AD skill-factory
Build and publish OpenClaw skills from recurring pain points. Scans .learnings/ for errors that hit 3+ recurrences, scaffolds skills from them, and publishes to ClawHub. Use when: (1) you want to create a new skill from a pain point, (2) you want to check if any recurring errors are ready for extraction, (3) you want to package and publish a skill in one step, (4) you want to automate the pain-to-skill pipeline. The thing that builds the thing.
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, 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: 3. 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 45/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-factory) differs from the folder (wren-skill-factory)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 75Steps. 3 steps
- 100Execution cost. Instruction body is 700 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
- +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 448: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (9 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.