Using agent stack skills
Skill barry166/agent-stack-skills/skills/using-agent-stack-skills
Use when a software-engineering request may match an Agent Stack Skills workflow, especially prompt refinement, unfamiliar or legacy project discovery, environment setup, safe refactoring preparation, complete legacy change delivery, or requests to find, list, recommend, or execute matching skills.From its SKILL.md
npx -y skills add barry166/agent-stack-skills --skill using-agent-stack-skillsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 28 days oldThe repository was created 28 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.9 KB, 336 tokens by cl100k_base, as published. Nobody here has run it
Using Agent Stack Skills
Route requests to the smallest matching plugin skill.
Rules
- Honor an explicitly named skill first.
- For list, find, compare, recommend, analyze, read-only, no-modification, or no-execution requests, report matches without loading downstream workflows.
- Otherwise, load and execute the smallest clear match. Follow its instructions and risk gates.
- If nothing clearly matches, continue normally without forcing a plugin skill.
Routing
| Request | Skill |
|---|---|
| Enhance, refine, optimize, sharpen, or rewrite a software-engineering prompt before execution | enhance |
| Understand, run, and protect an unfamiliar legacy project | onboard-legacy-project |
| Build static architecture, API, dependency, or data-model context | map-legacy-project |
| Reproduce, start, smoke-test, or hand off an environment | bootstrap-project-environment |
| Prepare tests, CI, and regression safety before risky changes | build-legacy-guardrails |
| Deliver a concrete legacy-project change from a one-line request through implementation, testing, acceptance, documentation sync, and retrospective | run-legacy-change-cycle |
Use enhance only when prompt refinement is part of the request; do not force it onto ordinary implementation work. For multi-stage legacy onboarding, prefer onboard-legacy-project; it coordinates the mapping, environment, and guardrail skills. Use run-legacy-change-cycle for a concrete change once the project has enough reliable context and a runnable baseline. If those prerequisites are missing, onboard first and then start the change cycle.
What ships with it: 1 file
266 B alongside SKILL.md
agents/
- openai.yaml266 B