AF docs-cleaner
Consolidates redundant documentation while preserving all valuable content; keeps a doc set truthful after things change. Modes: (1) POST-CHANGE GOVERNANCE — when code, scripts, config, env vars, ports, paths, deployment, auth, tests, or a documented procedure changed; also "which docs are now wrong", "check docs for inconsistencies", "过时的命令/路径", "文档同步". Use it even when the user mentions only the change and never the docs — updating them is part of the change, not optional cleanup. (2) CONSOLIDATION — "clean up docs", "documentation bloat", "reduce documentation sprawl", "consolidate documentation", "too many doc files", "merge redundant docs", "merge these docs", "文档太多/太乱", multiple files covering the same topic, or documentation exceeding 500 lines across multiple files on similar topics. Finds stale copies of a fact changed in only one place, values that should never have been persisted (counts, totals, "N items", restated summaries), rival definitions that drift apart, and orphaned cross-references.
Consolidates redundant documentation while preserving all valuable content; keeps a doc set truthful after things change.
As a process F 54/100 · Will not run — References files that are not bundled: 个|条|步|项|点
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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
- warning
body-longSKILL.md body ≈ 11943 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: 个|条|步|项|点 - note
edit-residuethe text marks something as outdated (lines 203, 206): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 54/100
- 0Tools and files. 1 referenced file(s) missing: 个|条|步|项|点
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 67 mutating operations with no state check
- 40Execution cost. Instruction body is 11943 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 46 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- 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
- low The response is described with custom markup (5 tags): a typed call is more reliable
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 1019: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.