Borrowing it
Nothing to install: this file belongs to mtarcure/claude-vibe-squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/.agents/skills/skill-description-trigger-authoring/SKILL.mdgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mtarcure/claude-vibe-squad/skill-description-trigger-authoring)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/skill-description-trigger-authoring"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/skill-description-trigger-authoring/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/skill-description-trigger-authoring"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/skill-description-trigger-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.00916 |
| Opus 5 | $0.00028 | $0.00458 |
| Sonnet 5 | $0.00011 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
skill-description-trigger-authoring scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Description Trigger Authoring
A skill's description is its activation surface: it is matched against the task at hand by a reader who does not yet know the method. A description that summarizes content instead of naming the firing situation produces a skill that is technically available and practically never loaded.
When to use
- Authoring or revising the
description:frontmatter of any skill. - A postmortem shows a task where an existing skill should have fired and didn't.
- Two adjacent skills keep being confused for each other.
Inputs
- The moments in real workflows when the skill must load ("about to emit
complete", "about to implement against a foreign schema"). - Real past tasks: several where the skill should have fired, several adjacent ones where it should not.
Steps
- Enumerate the firing situations: what is the practitioner doing or about to do when this skill must load? Situations, not topics — "about to claim done", not "quality assurance".
- Write from the reader's pre-skill state. They can recognize their situation; they cannot recognize the method's vocabulary. "Use when about to X" beats "a methodology for X-ing".
- Front-load the trigger. Descriptions are scanned under time pressure; the first clause decides whether the rest is read.
- Include the concrete cue words and symptoms as they appear in real tasks — the phrases in packets, the moment in the workflow, the observable temptation ("it should work"). Matching happens against the task's own language.
- Add anti-triggers where siblings overlap: when NOT to use this skill, and which sibling handles that case. Disambiguation in the description is cheaper than a wrong load.
- Keep it to one or two sentences. A trigger buried in a paragraph fires never; completeness belongs in the body's When-to-use, not the description.
- Replay-test: take three real past tasks where the skill should have fired and two adjacent ones where it shouldn't. Reading the description alone — no body — check it routes all five correctly. A miss is a description bug; fix the description, not the tasks.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 48 lines · 57 tokens per session scan A 59ae1d3d3e56
skill-description-trigger-authoring is a skill published in the GitHub repository mtarcure/claude-vibe-squad (142 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 916 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
skill-installer
Install, update, trust, or inspect Codewhale skills from GitHub or local skill folders. Use when the user asks for available skills or wants a community skill installed.