Coding & Dev Tools
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
-
mxrsv Bundle Review HealthStructural health review of a repo — architecture and coupling, dependency risk, and drift between living docs/schema/config and the code. Use at a milestone, after a big refactor or merge, or as the first review on a never-reviewed repo; needs only the repo, no running app and no diff. Not for a specific change or diff (use /review-change), not for UX or runtime behavior (use /review-experience), not for a ship decision (use /review-release).
-
mxrsv Bundle Review ExperienceReview the real user experience of a running app in a real browser — walk the affected flows, force loading/error/empty states, check 375/768/1440, capture console and network evidence. Use after UI, navigation or flow changes when a dev or staging URL is reachable, or when the app is reported confusing or broken in actual use. Not for code-level bugs (use /review-change), not for architecture or docs health (use /review-health).
-
mxrsv Skill Codebase OnboardingUse when entering a new codebase, needing a fast architecture map, or generating onboarding notes from an unfamiliar project. Focuses on reconnaissance first, then targeted reads.
-
ysyecust Skill Hermes ImportsHermesデータインポート、マッピング、変換、およびデータインテグリティ検証。
-
agentic-in Bundle AudiocraftPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
-
awaik Bundle AI Markers Remove 3Legacy-алиас безопасной редакторской полировки русскоязычного AI-подобного или шаблонного текста с сохранением фактов, авторского голоса и публикационного качества. Использовать только при явном вызове $ai-markers-remove; для обычной редактуры использовать $human-editorial-polish. Не использовать для обхода AI-детекторов.
-
awaik Bundle Workspace Project Manager 3Управлять Пространствами LidFly и project-first памятью Workspace: проекты, provider entities, кампании, документы, решения, настройки, задачи и AI-автозапуски. Использовать для любой записи памяти или управления проектом с точным workspace_project_id.
-
ngocsangyem Bundle Mk Verify 2Unified verification: build → lint → test → type-check → coverage. Use for 'is it green' / 'run all checks'; auto-called by mk:cook. NOT for lint only (mk:lint-and-validate).
-
ngocsangyem Bundle Mk Careful 3Session-scoped guardrails warning before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, etc; user can override. NOT for scoping edits to a directory (mk:freeze).
-
ngocsangyem Skill Mk Nyquist 3Maps test coverage to plan acceptance criteria and flags requirements with no tests. Use during Test/Review phases. NOT for running tests (mk:testing); NOT for structural review (mk:review).
-
ngocsangyem Bundle Mk Testing 2Writing tests, running validation, and (TDD mode) red-green-refactor. Active in Test + Build phases. NOT for coverage-gap mapping (mk:nyquist) or sprint contracts (mk:sprint-contract).
-
ngocsangyem Skill Mk Simplify 2Post-build pass reducing complexity without changing behavior. Catches dead code, needless abstractions, over-engineering. NOT for style (mk:clean-code) or diff review (mk:review).
-
ngocsangyem Skill Mk Validate Plan 3Validates an approved plan across 8 dimensions before build — incomplete acceptance criteria, missing dependencies, unresolved risks. Use after Gate 1, before Test.
-
ngocsangyem Bundle Mk Project Context 3Generate or update docs/project-context.md — the source of truth for conventions, tech stack, and anti-patterns, loaded by all agents as a constitution.
-
ngocsangyem Bundle Mk Lint And Validate 2Linting and static analysis after code edits. Triggers on lint, format, check, validate, types. NOT for full build verification (mk:verify) or test coverage (mk:testing).
-
ngocsangyem Bundle Mk Document Release 3Post-ship docs sync: cross-reference the diff and update README/ARCHITECTURE/CONTRIBUTING/AGENTS.md + CHANGELOG to match what shipped. Use on 'update/sync docs'; suggest after a PR opens.
-
ngocsangyem Bundle Mk Sequential Thinking 2Structured step-by-step reasoning before acting, to avoid guessing. For complex debugging, multi-step analysis, hypothesis checks. NOT for being stuck on approach (mk:problem-solving).
-
codyswanngt Skill Lisa Migrate 3Migrate an existing hand-rolled wiki onto the lisa-wiki kernel — phased and compatibility-first, with a strict no-loss guarantee (renaming is fine; losing functionality or data is not). Ends by running /doctor.
-
codyswanngt Skill Lisa Add Role 3Scaffold a domain-expert digital-staff role over the wiki — a dual-runtime subagent (Claude + Codex) plus a staff doc page — from a config.staff[] entry. The plugin only sets the subagent up; running/scheduling it is out of scope.
-
codyswanngt Skill Lisa Add Ingest 3Scaffold a project-specific front-door ingest skill that does something unique (classify a source, fetch from a special system, stamp domain frontmatter) and then chains into /ingest. Extends ingestion without forking the kernel.
-
codyswanngt Skill Lisa Connect Repo Topic 3Bind a Telegram forum topic to an OpenClaw dispatcher+worker pair that runs a coding CLI against a repo (single-repo or folder-scoped), so you can drive code work from chat. Requires /lisa:setup-openclaw first.
-
bioconductor Bundle Adr AuthorWrite a new Architecture Decision Record following the established Nygard format and conventions.
-
bioconductor Bundle Bioc HowtoA consolidated index of Bioconductor how-to skills covering genomics, sequencing, and omics data analysis tasks
-
bioconductor Bundle Bioc Pkg DevGuide an R package or a set of analysis scripts through Bioconductor submission: the pre-submission gate, the Contributions tracker, and post-acceptance maintenance
-
bioconductor Skill Update R NewsDraft or update an R package NEWS file from git commit history, examining diffs when commit messages are vague
-
bioconductor Skill Analyze R PackageAnalyze R/Bioconductor package structure to extract key information about its purpose, exports, and characteristics
-
bioconductor Skill Build Check BioccheckRun and interpret R CMD build, R CMD check, and both BiocCheck entry points against a Bioconductor package, separating real defects from environment gaps and known false positives
-
chakhdz Skill Theme FactoryToolkit for styling artifacts with a theme. 10 presets or a new one. Plan first, then wait for yes. Never delete.
-
chakhdz Skill Images By AuthorUse when the user gives a list of photographers for Photo Finder: open photo archives only (Commons, Openverse, Flickr, LOC, INAH). Not museum APIs. ≥20 photos, Author_Year_Series. Never delete. Not Pinterest.
-
chakhdz Skill Plan Then ConfirmUse on any file move, rename, download, catalog write, or skill run: first a very simple plan, then wait for the user to confirm before executing.
-
chakhdz Skill Catalog Close ReadingUse when qualitatively analyzing museum object records or a catalog corpus with an academic codebook. First a simple plan before downloads or exports; wait for yes. Do not call museum texts essays.
-
chakhdz Skill Analyze And ReorganizeUse when reorganizing a disk. First a very simple plan, then wait for “yes”. Look inside folders before grouping. Logs in LOG/. Never delete.
-
mine-fnl Skill Wireguard VpnUse when setting up a WireGuard VPN on a Linux server or client, when troubleshooting a WireGuard handshake, or when migrating from an OpenVPN / IPSec deployment. Applies when the user asks for "WireGuard setup", "wireguard endpoint", "wg-quick", or "kernel VPN tunnel". Do not use for IPSec tunnels, for managed SaaS VPN products (Tailscale, Cloudflare Tunnel), or for non-Linux platforms.
-
mine-fnl Skill Git Bisect BugsUse when a regression has been introduced in a long-lived codebase and the user knows the bug is present in `HEAD` but absent in some older release. Applies when the user asks for "find the bad commit", "git bisect", "binary search the history", or "which commit introduced this bug". Do not use for bug hunts that do not have a known-good commit (use `git log -S` or a manual review), or for bisecting test runtime rather than correctness.
-
mine-fnl Skill Postgres MigrationsUse when authoring or reviewing a PostgreSQL schema migration that runs against a live production database. Applies when the user asks for "add a column", "add an index", "backfill", "ALTER TABLE safely", or "zero-downtime migration". Do not use for application-level ORM migrations on a dev database, for greenfield schemas with no traffic, or for non-PostgreSQL databases (MySQL, SQLite).
-
mine-fnl Skill Python Package ReleaseUse when releasing a new version of a Python package — bumping version, cutting a tag, publishing to PyPI, writing the changelog, or announcing the release. Triggers: "cut a release", "publish to PyPI", "bump version", "this is ready to ship", "tag and release". Do not use for first-time repo setup, for the inner loop of writing code, or for releasing non-Python artifacts.
Frequently asked questions
What are Coding & Dev Tools agent skills?
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Which Coding & Dev Tools skills are most installed?
Popular Coding & Dev Tools skills on SkillMD right now include python-package-release, hermes-imports, review-health. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Coding & Dev Tools skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.