AD self-improving-agent
Captures learnings, errors, and corrections for continuous improvement. Use when: (1) A command fails unexpectedly, (2) User corrects you ('No, that's wrong...', 'Actually...'), (3) User requests a missing capability, (4) An external API or tool fails, (5) You realize your knowledge is outdated, (6) A better approach is found for a recurring task. Also review `.learnings/` before major tasks. Trigger words: 'actually', 'wrong', 'outdated', 'I wish you could', 'why can't you', non-zero exit code.
As a process D 46/100 · Unfinished process — weak spots: result and completion, 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: 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 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (self-improving-agent) differs from the folder (self-improvement-agent)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 100Steps. 22 steps
- 100Execution cost. Instruction body is 1511 tokens
- 100Progress reporting. Reports progress
- low 13 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
- +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 500: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.