AC tcms-writer
For tech-product marketing teams — turns a product knowledge base into brand-side long-form drafts (blogs, case studies, product write-ups), not third-party analysis. Produces only 1500-3000 word long-form drafts from a content brief; does not handle social posts, short content, or channel adaptation. Not for neutral industry research — use industry-deep-dive-pipeline for that.
For tech-product marketing teams — turns a product knowledge base into brand-side long-form drafts (blogs, case studies, product write-ups), not third-party…
As a process C 57/100 · 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "read_when" - note
frontmatter-keyunknown frontmatter key "disable"
Process rating: all ten parameters 57/100
- 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
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 981 tokens
- 100Running it twice. No mutating operations
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 380: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.