Analyze codebase or documentation for code/text duplication using jscpd. Generates a Markdown report with collapsible sections (suitable for GitHub/Gitea issues) showing duplicate clusters, statistics, and a mediation plan proposing refactoring strategies.
Bisect git-annex regressions using tinuous CI logs, create reproducers, generate fix patches, and submit Red/Green PRs to datalad/git-annex. Use when investigating test failures in git-annex CI, creating reproducer scripts, or preparing upstream bug reports.
Annotate a paper or work with CRediT (Contributor Roles Taxonomy) author contributions and render the LaTeX byline. Creates a .tributors.credit.yaml overlay (single source of truth, compatible with con/tributors), seeds it from sibling repos' git history when present, renders the "Author Contributions" section into…
Check the health and maintenance status of a GitHub project. Use when user asks about project status, whether a project is maintained, abandoned, or looking for alternatives. Analyzes commit history, releases, issues, PRs, and searches for active forks or community discussions about project future.
Introduce codespell spell-checking to a project. Creates branch, config file, CI workflow (GitHub Actions or Forgejo Actions for Codeberg), pre-commit hook. Lists typos, helps identify paths/words to ignore, and fixes typos interactively. Use when setting up codespell in a new project.
Introduce git-bug distributed issue tracking to a git project. Configures GitHub bridge, syncs issues, pushes refs, and documents workflow in DEVELOPMENT.md and CLAUDE.md. Use when setting up git-bug in a new project.
Introduce REUSE specification compliance (LICENSES/ directory, REUSE.toml, SPDX headers) to a software project or BIDS dataset, then validate it. Covers BIDS data-vs-code separation, DUO (Data Use Ontology) integration, DEP-3 patch tagging for vendoring repos, and integration with tox / pre-commit / Makefile / GitHub…
Load a PR's review feedback (human + bot) and CI status, classify each comment, and recommend what to address vs dismiss with draft responses. CI failures (merge conflicts, lint, tests, workflow runs) are first-class — diagnose, propose a fix, and bundle into the same actionable report. Works from a local repo…
Analyze con/tinuous CI log collections to identify test regressions, compare successful vs failing runs, and provide investigation recommendations. Use when users mention test failures, CI regressions, or need to understand what changed between CI runs.
Introduce automated releases using intuit/auto to a project. Creates .autorc, GitHub Actions release workflow, GitHub labels (with optional prefix to avoid dependabot conflicts), CHANGELOG transition, and release documentation. Use when setting up auto-release for GitHub projects (Python/PyPI, JS/npm, or pure GitHub…
Set up Chromatic visual regression testing for a one- or multi-page web app, with Storybook stories for component and page states, Playwright snapshots of whole pages at several viewports, the two GitHub workflows and a README section. Use when asked to add Chromatic, Storybook, visual snapshots or visual regression…
Shared report conventions for the review skills (review-repo-code-quality, review-org-code-quality) — where a dated review report goes, the provenance stamp recording which skill version produced it, evidence rules, handling of security-sensitive findings, re-review of a prior report, and confidence/status labels. Not…
Audit code health across an organization-wide ecosystem of similarly styled, interconnected data/ML/ETL pipelines or repositories. Focuses on systemic risk (template drift, contract fragility, cross-repo duplication, blast radius, bus factor) rather than single-repo code smells, and writes a dated report. Use when…
Functionality-preserving code-quality review of a single repository — dead code, duplication, consolidation, cleanup, and items needing verification — written as a dated Markdown report with per-finding location, proposed change, safety confidence, and a verification command. Use when asked to review, audit, or assess…
Create, update, package, and validate reusable skills specifically for distribution through APM, including maintenance in con/skills or another dedicated skill repository. Use when APM distribution or maintenance of that published collection is requested. Do not trigger for a generic request to create a skill, a…
Install, update, or migrate skills from any APM-compatible source at project or user scope. Keeps dependency metadata reproducible and generated copies separate from source development.
Security audit of a Claude Code skill directory. Reads SKILL.md and any bundled scripts, checks for prompt injection vectors, capability mismatch, dangerous permissions, exfiltration patterns, and unsafe subprocess use. Emits a structured report. Use when reviewing a skill before merging or publishing.
Sweep repositories for open dependabot[bot] and pre-commit-ci[bot] pull requests, verify authors by account ID, gate on complete and passing CI, squash-merge the green ones guarded by the head SHA, assign the maintainer, and report the rest. Use for dependency-bot PR triage, on demand or on a schedule.
Revise prose that is difficult to follow in documentation, READMEs, reports, and chat. Use for clarity requests or complaints about unintelligible text, explanations that are hard to understand, excessive jargon, or dense language. Also use when the user asks for more humane, human friendly, or human-friendly…
Shared procedure a skill follows at the end of a run that showed the skill itself falling short (a result the user corrects by hand every time, a setup it cannot read, an input whose shape has changed). Reports suggested skill changes after the run's output and, in an attended run of a skill installed from con/skills…
★not rated 2 yesterdayA101 tokens
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: