AC hui-yi
Trigger for cold-memory recall and archive work under memory/cold/. Use only for explicit requests about older low-frequency context, historical continuity, resurfacing, cooling, rebuild, and repetition-driven reinforcement — not for any casual mention of words like "archive" or "remember". Do not use for fresh daily notes, stable high-frequency facts, tooling/setup notes, or unvalidated new learnings. Also covers an optional opt-in hook (installed via scripts/install_hook.py, enabled in openclaw.json only with --enable) that accumulates Session signals from recall-related turns into memory/cold/ notes and tags.json.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 36. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 43 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 758 tokens
- 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
- +3Output format is not stated: the model decides each time
- -45 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 624: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (1 code blocks)
- +3All 11 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.