AF cleanup
Run the self-improving loop before session end. config - enable/disable individual tasks [config.md], hook-review - review hook errors and suggest improvements [hook-review.md], rag-store - persist to RAG before session end + sync fix_plan completed items to RAG (medium matrix fallback) [rag-store.md], run - 5-step sequential execution (commit → self-improve → knowledge persist → checklist record → next-action recommendation) [run.md]. Mistake recording (retrospect) and FA pruning moved to the fa skill — invoke Skill("fa") / Skill("fa", "fa-prune"). Supports Ralph mode (records to improvements.md instead of AskUserQuestion). Use on "wrap up", "session cleanup", "end session", "cleanup", "record mistake", "save feedback", "improve", "retrospect", "hook error", "next action", "RAG store", "qdrant store", "fix_plan sync".
Run the self-improving loop before session end.
As a process F 23/100 · Will not run — References files that are not bundled: ../fa/SKILL.md
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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../fa/SKILL.md - note
frontmatter-keyunknown frontmatter key "depends-on" - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 23/100
- 0Tools and files. 1 referenced file(s) missing: ../fa/SKILL.md
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 318 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 830: 120–800 characters recommended
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +4Structure: 5 headings
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.