BB ai-tool-research
Researches how people are using an AI tool (Claude Desktop, Cursor, OpenAI Codex, Google Gemini, or OpenClaw) and generates a Productivity Playbook plus a Skills Catalog in a consistent, rated, month-over-month format. Use when the user asks for a monthly research update on one of these tools, a productivity playbook, a skills catalog, a "what's new this month" report on an AI coding/agent tool, or wants to regenerate any of the files named `<Tool>-Productivity-Playbook.md` or `<Tool>-Skills-Catalog.md`. Also use if the user wants to run the same research cycle across all five tools.
Researches how people are using an AI tool (Claude Desktop, Cursor, OpenAI Codex, Google Gemini, or OpenClaw) and generates a Productivity Playbook plus a…
As a process B 72/100 · Nearly there — weak spots: 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: 8. 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 72/100
- 30Running it twice. 20 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 5 branches
- 85Steps. 112 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3835 tokens
- 100Progress reporting. Reports progress
- low 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (22 tags): a typed call is more reliable
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)
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 590: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 112 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.