AF skill-compass
Diagnose, fix, and prevent agent skill trigger failures. Use when a skill doesn't activate, when skills trigger incorrectly, when troubleshooting "skill not working" issues, when auditing skill descriptions for quality, when optimizing trigger accuracy, or when asked "why didn't my skill fire?". Also use proactively after installing new skills or when agent behavior seems to ignore available skills. Covers description optimization, YAML frontmatter validation, token budget analysis, conflict detection, and auto-remediation.
Diagnose, fix, and prevent agent skill trigger failures.
As a process F 60/100 · Will not run — References files that are not bundled: scripts/analyze_failures.py
How to improve
- 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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/analyze_failures.py
Process rating: all ten parameters 60/100
- 0Tools and files. 1 referenced file(s) missing: scripts/analyze_failures.py
- 0Result and completion. Does not say what the result is
- 30Running it twice. 7 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 53 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3007 tokens
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 529: enough signal without eating the budget
- +4Structure: 39 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.