AGENT SKILL

listen

Execute instructions while listening for and invoking every skill referenced within them

License 许可
MIT
最近更新
2026-09-10
Stars
★ 3
Forks
1

01 前言 Front Matter

name
listen
description
Execute instructions while listening for and invoking every skill referenced within them
argument-hint
<instructions containing /skill references>
user-invocable
true

03 SKILL.md 正文

Listen for Skill Usage

Perform the following instructions and enforce using all the skills referenced in the skills used. Perform the following instructions and listen for all the — whether referenced directly or transitively through other skills.

Instructions: "$ARGUMENTS"


Enforcement Protocol

Before executing the instructions above, you MUST:

  1. Scan the instructions for every /skill-name reference (e.g., /tdd, /brainstorming, /expert-review, /super, /duper, /cat, or any other skill invocation).
  2. Build a checklist of every skill found. Create a task for each one.
  3. Invoke each skill using the Skill tool at the appropriate point during execution. A skill reference in the instructions is NOT a suggestion — it is a requirement.
  4. Verify completeness before reporting done: every skill on the checklist must have been invoked. If any skill was skipped, go back and invoke it now.

Rules

  • If the instructions reference a compositional skill (e.g., /super-duper-cat), invoke that skill directly — do not decompose it into its primitives unless the skill itself does so.

  • If the instructions contain no skill references, execute them normally without this enforcement overhead.

  • If a referenced skill fails or is denied by the user, note it explicitly in your output rather than silently skipping it.

  • Follow the invoked skills' own instructions exactly — this enforcement layer adds the guarantee that they are all used, but does not override how each skill operates.

  • If the instructions reference a compositional skill (e.g., /super-duper-cat), invoke that skill directly — do not decompose it into its primitives unless the skill itself does so.

  • If the instructions contain no skill references, execute them normally without this enforcement overhead.

  • If a referenced skill fails or is denied by the user, note it explicitly in your output rather than silently skipping it.

  • Follow the invoked skills' own instructions exactly — this enforcement layer adds the guarantee that they are all used, but does not override how each skill operates.

Satisfaction Semantics

A skill reference in the instructions is satisfied when one of the following holds:

  1. Direct invocation — the Skill tool was called with that skill's name (e.g. Skill(skill="superpowers:writing-skills")) during this execution.
  2. Compositional delegation — a compositional skill was directly invoked whose body text explicitly delegates to the referenced skill. When claiming satisfaction via composition, cite the composing skill's line that delegates (e.g. "/super-duper-cat invokes /writing-skills at phase N"). If you cannot cite a specific delegation line, the claim does not hold.

Transitive / implicit application does NOT satisfy the requirement. Following a skill's discipline "in spirit" — applying its pattern without invocation — is not satisfaction. Reading a skill's content without invoking it is not satisfaction. If the skill was referenced in the instructions and you never invoked it (directly or through a composing skill that explicitly delegates), the requirement is unmet — go back and invoke it now.

Rationalization counter:

Excuse Reality
"I followed /writing-skills discipline through the chain — that counts" Composition counts only when the composing skill's text explicitly delegates. "In spirit" does not. Cite the delegation line or invoke directly.
"The skill's content informed my behavior, so it was applied" Content-informed behavior is not invocation. Invoke via the Skill tool.
"Invoking it at the end is redundant" Invoking at the right point is the requirement, not at the end. If skipped at the point, you have a gap — invoke now and note it.
"The compositional skill I used must be doing that internally" Must cite the internal delegation, otherwise no claim. If the composing skill doesn't actually delegate, invoke the target directly.
"Skill invocation order should be reordered for dependency reasons" Dependency reordering may move when a skill fires but never whether. The reference is a requirement, not a suggestion. If a dependency truly makes invocation impossible at the listed point, surface the blocker explicitly — never silently drop the invocation.

04 同仓库更多 Skills

laurac8r
laurac8r/claude-damn

visual-aid

Use when the user asks for a quick visual aid, visual explainer, concept card, one-pager, poster, cheat sheet, infographic, visual summary, summary card, or mini explainer page — especially from input like a block of text, attached images, an attached song (lyrics/audio), a web link, a CSV/dataset, a math formula, a code snippet to walk through, a tutorial's steps, a timeline, or an A-vs-B comparison. Triggers include "make me a quick visual aid", "turn this into a one-pager / cheat sheet / explainer", "summarize this visually", "give me a visual of", "explain this on a single page", "make a concept card for", "whip up a page about", "build a mini page that shows", "something I can paste into a doc explaining X", or any request to render a topic/text/link/image-set/song/data into a standalone page. Prefer this skill over frontend-design when the ask is an explanatory single-file page (not a production UI), over playground when the output is static information display (not an interactive configurator), and over a Markdown/code answer when the user explicitly wants a *page* (HTML). Produces a single self-contained HTML file that opens on double-click without a server.

前端开发视觉设计
★ 3
laurac8r
laurac8r/claude-damn

tesseract

Use when you've been poking at the same file, concept, or problem across many sessions and want to step outside time to see its whole arc — or when you want to leave a note for next-session-you. Triggers: 'I've been going in circles on X', 'what have I learned about X', 'what did past-me say about X', 'I keep rediscovering this'.

★ 3
laurac8r
laurac8r/claude-damn

tdd

Invoke test-driven development as an explicit one-at-a-time micro-cycle — one test, one piece of functionality, refactor, then repeat for the next behavior

★ 3
laurac8r
laurac8r/claude-damn

tdd-cat

TDD workflow with subagent-driven-development — /tdd composed with /cat, plus the A/B TDD execution-mode axis (split-phase vs micro-cycle) asked as a third question in /cat's combined pre-dispatch question

★ 3
laurac8r
laurac8r/claude-damn

task-list

TaskCreate / TaskUpdate / render the current TaskList in response to `/task-list` (with or without flags). The skill body executes immediately on the syntax — no permission-seeking, no echoing the list back as plain text.

★ 3
laurac8r
laurac8r/claude-damn

sync

Sync files between two local directories, repos, or git worktrees. Five modes (plan/interactive/push/pull/mirror), .gitignore-aware, Claude-workflow allowlist via --claude, dropbox-restore-style per-directory prompts.

★ 3