AC safe-self-improvement
Security-hardened self-improvement skill for OpenClaw. Captures learnings, errors, and corrections with mandatory human-approval gate, automated sanitization, audit tooling, and promotion rate-limiting. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent, (3) User requests a missing capability, (4) An external API or tool fails, (5) Agent realizes knowledge is outdated, (6) A better approach is discovered. Review learnings before major tasks.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 100Steps. 84 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2883 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 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
- +1No license
- +2Single-language instructions
- +3Description length 479: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 84 items
- +4Has examples (9 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.