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 GitHubSnapshot 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-harness1 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
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 byscripts/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
| Skill | Purpose |
|---|---|
| search-first | Research-before-coding workflow. Invokes the scout agent to discover existing tools |
| signal-first-research | Design guide for a research intake filter that admits only information likely to change your next action |
| learn-eval | Extracts reusable patterns from sessions, evaluates quality, and decides where to save |
| skill-stocktake | Skill quality audit. Quick Scan / Full Stocktake modes with parallel evaluation |
| rules-distill | Extracts cross-cutting principles from skills and promotes them to rules |
| skill-comply | Measures actual compliance of skills / rules / agents. Classifies behavioral sequences across 3 prompt strictness levels |
| context-sync | Audits and fixes project documentation. Detects role overlap, checks freshness, creates missing docs |
| llms-txt-writer | Writes AI-facing docs (llms.txt / llms-full.txt). Answer.AI standard + GEO/AEO static analysis |
| jsonld-knowledge-graph | Designs 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-ecosystem | Orchestrator for human-facing writing & review. Coordinates editor / essay-reviewer / fact-checker |
| write-prompt | Generates concise prompts via the lightweight prompt-writer agent |
| collect-context | Gathers in-session and external context into source material for article writing |
| authorship-strategy | 4-layer framework (Authenticity / Attribution diffusion / Idea-vs-scaffold / Tactics) for DOI-registered idea-rescue research repos |
| release-doi | Cuts a versioned release of a DOI-registered research repo (Zenodo concept DOI semantics, CHANGELOG / tag / asset packaging) |
| adr-writer | Records design decisions as numbered ADRs — directory detection, sequence numbering, index update; prose delegated to the adr-writer agent |
| paper-ecosystem | Orchestrator for academic paper writing & review — role boundaries for paper-writing plus five reviewer agents; holds Source Fidelity / Vocabulary / Voice / Clarity / Citation rules |
| paper-writing | Drafting procedure for academic papers — title, outline, section drafting, abstract, references with claim-cite 1:1 mapping |
| paper-deposit | Deposits 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-writer | Writes human-facing READMEs — deterministic structural lint plus holistic LLM review (no scores) |
| ja-to-en-translation | Voice-preserving JA→EN translation for essays, research docs, and READMEs — term-lock, 2-pass, back-translation QA |
| substack-publishing | Publishes reviewed essays to Substack and mirrors them to a corpus repo for LLM discovery |
| hf-sync | Mirrors graph.jsonld-bearing research repos to Hugging Face Datasets |
| wikidata-federation | Creates Wikidata items for researchers / papers / repos and cross-links QIDs with ORCID, DOI, and graph.jsonld |
| citation-sync | Audits the four citation layers of a research repo (docs / .zenodo.json / graph.jsonld / Wikidata P2860) and syncs them bottom-up |
| when-code-when-llm | Decision framework for deterministic code vs LLM processing — structural-vs-semantic axis, false-positive test |
| spawn-session | Launches a new detached Claude Code Remote Control session via tmux, visible in the mobile app session list |
| harness-sync | One-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
| Agent | Purpose |
|---|---|
| scout | Pre-implementation solution discovery. Searches npm / PyPI / MCP registries / GitHub for existing solutions |
| prompt-writer | Generates concise prompts using a lightweight model. Creates and rewrites LLM prompt templates |
| editor | Strict technical article editor. Rigorously reviews code accuracy, AI slop, narrative flow, and terminology consistency |
| essay-reviewer | Strict essay editor. Targets idea pieces mixing social theory / organizational analysis / design philosophy / personal narrative |
| fact-checker | Fact verification specialist. Extracts verifiable claims from articles and verifies them via web sources |
| adr-writer | Generates the 6-section ADR body from supplied input only — never invents context or alternatives |
| codemap-writer | Generates / refreshes docs/CODEMAPS/ — token-lean architecture documentation, ~1000 tokens per map |
| paper-reviewer | Academic paper structure review — argument flow, section transitions, claim sharpness, evidence-claim alignment |
| source-fidelity-checker | Reads each cited primary source directly and flags drift between paper claims and source content |
| vocabulary-consistency-checker | Verifies term definitions stay consistent and sub-classifications are explicit at introduction |
| clarity-reviewer | First-contact reader clarity review — coined-term budget, title-axis alignment, meta-commentary, insider-context dependency |
| citation-formatter | Verifies in-text citations against the reference list — format consistency, DOI / arXiv ID validity |
Rules
Behavioral principles auto-loaded every session (under rules/common/):
| Rule | Purpose |
|---|---|
| agents | Agent orchestration conventions. When to use which agent, parallel execution patterns |
| akc-cycle | Six-phase behavioral conventions of the Agent Knowledge Cycle (Research / Extract / Curate / Promote / Measure / Maintain) |
| authorship-strategy | Pointer rule activating the 4-layer authorship-strategy framework when working in DOI-registered idea-rescue research repos |
| planning | Required items for planning (What / Why / Alternatives). Mandates Phase 0 external research |
| skills | Skill origin tracking spec and knowledge placement principles |
| contemplative-axioms | Contemplative 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:
| origin | Meaning |
|---|---|
shimo4228 | Authored by shimo4228. The scope of this repo |
ECC | From Everything Claude Code. Not included here |
ECC-customized | ECC derivative + shimo4228 modifications. Not included |
auto-extracted | Learned 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.