsAgent orchestration conventions. When to use which agent, parallel execution patterns
akc-cycleSix-phase behavioral conventions of the Agent Knowledge Cycle (Research / Extract / Curate / Promote / Measure / Maintain)
authorship-strategyPointer rule activating the 4-layer authorship-strategy framework when working in DOI-registered idea-rescue research repos
planningRequired items for planning (What / Why / Alternatives). Mandates Phase 0 external research
skillsSkill origin tracking spec and knowledge placement principles
contemplative-axiomsContemplative Constitutional AI clauses from Laukkonen et al. (2025), verbatim

Usage

Full install

git clone https://github.com/shimo4228/claude-harness.git ~/.claude-harness
# Copy skills / agents / rules into ~/.claude/
cp -r ~/.claude-harness/skills/* ~/.claude/skills/
cp -r ~/.claude-harness/agents/* ~/.claude/agents/
cp -r ~/.claude-harness/rules/common/* ~/.claude/rules/common/

Cherry-pick

Copy only what you want:

cp -r ~/.claude-harness/skills/search-first ~/.claude/skills/

Setup for skills with Python implementations

llms-txt-writer, skill-comply, rules-distill, and skill-stocktake ship with Python code. In each skill directory:

cd ~/.claude/skills/<skill-name>
uv sync  # or: pip install -e .

Origin tags

Each file's frontmatter (YAML or HTML comment) carries an origin field:

originMeaning
shimo4228Authored by shimo4228. The scope of this repo
ECCFrom Everything Claude Code. Not included here
ECC-customizedECC derivative + shimo4228 modifications. Not included
auto-extractedLearned skill auto-extracted by learn-eval. Not included

This repo is the result of a mechanical collection limited to origin: shimo4228.

Related repos

  • shimo4228 — Hub repo aggregating the three research lines (AKC / Contemplative Agent / AAP) and the supporting ecosystem
  • agent-knowledge-cycle — AKC concept and DOI release (Zenodo: 10.5281/zenodo.19200726)
  • contemplative-agent-rules — Rule implementation of Contemplative Constitutional AI
  • claude-skill-* standalone repos — Individual versions of each AKC skill (search-first / learn-eval / skill-stocktake / rules-distill / skill-comply / context-sync) plus the adjacent skills (llms-txt-writer / daily-research / jsonld-knowledge-graph / writing-ecosystem)

Contributing

This repo is shimo4228's personal harness artifact, so external PRs are not accepted. Instead:

  • Fork it and customize freely
  • Issues for questions or suggestions are welcome

Bug fixes flow upstream into ~/.claude/ when shimo4228 incorporates them.

License

MIT License. See LICENSE.

Ver o original no GitHub

Bom para

Relacionados