troykelly/codex-skills

1

error-recovery Use when encountering failures - assess severity, preserve evidence, execute rollback decision tree, and verify post-…

troykelly/codex-skills

49

2

documentation-audit Use when documentation drift is detected. Comprehensively audits codebase and creates/updates Swagger, features docs,…

troykelly/codex-skills

32

3

security-review MANDATORY for security-sensitive code changes - OWASP-based security review with dedicated checklist, required before…

troykelly/codex-skills

30

4

code-simplifier Use when asked to simplify recently changed code without changing behavior or explicitly asked to run the code-simpli…

troykelly/codex-skills

19

5

code-explorer Use when asked to trace existing codepaths or explicitly asked to run the code-explorer subagent.

troykelly/codex-skills

16

6

code-reviewer Use when explicitly asked to run the code-reviewer subagent or when another skill requires the code-reviewer agent ca…

troykelly/codex-skills

11

7

comprehensive-review Use after implementing features - 7-criteria code review with MANDATORY artifact posting to GitHub issue; blocks PR c…

troykelly/codex-skills

10

8

conflict-resolution Use when encountering merge conflicts - handle conflicts cleanly, verify resolution, and maintain code integrity

troykelly/codex-skills

10

9

timescaledb MANDATORY when working with time-series data, hypertables, continuous aggregates, or compression - enforces Timescale…

troykelly/codex-skills

10

10

work-intake Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to a…

troykelly/codex-skills

10

11

api-documentation Use when API code changes (routes, endpoints, schemas). Enforces Swagger/OpenAPI sync. Pauses work if documentation h…

troykelly/codex-skills

9

12

code-architect Use when asked for an architecture blueprint or explicitly asked to run the code-architect subagent.

troykelly/codex-skills

9

13

issue-driven-development Use for any development work - the master 13-step coding process that orchestrates all other skills, ensuring GitHub …

troykelly/codex-skills

9

14

pexels-media Source royalty-free images and videos from Pexels API for design, placeholders, or content. Supports search, curated/…

troykelly/codex-skills

9

15

postgis MANDATORY when working with geographic data, spatial queries, geometry operations, or location-based features - enfor…

troykelly/codex-skills

9

16

postgres-rls MANDATORY when touching auth tables, tenant isolation, RLS policies, or multi-tenant database code - enforces Row Lev…

troykelly/codex-skills

9

17

pre-work-research Use before starting implementation - research repository documentation, codebase patterns, and external resources to …

troykelly/codex-skills

9

18

research-after-failure Use after 2 consecutive failed attempts at solving a problem - STOP guessing and research documentation, codebase, an…

troykelly/codex-skills

9

19

review-gate HARD GATE before PR creation - verifies review artifact exists in issue comments, all findings addressed or tracked, …

troykelly/codex-skills

9

20

review-scope Use before code review - determine if change is minor (review new code only) or major (review impacted code too)

troykelly/codex-skills

9

21

security-reviewer Use when explicitly asked to run the security-reviewer subagent or when another skill requires the security-reviewer …

troykelly/codex-skills

9

22

strict-typing Use when writing code in typed languages - enforces full typing with no any/unknown/untyped escapes, even if it requi…

troykelly/codex-skills

9

23

acceptance-criteria-verification Use after implementing features - verifies each acceptance criterion with structured testing and posts verification r…

troykelly/codex-skills

8

24

apply-all-findings Use after code review - implement ALL findings; any finding not fixed MUST have tracking issue created; no finding di…

troykelly/codex-skills

8

25

autonomous-operation Use when starting any work session - establishes autonomous operation mode, overriding token limits and time pressure…

troykelly/codex-skills

8

26

branch-discipline Use before any code changes - hard gate ensuring work never happens on main branch, with proper feature branch creati…

troykelly/codex-skills

8

27

ci-monitoring Use after creating PR - monitor CI pipeline, resolve failures cyclically until green or issue is identified as unreso…

troykelly/codex-skills

8

28

clean-commits Use when committing code - ensures atomic, descriptive commits that leave the codebase in a merge-ready state at ever…

troykelly/codex-skills

8

29

database-architecture MANDATORY when designing schemas, writing migrations, creating indexes, or making architectural database decisions - …

troykelly/codex-skills

8

30

environment-bootstrap Use for development environment setup - create and maintain init scripts, run smoke tests, ensure consistent environm…

troykelly/codex-skills

8

31

epic-management Use for LARGE work requiring feature-level grouping. Creates epic tracking issues, manages related issues under a com…

troykelly/codex-skills

8

32

features-documentation Use when user-facing features change. Ensures features documentation is updated. Pauses work if documentation has dri…

troykelly/codex-skills

8

33

feedback-triage Use when receiving UAT feedback, bug reports, user testing results, stakeholder feedback, QA findings, or any batch o…

troykelly/codex-skills

8

34

local-service-testing Use when code changes touch database, cache, queue, or other service-dependent components - enforces testing against …

troykelly/codex-skills

8

35

no-deferred-work Use during all development - no TODOs, no FIXMEs, no "we'll add this later"; do it now or get explicit deferral permi…

troykelly/codex-skills

8

36

pr-creation Use after completing implementation - create pull request with complete documentation, proper labels, linked issues, …

troykelly/codex-skills

8

37

pr-test-analyzer Use when asked to evaluate PR test coverage or explicitly asked to run the pr-test-analyzer subagent.

troykelly/codex-skills

8

38

session-start Use at the beginning of every work session - establishes context by checking GitHub project state, reading memory, ve…

troykelly/codex-skills

8

39

silent-failure-hunter Use when asked to detect silent failures/weak error handling or explicitly asked to run the silent-failure-hunter sub…

troykelly/codex-skills

8

40

style-guide-adherence Use when writing code - follow Google style guides where available, otherwise follow established best practices for t…

troykelly/codex-skills

8

41

tdd-full-coverage Use when implementing features or fixes - test-driven development with RED-GREEN-REFACTOR cycle and full code coverag…

troykelly/codex-skills

8

42

type-design-analyzer Use when asked to evaluate type design/invariants or explicitly asked to run the type-design-analyzer subagent.

troykelly/codex-skills

8

43

verification-before-merge Use before merging PR - final gate ensuring all tests pass, review complete, CI green, and acceptance criteria verifi…

troykelly/codex-skills

8

44

worker-dispatch Use to spawn isolated worker processes for autonomous issue work. Creates git worktrees, constructs worker prompts, a…

troykelly/codex-skills

8

45

worker-protocol Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting…

troykelly/codex-skills

8

46

autonomous-orchestration Use when user requests autonomous operation across multiple issues. Orchestrates parallel workers, monitors progress,…

troykelly/codex-skills

7

47

comment-analyzer Use when asked to review code comments for accuracy/quality or explicitly asked to run the comment-analyzer subagent.

troykelly/codex-skills

7

48

deferred-finding Use when a review finding cannot be fixed in current PR - creates properly documented tracking issue with full contex…

troykelly/codex-skills

7

49

inclusive-language Use when writing code, documentation, or comments - always use accessible and respectful terminology

troykelly/codex-skills

7

50

initiative-architecture Use for MASSIVE work requests requiring multi-epic planning. Creates research spikes, documents all unknowns and deci…

troykelly/codex-skills

7