AF self-improvement
Capture durable lessons from debugging, user corrections, missing capabilities, and repeated workflow friction so future sessions avoid the same mistakes. Use this skill when a non-obvious failure is diagnosed, the user corrects or updates the agent, a workaround or project convention is discovered, a capability is missing, a solved issue should be promoted into shared memory, or you should review prior learnings before changing a known-problem area. Do not use for trivial typos, expected failures, straightforward retries, or one-off noise with no reusable lesson.
As a process F 44/100 · Will not run — References files that are not bundled: scripts/..., references/..., assets/...
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: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/... - warning
missing-refreference to a missing file: references/... - warning
missing-refreference to a missing file: assets/...
Process rating: all ten parameters 44/100
- 0Tools and files. 3 referenced file(s) missing: scripts/..., references/..., assets/...
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (self-improvement) differs from the folder (actual-self-improvement)
- 50When it triggers. No condition that starts the skill
- 85Steps. 58 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2183 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 570: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (6 of 7)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.