cygnusfear/agent-skills

8652

file-name-wizard Audit all filename and naming conventions in the codebase against AGENTS.md standards and common patterns. Use when u…

cygnusfear/agent-skills

1.2K

2

architectural-analysis Deep architectural audit focused on finding dead code, duplicated functionality, architectural anti-patterns, type co…

cygnusfear/agent-skills

34

3

video-explorer This skill should be used when analyzing video files. You cannot process video directly, so this skill extracts frame…

cygnusfear/agent-skills

34

4

review-changes Code review of current git changes, compare to related plan if exists, identify bad engineering, over-engineering, or…

cygnusfear/agent-skills

33

5

design-spec-extraction Use when extracting design specifications from visual sources including Figma exports, UI mockups, screenshots, or li…

cygnusfear/agent-skills

32

6

obsidian-plan-wiki Create and manage behavior specification wikis in Obsidian format. Use when creating specs, documenting features, or …

cygnusfear/agent-skills

31

7

update-docs Update all documentation in docs and AGENTS.md files to match current codebase state. Use when user asks to update do…

cygnusfear/agent-skills

31

8

delphi Use when the user asks to "use delphi", "ask delphi", or wants multiple parallel oracle investigations of the same qu…

cygnusfear/agent-skills

29

9

create-worker Use when creating custom agents for Claude Code, configuring specialized AI assistants, or when the user asks about a…

cygnusfear/agent-skills

28

10

systematic-debugging ONLY USE THIS SKILL UPON USER/HOOMAN REQUEST TO USE EXACTLY THIS SKILL, ONLY RUN ON HOOMAN [OK]. Use when encounterin…

cygnusfear/agent-skills

28

11

writing-clearly-and-concisely Use when writing any prose humans will read — documentation, commit messages, error messages, explanations, reports, …

cygnusfear/agent-skills

28

12

blitz This skill should be used when parallelizing multi-issue sprints using git worktrees and parallel agents. Use when ta…

cygnusfear/agent-skills

27

13

brainstorming Use when starting any extended creative work — creating features, building components, adding functionality, or modif…

cygnusfear/agent-skills

27

14

code-review This skill should be used when reviewing pull requests, performing comprehensive code review, analyzing code changes …

cygnusfear/agent-skills

27

15

create-plan Create comprehensive implementation plan as a ticket based on analysis or report. Use when user asks to create a plan…

cygnusfear/agent-skills

27

16

create-skill Use when users want to create a new skill (or update an existing skill) that extends agent capabilities with speciali…

cygnusfear/agent-skills

27

17

the-oracle Use when the user asks to "use the oracle" or "ask the oracle" for deep research, analysis, or architectural question…

cygnusfear/agent-skills

27

18

ticket Use when a skill needs to persist output as a standardized artifact — research findings, plans, postmortems, reviews,…

cygnusfear/agent-skills

27

19

4-step-program Coordinator workflow for orchestrating dockeragents through fix-review-iterate-present loop. Use when delegating any …

cygnusfear/agent-skills

26

20

check-plan Audit implementation progress against a plan ticket, verify completed work, identify remaining tasks, and validate qu…

cygnusfear/agent-skills

26

21

chrome-devtools Control Chrome browser programmatically using chrome-devtools-mcp. Use when user asks to automate Chrome, debug web p…

cygnusfear/agent-skills

26

22

create-mcp-skill Create a new skill that uses an MCP server, following best practices from the MCP CLI guide. Use when user wants to c…

cygnusfear/agent-skills

26

23

create-pr Use when completing work on a branch and ready to open a pull request or merge request. Creates PRs/MRs that link rel…

cygnusfear/agent-skills

26

24

superpower-zustand Use when creating Zustand stores — MANDATORY. Do NOT create stores without this skill. All stores must use the requir…

cygnusfear/agent-skills

26

25

teams-driven-development Use when executing implementation plans with independent tasks in the current session

cygnusfear/agent-skills

26

26

using-superpowers Use when loading skills for complex tasks — provides guidelines for using skills effectively, not every message.

cygnusfear/agent-skills

26

27

writing-plans Use when you have a spec or requirements for a multi-step task, before touching code

cygnusfear/agent-skills

26

28

ctx Use when starting a session on a project, returning after time away, or before making significant changes. Essential …

cygnusfear/agent-skills

25

29

executing-plans Use when you have a written implementation plan to execute in a separate session with review checkpoints

cygnusfear/agent-skills

25

30

finishing-a-development-branch Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides comple…

cygnusfear/agent-skills

25

31

obsidian-upgrade Upgrade Obsidian wikis to latest format. Handles structure migration (phases/tasks → features/specs), comment format …

cygnusfear/agent-skills

25

32

test-driven-development Use when implementing any feature or bugfix, before writing implementation code

cygnusfear/agent-skills

25

33

the-archivist This skill should be used when engineering decisions are being made during code implementation. The Archivist enforce…

cygnusfear/agent-skills

25

34

using-git-worktrees Use when starting feature work that needs isolation from current workspace or before executing implementation plans -…

cygnusfear/agent-skills

25

35

dispatching-parallel-agents Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

cygnusfear/agent-skills

24

36

receiving-code-review Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or tec…

cygnusfear/agent-skills

24

37

requesting-code-review Use when completing tasks, implementing major features, or before merging to verify work meets requirements

cygnusfear/agent-skills

24

38

writing-skills Use when creating new skills, editing existing skills, or verifying skills work before deployment

cygnusfear/agent-skills

24

39

verification-before-completion Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running ver…

cygnusfear/agent-skills

23

40

domain-first-architecture-delphi Use when architecture feels component-based but ownership is split across technical buckets (tables/init/debug), caus…

cygnusfear/agent-skills

16

41

hammer Automated implement-review-iterate loop using nested teams delegation. Use when delegating any task that should reach…

cygnusfear/agent-skills

13

42

professional-rust-review Use when reviewing Rust code for craft quality, when writing new Rust code that should follow professional patterns, …

cygnusfear/agent-skills

12

43

service-communication-audit Use when analyzing, designing, or fixing how services communicate — especially when communication is unstable, one-di…

cygnusfear/agent-skills

7

44

make-it-so Make it so

cygnusfear/agent-skills

4