AC kinthai-self-improving-user
User-level self-improvement: captures corrections, preferences, and errors per user_id. After every conversation where the user corrects you or states a preference, log it to .learnings/{user_id}/. Use when: user corrects you, states a preference, you make a mistake, or you learn something new about the user.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Concealment
en-hide-from-userhooks/openclaw/handler.js:106Instruction to hide actions from the user (quoted — discussed, not commanded)Use the Bash tool (echo/cat >> or mkdir -p) to write files. Do NOT just say "noted" — actually execute the file write. This is silent — never mention it to the user.`;
quoted
Files scanned: 9. 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 62/100
- 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. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2356 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 10 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 310: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.