AB repo-analysis
Read, explain, and evaluate a software repository or GitHub project in an engineering-oriented way. Use when the user asks to read a repo, understand a codebase, analyze architecture, evaluate whether a project is worth following or adopting, prepare onboarding notes, or summarize stack, module boundaries, risks, and entry points. Supports three output modes: 速读版, 架构版, and 接手评审版. Also supports a lightweight GitHub health layer for public repositories when the user asks whether a project is worth following, adopting, or referencing. Triggers include requests like 读一下这个项目, 看看这个 GitHub 仓库, 分析一下 repo, 这个项目怎么样, 帮我快速理解代码结构, 给我一个架构分析, or 给我一个接手评审.
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions
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: 6. 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 75/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 6 branches
- 85Steps. 248 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3193 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 13 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 648: enough signal without eating the budget
- +4Structure: 50 headings
- +3Step-by-step instructions: 248 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.