hburaktasyurek/agent-skills-and-commands

1

to-spec Produce an evidence-backed four-file implementation spec for one bounded software change, using consequence-calibrate…

hburaktasyurek/agent-skills-and-commands

57

2

commit-work Stage intended changes, split into logical commits, and write Conventional Commit messages; push only when the user e…

hburaktasyurek/agent-skills-and-commands

55

3

pr-branch Use when the user explicitly invokes pr-branch or asks to open or refresh a GitHub pull request from the current bran…

hburaktasyurek/agent-skills-and-commands

52

4

session-handoff Use only when the user explicitly names session-handoff or explicitly asks to create a durable resume packet for a la…

hburaktasyurek/agent-skills-and-commands

52

5

spec-readiness Check whether a named implementation specification is ready to hand to an implementer without forcing them to invent …

hburaktasyurek/agent-skills-and-commands

52

6

grill-me Use only when the user explicitly names grill-me or explicitly asks for an interactive grilling of a plan, decision, …

hburaktasyurek/agent-skills-and-commands

50

7

tdd Use only when the user explicitly names tdd or an upstream task explicitly invokes it to implement a feature or bug f…

hburaktasyurek/agent-skills-and-commands

48

8

prompt-creator Build Claude prompts via an interview grounded in Anthropic best practices. Use when creating, writing, improving, or…

hburaktasyurek/agent-skills-and-commands

45

9

senior-implementer Use only when explicitly invoked as `/senior-implementer`, `use senior-implementer`, or equivalent to implement an ap…

hburaktasyurek/agent-skills-and-commands

44

10

triage-issue Triage a bug or issue by exploring the codebase to find root cause, then create a GitHub issue with a TDD-based fix p…

hburaktasyurek/agent-skills-and-commands

44

11

adversarial-spec-review Evidence-bounded red-team review that challenges a plan or spec without manufacturing findings. Returns a priority-so…

hburaktasyurek/agent-skills-and-commands

39

12

tune-skill Improve one existing shipped skill from concrete feedback or a failed run via bounded PDCA. Use when skill instructio…

hburaktasyurek/agent-skills-and-commands

38

13

adversarial-diff-review Hostile kill-test of an explicit branch/worktree/PR diff against its task definition; P0–P3 with file:line evidence. …

hburaktasyurek/agent-skills-and-commands

33

14

review-implementation Review an implemented change against a named specification before opening a PR. Use when the user asks for spec-compl…

hburaktasyurek/agent-skills-and-commands

30

15

task-groundwork Use only when the user explicitly names task-groundwork to ground a vague or non-trivial software task before specifi…

hburaktasyurek/agent-skills-and-commands

29

16

revise-spec-from-review Reconcile supplied adversarial-spec-review or spec-readiness findings into a named spec folder, closing each confirme…

hburaktasyurek/agent-skills-and-commands

27

17

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

hburaktasyurek/agent-skills-and-commands

25

18

request-refactor-plan Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user w…

hburaktasyurek/agent-skills-and-commands

24

19

adversarial-review Red-team review that tries to kill a plan or spec. Returns a priority-sorted finding list (P0–P3), with verdict when …

hburaktasyurek/agent-skills-and-commands

23

20

methodology-skill-creator Create one focused methodology SKILL.md from a completed methodology-selector contract. Use when a catalog method sho…

hburaktasyurek/agent-skills-and-commands

15

21

loop-orchestrator Coordinate methodology-selector with goal-engineering, loop-readiness-score, methodology-skill-creator, or loop-run-r…

hburaktasyurek/agent-skills-and-commands

14

22

risk-calibrated-pr-review Use only when explicitly invoked as `$risk-calibrated-pr-review` or equivalent to independently review a current impl…

hburaktasyurek/agent-skills-and-commands

14

23

methodology-selector Select one best-fit methodology from the twelve-method catalog, or none. Use when a task needs a structured method be…

hburaktasyurek/agent-skills-and-commands

13

24

goal-engineering Turn a selected methodology and task contract into a compact, verifiable loop goal for any agent tool. Use after meth…

hburaktasyurek/agent-skills-and-commands

12

25

loop-readiness-score Score a rendered loop goal against eleven weighted readiness criteria totaling 100, then return blocked, supervised, …

hburaktasyurek/agent-skills-and-commands

12

26

loop-run-record Turn externally supplied evidence from one completed loop run into a canonical, review-required record bound to the e…

hburaktasyurek/agent-skills-and-commands

12

27

revise-skill-from-review Apply PDCA to apply closed purpose-fail remedies to a skill draft. Use when a workflow should improve through repeate…

hburaktasyurek/agent-skills-and-commands

10

28

skill-brief Apply 5W2H to fill the skill-path-selector checklist from skill-design intent, using bounded grill-me only for missin…

hburaktasyurek/agent-skills-and-commands

10

29

skill-composition Check one skill's invoke/forbid/require edges against the catalog. Use when a single skill package needs an invoke/fo…

hburaktasyurek/agent-skills-and-commands

10

30

skill-path-selector Apply Decision Matrix to choose one skill-create path from a completed checklist. Use when several options must be co…

hburaktasyurek/agent-skills-and-commands

10

31

skill-review Apply SMART Goals to judge whether a skill draft achieves its stated purpose. Use when a goal must become measurable …

hburaktasyurek/agent-skills-and-commands

10

32

skill-router Apply Decision Matrix to recommend exactly one catalog skill for a job, or none/blocked with evidence. Use when sever…

hburaktasyurek/agent-skills-and-commands

10

33

skill-eval Use only when explicitly asked to evaluate one repository skill package against its exact old-skill or no-skill basel…

hburaktasyurek/agent-skills-and-commands

7

34

omp-task-to-spec Use only when the user explicitly names omp-task-to-spec.

hburaktasyurek/agent-skills-and-commands

6

35

skill-creator Draft skill proposals under .skill-proposals or ship after purpose_pass. Use when A skill-path-selector path is metho…

hburaktasyurek/agent-skills-and-commands

6

36

skill-design-loop Orchestrate repository skill intake, path selection, and proposal drafting in one task, then stop before review or sh…

hburaktasyurek/agent-skills-and-commands

6

37

skill-draft-ship Draft one repository skill proposal from a complete checklist and selected path, or ship a reviewed proposal after ex…

hburaktasyurek/agent-skills-and-commands

6

38

codex-task-to-spec Use only when the user explicitly asks for the Codex task-to-spec gate. Produce and locally commit a grounded four-fi…

hburaktasyurek/agent-skills-and-commands

4