AC research-account
Research one company before a meeting and hand back a briefing, powered by Cargo — what it does, what it publicly says is hard right now, and who it names as competition, each line traceable to where it came from. Triggers: "research this company", "brief me on this account", "prep me for this meeting", "what should I know about them", "write me a one-pager on", "what are they struggling with", "who do they compete with". Meeting prep, briefing, dossier, talking points. Skip when: you want many companies filtered rather than one understood — use build-tam-list; or you want the people to contact there — use find-stakeholders.
Research one company before a meeting and hand back a briefing, powered by Cargo — what it does, what it publicly says is hard right now, and who it names as…
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 53/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2126 tokens
- 100Running it twice. Mutating operations check current state
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
- +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
- +5Description quotes 7 example trigger phrases
- +3Description length 632: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.