AC openclaw-deep-research
Coordinate deep, source-verifiable research projects in OpenClaw using AgentSkills-compatible folders, local artifact tracking, and explicit evidence ledgers. Use when the user wants a high-quality report or investigation that spans many sources, needs auditable claims, benefits from delegation, or must manage context-window limits by writing project state to local files during an OpenClaw workflow.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 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 60/100
- 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
- 40Consistency. Frontmatter name (openclaw-deep-research) differs from the folder (multi-agent-deep-research)
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 58 steps
- 100Execution cost. Instruction body is 1576 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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 402: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 58 items
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.