AC github-repo-teardown
Deep-dive teardown of any GitHub open-source project into a beautifully designed HTML report that both product people and engineers can understand. Covers architecture, design decisions, comparable repos, and actionable application scenarios. Use this skill whenever the user shares a GitHub repo URL and asks to analyze, explain, teardown, or understand a project. Also trigger when the user says things like "break down this repo", "how does this project work", "analyze this codebase", "walk me through this repo", "what can I learn from this project", "explain this open-source project", "拆解一下", "帮我看看这个项目", or "讲解这个 repo". Even if the user just drops a GitHub link with a brief "what is this?" — use this skill. Produces a polished HTML teardown document covering product logic, technical architecture, and practical takeaways.
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 7 branches
- 85Steps. 117 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3604 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 832: 120–800 characters recommended
- -216 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 33 headings
- +3Step-by-step instructions: 117 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.