helderberto/agent-skills

1

code-review Review a GitHub Pull Request for bugs, security, performance, and code quality. Use when user asks to review a PR or …

helderberto/agent-skills

79

2

explain-code Explains code with visual diagrams and analogies.

helderberto/agent-skills

61

3

commit Group unstaged changes into atomic commits by concern, following repository style. Use when user asks to "commit", "c…

helderberto/agent-skills

57

4

lint Run linting and formatting checks. Use when user asks to "run linter", "/lint", "check linting", "fix lint errors", o…

helderberto/agent-skills

54

5

ship Commit and push changes with a pre-launch gate (validate-code + safe-repo) by default. `--fast` skips the gate.

helderberto/agent-skills

53

6

refactor-plan Create structured refactoring plans. Use when user wants to plan a refactor, needs a refactoring strategy, or mention…

helderberto/agent-skills

49

7

tdd Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refact…

helderberto/agent-skills

46

8

safe-repo Check for sensitive data in repository. Use when user asks to "check for sensitive data", "/safe-repo", or wants to v…

helderberto/agent-skills

45

9

coverage Check test coverage for unstaged changes. Use when user asks to "check coverage", "/coverage", or wants to see which …

helderberto/agent-skills

41

10

perf-audit Audit frontend bundle size and performance. Use when user asks to "audit performance", "/perf-audit", "analyze bundle…

helderberto/agent-skills

39

11

architecture-audit Explore a codebase to surface architectural friction and propose refactors toward deep modules (simple interface, lar…

helderberto/agent-skills

37

12

atomic-commits Group unstaged changes into atomic commits by concern, then push. Use when user asks to "atomic commits", "commit by …

helderberto/agent-skills

36

13

e2e Write end-to-end tests for user flows using Cypress. Use when user asks to "write e2e tests", "/e2e", "add Cypress te…

helderberto/agent-skills

34

14

i18n Audit internationalization coverage and find hardcoded strings.

helderberto/agent-skills

34

15

create-pull-request Create a GitHub pull request — fills the repo's PR template, conventional-commit title, ticket refs. Draft mode via `…

helderberto/agent-skills

33

16

grill-me A relentless interview to sharpen a plan or design. Use when the user wants to stress-test a plan, pressure-test assu…

helderberto/agent-skills

30

17

deps-audit Check dependencies for known vulnerabilities and staleness. Use when user asks to "audit dependencies", "/deps-audit"…

helderberto/agent-skills

26

18

a11y-audit Audit accessibility compliance in frontend code.

helderberto/agent-skills

23

19

revise Structurally edit and improve article drafts — reorder sections, tighten arguments, improve clarity. Use when user as…

helderberto/agent-skills

22

20

write-a-skill Create new agent skills with proper structure and progressive disclosure. Use when user wants to create, write, or bu…

helderberto/agent-skills

22

21

prose-fix Fix prose formatting, typos, and clarity issues in markdown or text files. Use when user asks to "fix dashes", "fix t…

helderberto/agent-skills

20

22

testing Run the test suite and report results. Use when user asks to "run tests", "/test", "/testing", "execute tests", or re…

helderberto/agent-skills

20

23

audit-deps Check dependencies for vulnerabilities. Use when user asks to "audit dependencies", "/audit-deps", "check for vulnera…

helderberto/agent-skills

19

24

validate-code Validate code quality: auto-fix formatting/lint, verify types, run tests. Use when user asks to \"validate code\", \"…

helderberto/agent-skills

15

25

fortify Fortify existing code by splitting large functions, adding edge-case coverage, and backfilling unit tests.

helderberto/agent-skills

14

26

prd-to-plan Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file…

helderberto/agent-skills

14

27

write-a-prd Create a PRD through user interview, codebase exploration, and module design, saved locally to prds/. Use when user w…

helderberto/agent-skills

12

28

git-safety-hooks Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they exe…

helderberto/agent-skills

11

29

create-pr Create GitHub pull requests. Use when user asks to "create a pull request", "open a PR", "/create-pr", or requests cr…

helderberto/agent-skills

10

30

review-pr Review pull requests. Use when user asks to "review a PR", "/review-pr", or wants to review a pull request.

helderberto/agent-skills

10

31

setup-pre-commit Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests. Use when user asks to "add pre-c…

helderberto/agent-skills

10

32

source-driven Implement features using official docs for exact dependency versions instead of training data. Use when user asks to …

helderberto/agent-skills

10

33

a11y Audit accessibility compliance in frontend code. Use when user asks to "check accessibility", "/a11y", "audit a11y", …

helderberto/agent-skills

8

34

checks Pre-commit quality gate: auto-fix formatting/lint, verify types, run tests. Use when user asks to "run checks", "/che…

helderberto/agent-skills

7

35

harden Harden code proactively against vulnerabilities at the boundary where untrusted input enters the system.

helderberto/agent-skills

7

36

diagnose Disciplined diagnosis loop for hard bugs and performance regressions.

helderberto/agent-skills

6

37

create-adr Record an Architecture Decision Record (ADR) — a 1–3 sentence note capturing what was decided and why.

helderberto/agent-skills

5

38

plan Turn a spec into a multi-phase implementation plan using tracer-bullet vertical slices. Use after /spec when a spec e…

helderberto/agent-skills

5

39

visual-validate Validate UI changes in a real browser using Chrome DevTools or Playwright MCP. Takes screenshots, compares before/aft…

helderberto/agent-skills

5

40

build Implement one phase of a plan — reads the plan, finds the next incomplete phase, implements it with feedback loops, m…

helderberto/agent-skills

4

41

caveman Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accu…

helderberto/agent-skills

4

42

create-skill Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to …

helderberto/agent-skills

4

43

handoff Compact the current conversation into a handoff document for another agent to pick up. Use when the user wants to han…

helderberto/agent-skills

4

44

review Orchestrated REVIEW phase — fan out parallel, read-only reviewers over a diff (scope-detected audit skills AND indepe…

helderberto/agent-skills

4

45

visual-review Render a GitHub Pull Request diff as a self-contained HTML page where each changed hunk is annotated with a software-…

helderberto/agent-skills

4

46

accessibility-audit Audit accessibility compliance in frontend code. Use when user asks to "check accessibility", "/accessibility-audit",…

helderberto/agent-skills

3

47

brief Session briefing — shows active features, progress, and suggested focus. Use at the start of a session, when asking w…

helderberto/agent-skills

3

48

codebase-design Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…

helderberto/agent-skills

3

49

pr-reply Draft friendly, concise replies to pull request review comments. Use when user pastes a PR comment, asks to "reply to…

helderberto/agent-skills

3

50

prd Create a PRD through user interview, codebase exploration, and module design. Use when starting a new feature or chan…

helderberto/agent-skills

3