c0nant/skills

1

grill-with-docs A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

c0nant/skills

52

2

grill-me A relentless interview to sharpen a plan or design.

c0nant/skills

51

3

improve-codebase-architecture Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one y…

c0nant/skills

51

4

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

c0nant/skills

51

5

caveman Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keepi…

c0nant/skills

50

6

handoff Compact the current conversation into a handoff document for another agent to pick up.

c0nant/skills

50

7

setup-skills Configure this repo for the engineering skills, set up its issue tracker, triage label vocabulary, domain doc layout,…

c0nant/skills

50

8

setup-statusline Install a Claude Code status line

c0nant/skills

41

9

prototype Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state mode…

c0nant/skills

40

10

ask-skills Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

c0nant/skills

38

11

grilling Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, o…

c0nant/skills

38

12

implement Implement a piece of work based on a spec or set of tickets.

c0nant/skills

38

13

resolving-merge-conflicts Use when you need to resolve an in-progress git merge/rebase conflict.

c0nant/skills

38

14

setup-pre-commit Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when use…

c0nant/skills

37

15

diagnosing-bugs Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports …

c0nant/skills

35

16

research Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Us…

c0nant/skills

35

17

reset-agent-env Reset global agent environments, wipe installed skills, hooks, rules, and MCP configs across Claude Code, Cursor, Win…

c0nant/skills

35

18

review-axes Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code …

c0nant/skills

34

19

wayfinder Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tr…

c0nant/skills

32

20

to-spec Turn the current conversation into a spec and publish it to the project issue tracker: synthesis of what you've alrea…

c0nant/skills

30

21

to-tickets Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edge…

c0nant/skills

30

22

delegate-tickets Orchestrates sequential ticket implementation through fresh subagents, requiring each one to use the /implement skill.

c0nant/skills

25

23

writing-great-skills Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

c0nant/skills

25

24

frontend-handoff Turn a finished backend change into a pasteable handoff for the frontend team, verdict first, must-change, should-cha…

c0nant/skills

22

25

setup-solid Write an architecture-level SOLID section into this repo's CLAUDE.md, scoped by the boy scout rule. Run once per repo.

c0nant/skills

22

26

to-issues Break a plan, spec, or PRD into independently-grabbable issues — published as local markdown by default (or to GitHub…

c0nant/skills

21

27

to-prd Turn the current conversation into a PRD and publish it as local markdown by default (or GitHub/GitLab on request) — …

c0nant/skills

21

28

review-mr Review someone else's merge request for bugs, security, performance and design, check it against the task's acceptanc…

c0nant/skills

18

29

wizard Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning inf…

c0nant/skills

16

30

to-questionnaire Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

c0nant/skills

15

31

wait-what Stop. That last message did not land: re-pitch it.

c0nant/skills

15

32

writing-for-agents Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

c0nant/skills

15

33

diagnose Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument…

c0nant/skills

12

34

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

c0nant/skills

12

35

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

c0nant/skills

12

36

zoom-out Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a …

c0nant/skills

12

37

sync-upstream Merge an upstream repo into this fork and resolve the conflicts in favour of the fork's deliberate divergences, then …

c0nant/skills

8

38

setup-conan-skills Configure the Claude Code hooks that the conan-skills set depends on after installing via `npx skills@latest add <use…

c0nant/skills

6

39

setup-devcontainer Set up a Compose-based devcontainer that inherits the host's git, CLI and agent identity, toolchain in the container,…

c0nant/skills

5

40

writing-beats Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.

c0nant/skills

5

41

writing-fragments Writing, explore: mine raw fragments, no structure yet.

c0nant/skills

5

42

writing-shape Writing, exploit: shape raw material into an article, paragraph by paragraph.

c0nant/skills

5

43

review Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code…

c0nant/skills

4

44

loop-me Grill me about specs for the workflows I want to build, within this workspace.

c0nant/skills

3

45

triage Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, …

c0nant/skills

3

46

claude-handoff Hand the current conversation off to a fresh background agent that picks up the work immediately.

c0nant/skills

2

47

design-an-interface Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants t…

c0nant/skills

2

48

edit-article Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to …

c0nant/skills

2

49

migrate-to-shoehorn Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to…

c0nant/skills

2

50

obsidian-vault Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, c…

c0nant/skills

2