abpai/skills

1

bun-expert Bun runtime guidance for JavaScript and TypeScript projects — package management, HTTP servers, Bun-specific APIs (`B…

abpai/skills

46

2

human-writer Rewrite AI-sounding drafts into natural, specific prose — for text that feels generic, over-polished, promotional, re…

abpai/skills

41

3

visualize Generate single-file HTML visualizations that teach systems, plans, code flows, architectures, comparisons, timelines…

abpai/skills

33

4

agent-browser Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, …

abpai/skills

28

5

claude Run Claude Code from Codex as a headless external worker. Use only for explicit requests to ask, delegate to, run, or…

abpai/skills

27

6

code Route coding workflows through one scoped /code command. Use prepare-pr for effort-scaled PR readiness through push, …

abpai/skills

27

7

code-simplifier Simplify and refine code for clarity, consistency, and maintainability while preserving all functionality. Focuses on…

abpai/skills

25

8

cli-design-expert Design, review, or refactor command-line interfaces for usability and automation. Use for help text, args/flags, stdo…

abpai/skills

24

9

dead-code-eliminator Audit a codebase for dead code first: unreachable functions, unused imports, orphaned classes, unreachable branches, …

abpai/skills

23

10

socratic-code-owner Quizzes the developer on code, architecture, or plans that an AI agent just built or proposed — one question at a tim…

abpai/skills

23

11

beautiful-mermaid Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermai…

abpai/skills

22

12

project-memory Always-on project memory workflow. At the start of every task, read `.agents/LEARNINGS.md`; while working, update it …

abpai/skills

22

13

lateral-thinking Generate non-obvious hypotheses by decomposing a problem to its mechanism and raiding distant fields for transferable…

abpai/skills

21

14

engineering Route engineering-practice workflows through one scoped /engineering command. Use grill-me to stress-test a plan, tdd…

abpai/skills

19

15

vibe-kanban Manage work in Vibe Kanban (VK), the shared source of truth for agent tasks. Use when checking assigned work, creatin…

abpai/skills

18

16

distill Decompose a complex system into essential primitives and a compressed mental model. Use when the user asks to distill…

abpai/skills

17

17

try Evaluate a new library, tool, or GitHub repo before adopting it. Uses the try CLI for workspace management when avail…

abpai/skills

16

18

codex-exec Run, review, resume, or delegate through the Codex CLI as a second-opinion worker. Use for `codex exec`, `codex revie…

abpai/skills

14

19

code-review-and-commit Review uncommitted Git changes for correctness, quality, and project convention alignment, then apply fixes and prepa…

abpai/skills

13

20

composer Run, monitor, resume, or review work with Cursor Agent and Composer models. Use when delegating bounded implementatio…

abpai/skills

13

21

harness Route agent-harness workflows through one scoped /harness command. Use guide for scenario-based first-audit, adoption…

abpai/skills

10

22

improve-prompt Improve, rewrite, or sharpen prompts into reusable instructions. Use when the user has a rough request, wants a promp…

abpai/skills

10

23

tutorial Write hands-on, self-verified, code-first tutorials where every step ends in a runnable action and the reader finishe…

abpai/skills

10

24

codex Run Codex CLI for code analysis and automated edits. Use when users ask to run `codex exec`/`codex resume`, continue …

abpai/skills

9

25

visual-explainer Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when …

abpai/skills

9

26

decision-worksheet Capture concise user feedback notes or build evidence-backed decision worksheets. Use when the user asks to record a …

abpai/skills

8

27

review-and-commit Review uncommitted Git changes for correctness, quality, and project convention alignment, then apply fixes and prepa…

abpai/skills

8

28

slidev Create and present web-based slides for developers using Markdown, Vue components, code highlighting, animations, and…

abpai/skills

8

29

hexagon-audit Audit Ports & Adapters / hexagonal architecture boundaries in packages/ + adapters/ monorepos. Use for hexagon compli…

abpai/skills

6

30

debate Structured architecture debate: Claude proposes, Codex critiques, Claude synthesizes into a final ADR with concrete n…

abpai/skills

4

31

dokploy Comprehensive skill for operating Dokploy via the official Dokploy CLI (oclif-based). Use when users ask to authentic…

abpai/skills

4

32

scratch Understand an existing project by playing with its real modules in a safe workspace. Creates a .scratch/ folder with …

abpai/skills

4

33

arch-council Orchestrate a structured architecture debate between Claude and Codex. Claude proposes, Codex critiques, Claude synth…

abpai/skills

3

34

status-update Summarize a long-running agent task as a concise, evidence-backed snapshot of completed outcomes, current activity, r…

abpai/skills

3

35

capture-feedback Capture concise user corrections about how an agent should have behaved differently, saving a local shared feedback n…

abpai/skills

2

36

dead-code Route dead-code reachability audits to the code workflow module.

abpai/skills

2

37

claude-session Locate, read, and summarize local Claude Code transcripts by session UUID. Use first whenever the user supplies a Cla…

abpai/skills

1

38

pi-protocol Claude-native harness for long-running engineering work. Defines the planner -> generator -> evaluator loop, checkpoi…

abpai/skills

1

39

secure-dependencies Harden dependency resolution and supply-chain policy in the current repository.

abpai/skills

1