pragmatic-agent-skills

In the author's own words, from each skill's SKILL.md.

• claude-code-orchestrator

  Use when delegating on Claude Code: select a subagent role, brief the task, and start, stop, resume or reconcile a child. Not for peer sessions or other CLIs. Slicing -> xp-agile-delivery.

  skills/claude-code-orchestrator/SKILL.md on GitHub (opens in a new tab)

• code-review

  Use when asked to review a diff, PR or uncommitted change for correctness, regressions and unneeded complexity. Not OWASP/authz -> security-review. Not deleting extras -> kill-slop.

  skills/code-review/SKILL.md on GitHub (opens in a new tab)

• codebase-design

  Use when designing or improving a module's interface (deep modules, small interfaces, clean seams) or finding and assessing shallow modules worth deleting, inlining or deepening. Moves -> refactoring-catalog.

  skills/codebase-design/SKILL.md on GitHub (opens in a new tab)

• codex-subagent-routing

  Use when delegating on Codex: select an eligible role, brief it as the mission (goal, scope, constraints, acceptance, delivery) and reconcile the delivery. Not for peer sessions or other CLIs.

  skills/codex-subagent-routing/SKILL.md on GitHub (opens in a new tab)

• diagnosing-bugs

  Use to reproduce a bug from evidence, or a failing test whose code may be wrong, and isolate one cause before changing code. Not proving a seam is wired -> layered-testing-executor.

  skills/diagnosing-bugs/SKILL.md on GitHub (opens in a new tab)

• docker-compose

  Use when a change must run against the repo's own Compose project (service won't start, ports, volumes). Reuse `docker compose -p <project>`. Test selection -> layered-testing-executor.

  skills/docker-compose/SKILL.md on GitHub (opens in a new tab)

• exhaustive-repo-cleanup-audit

  Use when asked to audit or clean up a repository, or identify files safe to delete. Audit every file; delete proven junk only when removal is requested. Dead code -> kill-slop.

  skills/exhaustive-repo-cleanup-audit/SKILL.md on GitHub (opens in a new tab)

• gemini-cli-orchestrator

  Use when delegating on Antigravity (Gemini family): read the dispatch schema, pick the child by task and complexity, brief it as the mission, verify returned work. Not the separate Gemini CLI.

  skills/gemini-cli-orchestrator/SKILL.md on GitHub (opens in a new tab)

• grok-build-orchestrator

  Use when delegating on Grok Build via spawn_subagent: pick the child by task type and complexity from the live schema and brief it as the mission. Not peer sessions or other CLIs.

  skills/grok-build-orchestrator/SKILL.md on GitHub (opens in a new tab)

• kill-slop

  Use when code or a diff has unneeded files, dependencies, abstractions (factory of factory) or dead code. Strip them; keep the behavior. Not a PR review -> code-review. Not renames or moves -> legacy-code-change.

  skills/kill-slop/SKILL.md on GitHub (opens in a new tab)

• kimi-cli-orchestrator

  Use when delegating on Kimi Code CLI: pick the child from its native agent files by task type and complexity, brief it as the mission. Not another runtime's orchestrator, a peer session or another CLI.

  skills/kimi-cli-orchestrator/SKILL.md on GitHub (opens in a new tab)

• layered-testing-executor

  Use when a changed capability is ready to verify: tests to pick and run, seams to prove reachable, genuine zero vs unknown. Narrowest layer first. Not first failing test -> tdd. Not story Done gate -> xp-agile-delivery.

  skills/layered-testing-executor/SKILL.md on GitHub (opens in a new tab)

• legacy-code-change

  Use when changing code with no trusted tests (characterize, cut the smallest seam, red then green). Trusted tests -> refactoring-catalog. New code -> tdd. Unknown cause -> diagnosing-bugs.

  skills/legacy-code-change/SKILL.md on GitHub (opens in a new tab)

• pragmatic-engineering

  Use when an engineering trade-off needs a choice: simplest thing, reversibility, tracer bullet or prototype, DRY, broken windows, estimate uncertainty, "is this over-engineered?". Slicing a story -> xp-agile-delivery.

  skills/pragmatic-engineering/SKILL.md on GitHub (opens in a new tab)

• refactoring-catalog

  Use when code has real duplication, confusing intent or excess coupling and trusted behavioral tests exist. Gives small safe moves (extract, rename, move), green throughout. No trusted tests -> legacy-code-change.

  skills/refactoring-catalog/SKILL.md on GitHub (opens in a new tab)

• security-review

  Use for a structured security review: threat modelling, OWASP checks and severity-ranked findings. Not an ordinary correctness pass -> code-review.

  skills/security-review/SKILL.md on GitHub (opens in a new tab)

• tdd

  Use when about to write code for a feature or bugfix and no failing test exists yet. Red-green-refactor. Layers -> layered-testing-executor. Untested -> legacy-code-change; unknown cause -> diagnosing-bugs.

  skills/tdd/SKILL.md on GitHub (opens in a new tab)

• test-audit

  Use when adding/changing a test or auditing/pruning low-value, implementation-coupled or duplicate tests. Not red-green -> tdd. Not layer choice -> layered-testing-executor. Untested code to change -> legacy-code-change.

  skills/test-audit/SKILL.md on GitHub (opens in a new tab)

• testing-e2e-playwright

  Use when writing, fixing or de-flaking a Playwright/e2e browser test: fixtures, locators, waits, user-visible assertions. Not the pre-delivery UI pass.

  skills/testing-e2e-playwright/SKILL.md on GitHub (opens in a new tab)

• windows-shell-interop

  Use for UnicodeEncodeError, console mojibake (cp1252), PowerShell 5.1 vs 7, or a path/quoting trap across PowerShell, Git Bash, cmd and Windows paths. Not a Linux-only script. Compose volumes -> docker-compose.

  skills/windows-shell-interop/SKILL.md on GitHub (opens in a new tab)

• worktree-lifecycle

  Use when a second concurrent writer needs an isolated tree, or a git worktree needs census, ownership check or disposal. One owner per tree. Not merge conflicts. Whole-repo cleanup -> exhaustive-repo-cleanup-audit.

  skills/worktree-lifecycle/SKILL.md on GitHub (opens in a new tab)

• xp-agile-delivery

  Use when a story moves from ready to in-progress, or a mission needs slicing. Beyond one slice: blocked sub-issues via tdd. Not test layers -> layered-testing-executor. Trade-off doubt -> pragmatic-engineering.

  skills/xp-agile-delivery/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• superpowersby obra An agentic skills framework & software development methodology that works. 300k stars · 15 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 293k stars · 30 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 181k stars · 19 skills