AC skill-subtraction
Check installed AI skills and recommend keep / archive / uninstall to keep your skill set lean and focused. Triggers when the user asks to check or list installed skills, do a skill subtraction or cleanup, decide which skills to keep or delete, declutter or slim down their skill list, or find redundant or duplicate skills. Scans all installed skills across agent platforms, classifies them into 6 industry functional domains (dev & engineering, data & connectors, content & media, domain business, productivity, meta & agent control) plus subcategories, scores each on 6 weighted metrics, and generates a structured keep / archive / uninstall report with dedup and batch-install detection. Supports Chinese and English output. 技能减法：检查已安装技能，生成保留/归档/卸载建议报告。当用户要求检查已安装技能、清理技能、做技能减法、评估技能去留、整理技能列表时触发。
Check installed AI skills and recommend keep / archive / uninstall to keep your skill set lean and focused.
As a process C 64/100 · Has gaps — weak spots: result and completion, 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: 12. 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 64/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3637 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +3Description length 798: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.