AC skill-evolver
A complete skill lifecycle manager for discovering, orchestrating, fusing, and evolving skills. Helps decide which skills to use, how to compose or fuse them, and whether to materialize a successful workflow into a new reusable skill. Trigger when: - User asks how to choose or combine skills - No single skill is sufficient and orchestration is needed - A solved workflow may need to be preserved as a new skill - Multiple skills need to be fused into one Do not trigger when: - User explicitly requests one specific skill - Native Claude ability is obviously sufficient
As a process C 64/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Risky intent
intent-offensive-securityREADME.md:55Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Security audit**: detect destructive commands, remote execution patterns, credential exfiltration, and privilege escalation risks.
detector
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 15. 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
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 911 tokens
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
- -33 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 574: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.