The public, one-way copy of the Claude Code harness shimo4228 uses every day: skills, subagents, rules and commit hooks you can lift one at a time, with the dated decision records behind each piece.
Skill Claude Code
A workflow for recording an approved architecture decision as a numbered document in a project’s docs/adr folder. An ADR, or Architecture Decision Record, explains a decision, rejected alternatives, and consequences.
Skill Claude Code
Audit the /.claude/agents definitions and give each a verdict.
Skill Claude Code
A strategy framework for makers who want their work to be recognizable, traceable, and citable in the age of AI. It treats tools such as papers, DOIs, and software identifiers as ways to preserve and spread authorship.
Skill Claude Code
A research-material collection tool for gathering context from the current session, related past sessions, and project knowledge before writing an article. It creates a source-linked evidence record.
Skill Claude Code
Audit a repo's context documents (CLAUDE.md, ADRs, README, graph.jsonld) for role overlap and staleness against the code, and fix them; README findings are only flagged. Use when the docs may have drifted from the code or duplicate each other. For README content, use readme-writer.
Skill Claude Code
Audit the harness when a new Claude model takes a role (judge, build or everyday).
Skill Claude Code
Design lens: which layer a harness mechanism belongs in, and whether it outlives the next model or runtime.
Skill Claude Code
A one-way synchronisation process for exporting selected parts of a local AI harness to public Git repositories. It removes runtime files, checks metadata, scans for secrets, and copies approved components.
Skill Claude Code
A headline-idea generator for article titles, README taglines, subtitles, and social announcements. It creates candidates using clarity, concrete benefits, honest curiosity, and search or feed considerations.
Skill Claude Code
Mirror a research repo's graph.jsonld to its Hugging Face dataset as graph.jsonl. Use after the GitHub release step of release-doi, or to resync the dataset.
Skill Claude Code
A planning guide that classifies implementation work as a feature, bug fix, refactor, chore, prototype, or writing task, then chooses a matching sequence of planning, testing, review, documentation, and verification steps.
Skill Claude Code
Design and ship a JSON-LD knowledge graph (graph.jsonld) beside llms.txt that encodes a project's entities and relations as schema.org triples. Use when a project has a matrix, hierarchy or phase structure that prose leaves implicit and that stays stable across releases.
Skill Claude Code
A workflow for extracting reusable lessons from the current coding session and deciding where they should be saved. It can place a lesson in an existing skill, rule, or document, or promote it to a new skill.
Skill Claude Code
Design pattern for LLM-as-judge evaluators: binary checks as evidence, one named verdict.
Skill Claude Code
Write AI-facing documents (llms.txt, llms-full.txt, FAQ pages, glossaries) to the llms.txt standard. Use when a document's only reader is an AI system.
Skill Claude Code
A set of rules for making and reviewing claims based on measurements, thresholds, warnings, and experiment results. It focuses on what was observed, how much evidence exists, and whether a check is properly calibrated.
Skill Claude Code
Inject outside-angle prompts from creativity-technique catalogs when work is stuck in the same moves.
Skill Claude Code
A Japanese-to-English and English-to-Japanese translation tool for human-readable writing such as essays, research documents, READMEs, and architecture decision records.
Skill Claude Code
A writing tool for replies in public technical discussions, such as GitHub issues, pull requests, discussions, Hugging Face threads, and technical forums.
Skill Claude Code
Write, revise or judge a README, the page someone sees first when opening a repo, and keep the GitHub About in step with it. Use when a README is hard to read or overgrown, needs to follow a code change, or needs only a verdict.
Skill Claude Code
A release procedure for research repositories that publish versions with a DOI, a permanent identifier for scholarly work, through Zenodo.
Skill Claude Code
A checklist for starting bug fixes, unfinished tasks, and changes to data schemas or stored formats.
Skill Claude Code
Audit a repo's non-code assets (tool configs, CI workflows, runbooks, docs) for ones whose consumer is gone. Use when configs, workflows or runbooks may be dead.
Skill Claude Code
Move the mechanical items of a reviewer's checklist or past findings into a deterministic script.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: