Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
railway-doctor
stars-end/agent-skills
-
git-safety-guard
Installs a Git safety guard hook for Claude Code to prevent destructive Git and filesystem commands.
Blocks accidental data loss from commands like 'git checkout --', 'git reset --hard', 'git clean -f', 'git push --force', and 'rm -rf'.
Use this skill to set up safety rails in a new or existing repository, or globally for the agent.
stars-end/agent-skills
-
beads-guard
Safe Beads workflow helper (warning-only). Use before bd sync/close/create to
avoid JSONL conflicts. Ensures you are on a feature branch, up to date with
origin/master, and stages Beads files cleanly with Feature-Key commits.
stars-end/agent-skills
-
vm-bootstrap
Linux VM bootstrap verification skill. MUST BE USED when setting up new VMs or verifying environment.
Supports modes: check (warn-only), install (operator-confirmed), strict (CI-ready).
Enforces Linux-only + mise as canonical; honors preference brew→npm (with apt fallback).
Verifies required tools: mise, node, pnpm, python, poetry, gh, railway, bd, tmux, jq, rg.
Handles optional tools as warnings: tailscale, playwright, docker, bv.
Never prints/seeds secrets; never stores tokens in repo/YAML; Railway vars only for app runtime env.
Safe on dirty repos (refuses and points to dirty-repo-bootstrap skill, or snapshots WIP branch).
Keywords: vm, bootstrap, setup, mise, toolchain, linux, environment, provision, verify, new vm
stars-end/agent-skills
-
area-context-create
Create codebase area context skills for rapid navigation. MUST BE USED for creating area context skills.
Handles ONE-TIME auto-detection with Serena, template-based generation, and manual maintenance.
Use when creating new area contexts or regenerating existing ones,
or when user mentions "create context skill", "generate area context", "map codebase area",
skill generation, codebase navigation, area mapping, or template-based skill creation.
stars-end/agent-skills
-
finish-feature
Complete epic with cleanup and archiving, or verify feature already closed. MUST BE USED when finishing epics/features.
For epics: Verifies children closed, archives docs, caches to Serena, closes epic.
For features/tasks/bugs: Verifies already closed (from PR creation), archives docs, caches to Serena.
Non-epic issues must be closed at PR creation time (atomic merge pattern).
Use when user says "I'm done with this epic", "finish the feature", "finish this epic", "archive this epic",
or when user mentions epic completion, cleanup, archiving, feature finalization, or closing work.
stars-end/agent-skills
-
skills-doctor
stars-end/agent-skills
-
feature-lifecycle
A suite of skills to manage the full development lifecycle from start to finish.
- `start-feature`: Initializes a new feature branch, docs, and story.
- `sync-feature`: Saves work with CI checks.
- `finish-feature`: Verifies and creates a pull request.
stars-end/agent-skills
-
issue-first
Enforce Issue-First pattern by creating Beads tracking issue BEFORE implementation. MUST BE USED for all implementation work.
Classifies work type (epic/feature/task/bug/chore), determines priority (0-4), finds parent in hierarchy, creates issue, then passes control to implementation.
Use when starting implementation work,
or when user mentions "no tracking issue", "missing Feature-Key", work classification,
creating features, building new systems, beginning development, or implementing new functionality.
stars-end/agent-skills
-
dirty-repo-bootstrap
stars-end/agent-skills
-
lint-check
Run quick linting checks on changed files. MUST BE USED when user wants to check code quality.
Fast validation (<5s) following V3 trust-environments philosophy.
Use when user says "lint my code", "check formatting", or "run linters",
or when user mentions uncommitted changes, pre-commit state, formatting issues,
code quality, style checks, validation, prettier, eslint, pylint, or ruff.
stars-end/agent-skills
-
context-database-schema
Supabase PostgreSQL schema management, 86+ migrations, RLS policies, and type generation.
Handles table creation, schema changes, migrations, foreign key constraints, and migration workflows.
Use when working with database schema, migrations, data modeling, or type definitions,
or when user mentions database changes, table modifications, schema updates, migration failures,
"relation does not exist" errors, foreign key issues, Supabase schema operations, users table, accounts table, or holdings table.
stars-end/agent-skills
-
dx-alerts
stars-end/agent-skills
-
session-end
End Claude Code session with Beads sync and summary. MUST BE USED when user says they're done, ending session, or logging off.
Guarantees Beads export to git, shows session stats, and suggests next ready work. Handles cleanup and context saving.
Use when user says "goodbye", "bye", "done for now", "logging off",
or when user mentions end-of-session, session termination, cleanup, context saving,
bd sync, or export operations.
stars-end/agent-skills
-
fix-pr-feedback
Address PR feedback with iterative refinement. MUST BE USED when fixing PR issues.
Supports auto-detection (CI failures, code review) and manual triage (user reports bugs). Creates Beads issues for all problems, fixes systematically.
Use when user says "fix the PR", "i noticed bugs", "ci failures", or "codex review found issues",
or when user mentions CI failures, review comments, failing tests, PR iterations,
bug fixes, feedback loops, or systematic issue resolution.
stars-end/agent-skills
-
create-pull-request
Create GitHub pull request with atomic Beads issue closure. MUST BE USED for opening PRs.
Asks if work is complete - if YES, closes Beads issue BEFORE creating PR (JSONL merges atomically with code).
If NO, creates draft PR with issue still open. Automatically links Beads tracking and includes Feature-Key.
Use when user wants to open a PR, submit work for review, merge into master, or prepare for deployment,
or when user mentions "ready for review", "create PR", "open PR", "merge conflicts", "CI checks needed",
"branch ahead of master", PR creation, opening pull requests, deployment preparation, or submitting for team review.
stars-end/agent-skills
-
bd-doctor
stars-end/agent-skills
-
beads-workflow
Beads issue tracking and workflow management with automatic git branch creation. MUST BE USED for Beads operations.
Handles full epic→branch→work lifecycle, dependencies, and ready task queries.
Use when creating epics/features (auto-creates branch), tracking work, finding ready issues, or managing dependencies,
or when user mentions "create issue", "track work", "bd create", "find ready tasks",
issue management, dependencies, work tracking, or Beads workflow operations.
stars-end/agent-skills
-
mcp-doctor
stars-end/agent-skills
-
coordinator-dx
stars-end/agent-skills
-
devops-dx
GitHub/Railway housekeeping for CI env/secret management and DX maintenance.
Use when setting or auditing GitHub Actions variables/secrets, syncing Railway env → GitHub, or fixing CI failures due to missing env.
stars-end/agent-skills
-
cli-mastery
stars-end/agent-skills
-
agent-mail-guide
stars-end/agent-skills
-
sync-feature-branch
Commit current work to feature branch with Beads metadata tracking and git integration. MUST BE USED for all commit operations.
Handles Feature-Key trailers, Beads status updates, and optional quick linting before commit.
Use when user wants to save progress, commit changes, prepare work for review, sync local changes, or finalize current work,
or when user mentions "uncommitted changes", "git status shows changes", "Feature-Key missing",
commit operations, saving work, git workflows, or syncing changes.
stars-end/agent-skills