carlitose/agent-skills

1

grill-me A relentless interview to sharpen a plan or design. Compatibility alias for grilling; use when the user says "grill m…

carlitose/agent-skills

59

2

improve-codebase-architecture Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable…

carlitose/agent-skills

58

3

tdd Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, me…

carlitose/agent-skills

57

4

qa-test-plan Plan causal QA for a runner candidate or standalone PR, commit, local diff, or requested scope without executing or d…

carlitose/agent-skills

51

5

triangulate-diagnosis Diagnose a hard bug from three independent angles at once, then record the consensus as a diagnostic or decision spec…

carlitose/agent-skills

48

6

domain-modeling Build and sharpen a project's domain model and ubiquitous language while planning or changing software. Use when the …

carlitose/agent-skills

47

7

grilling Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, as…

carlitose/agent-skills

47

8

grill-with-docs A relentless interview to sharpen a plan or design, while also creating or updating domain-modeling docs such as CONT…

carlitose/agent-skills

46

9

ticket-autopilot Drive a ticket folder AFK through deterministic scheduling, isolated implementation, evidence-backed quality gates, p…

carlitose/agent-skills

46

10

wayfinder Maintain a persistent map and investigation frontier for huge or vague work, using canonical normalized tickets and o…

carlitose/agent-skills

46

11

code-review Review a runner candidate or standalone PR, commit, local diff, or requested scope read-only for regressions, evidenc…

carlitose/agent-skills

45

12

execute-ticket Implement one normalized ticket through a bounded quality loop and return a validated handoff without scheduler or Gi…

carlitose/agent-skills

45

13

ask-skills Route a request to the smallest composable local skill flow without duplicating orchestration or removed super-autopi…

carlitose/agent-skills

44

14

codebase-improver End-to-end, self-contained Python/TypeScript workflow that maps and audits a whole repo, then recursively deepens mod…

carlitose/agent-skills

44

15

prototype Build a throwaway prototype to answer one design, logic, data-model, state-machine, or UI question before committing …

carlitose/agent-skills

44

16

to-spec Create or update a focused feature, decision, diagnostic, architecture, or bug-analysis spec; backward compatibility …

carlitose/agent-skills

44

17

to-tickets Break a spec into independently-grabbable tracer-bullet tickets and emit each versioned Ticket Envelope through the c…

carlitose/agent-skills

44

18

research Research a factual, codebase, product, or external-documentation question using primary sources and return an evidenc…

carlitose/agent-skills

43

19

diagnose Diagnose one bug by reproducing it, testing hypotheses, locating the root cause, and returning an evidence-backed dia…

carlitose/agent-skills

42

20

pr-antipattern-review Review a diff (pull request, commit, or local changes) by comparing it against the project's BLUEPRINT.md slice catal…

carlitose/agent-skills

42

21

peer-programming Use this skill whenever the user wants to peer program, pair program, or do collaborative coding where THE HUMAN writ…

carlitose/agent-skills

41

22

project-blueprint Discover the architectural slices, conventions, and patterns of a codebase by examining its structure, then output a …

carlitose/agent-skills

41

23

code-simplification Simplify the current candidate diff for clarity while preserving behavior, scope, tests, errors, side effects, and pr…

carlitose/agent-skills

40

24

explain-pr Render and optionally publish a deterministic PR body from a validated verification bundle without changing its claim…

carlitose/agent-skills

40

25

verification-audit Produce, validate, and reduce the canonical Verification Record for a frozen candidate without fabricating evidence o…

carlitose/agent-skills

40

26

codebase-design Shared vocabulary for designing deep, testable modules and evaluating interfaces, implementations, seams, adapters, l…

carlitose/agent-skills

28

27

handoff Create a small, redacted, pointer-based handoff in the operating-system temporary directory so a fresh session can co…

carlitose/agent-skills

28

28

resolving-merge-conflicts Trace both sides of an in-progress Git merge or rebase conflict, resolve compatible intent with scoped authority, and…

carlitose/agent-skills

28

29

to-questionnaire Draft a focused questionnaire for an explicit external decision owner when the current user cannot answer alone. Use …

carlitose/agent-skills

28

30

wizard Author a staged Bash wizard for a manual setup, credential, migration, or cutover procedure that a human will run exp…

carlitose/agent-skills

28

31

writing-for-agents Improve documents that agents consume, including skills, AGENTS.md, CLAUDE.md, prompts, and linked instructions. Use …

carlitose/agent-skills

28

32

llm-wiki Build and maintain a self-compiling markdown wiki — an Agent ingests raw sources and a project's own docs, compiles c…

carlitose/agent-skills

21

33

write-a-prd Create a PRD through user interview, codebase exploration, and module design, then save as a local Markdown file. Use…

carlitose/agent-skills

20

34

wait-what Stop. That last message did not land: re-pitch it. Re-explains the previous answer in the controlled-language standar…

carlitose/agent-skills

19

35

prd-to-issues Break a PRD into independently-grabbable local Markdown issue files using tracer-bullet vertical slices. Use when use…

carlitose/agent-skills

17

36

issues-to-openspec Convert a PRD and its issue files into an OpenSpec change folder with proposal, specs, design, and tasks. Use when us…

carlitose/agent-skills

10

37

write-a-adr Create an Architecture Decision Record and follow-up implementation issue from an existing bug, architecture problem,…

carlitose/agent-skills

9

38

change-status-ticket Change an exact ticket's administrative disposition to open, on-hold, or canceled. Use only for explicit hold, cancel…

carlitose/agent-skills

8

39

execute-issue Implement a specific issue end-to-end from a local issue file, pasted issue text, GitHub/Linear issue context, or exi…

carlitose/agent-skills

6

40

issue-autopilot Autonomously drive a whole folder of local issue files to done — for each ready issue it runs execute-issue, then cod…

carlitose/agent-skills

4

41

ralph Run one autonomous AFK implementation iteration from local issue files. Use when the user asks Ralph to pick and comp…

carlitose/agent-skills

4

42

super-autopilote-issue Variante autosuficiente de issue-autopilot. Conduce AFK una carpeta de issues locales a done/, ejecutando por cada is…

carlitose/agent-skills

3

43

super-autopilote-ticket Self-contained AFK variant of ticket-autopilot. Drives a local ticket folder to done with inline implementation, stri…

carlitose/agent-skills

3