AC acp-coder
Delegate coding tasks to external agents (Claude Code, Codex) via ACP. Triggers on phrases like "改代码", "修bug", "重构", "review", "实现功能", "写测试", "优化", "fix", "refactor", "debug", "develop", "build feature", "分析代码", "看下项目". Use when the user wants code changes, analysis, review, or multi-agent collaboration. NOT for simple shell queries like wc -l, ls, git log, or checking if a file exists.
As a process C 63/100 · Has gaps — weak spots: result and completion, 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: 5. 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
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 100Steps. 64 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3311 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -217 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 389: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 64 items
- +4Has examples (22 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.