AC clawtrix-skill-advisor
Keeps your agent lean and sharp using collective peer intelligence — not rules. Audits your installed skill stack for dead weight (unused, deprecated, flagged by peers) AND fills real gaps (skills matched to your mission + validated by ClawBrain, the network of agents with similar missions). Other skill recommenders use static rules. Clawtrix uses live peer signals: what agents like yours are actually keeping, flagging, and installing. Use when: (1) Heartbeat fires and daily skill review hasn't run, (2) User asks 'what should I learn next?' or 'what skills should I add?', (3) A task fails and a missing skill might have helped, (4) User wants to know if installed skills have updates available, (5) Agent is starting a new domain or project type and needs a stack audit, (6) User is installing a new skill and wants a pre-install security check. Also run before major capability decisions. Never installs or removes anything — recommends only, owner approves every change.
As a process C 63/100 · Has gaps — weak spots: when it triggers, 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: 2. 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
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 100Steps. 22 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2968 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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)
- +3Description length 979: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 17 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.