AC listicle-and-roundup
The list/roundup content type — design honestly-curated, scannable, AI-citable listicles ("7 ways to X", "best tools for Y") and expert / product / link roundups. Use when someone wants a listicle, a "best of" or "top N" list, a ranked recommendation list, an expert roundup, a product/affiliate roundup, or a curated resource list. Ranked "best-of" lists are among the most-cited formats in AI search. Uses the RANKS framework. Reads brand-profile + audience-research first. The agent designs the list and frames the cuts; for roundups it drafts the contributor ask; the human secures real contributor quotes/consent and verifies product facts; WoopSocial publishes the cuts. Feeds the format writers and ai-search-optimization + social-seo. NEVER fabricates items, quotes, or rankings, or pads to a number; discloses affiliate/own-product. Distinct from carousel-writer/thread-writer, educational-content-and-how-to, data-and-original-research, and competitor-analysis.
The list/roundup content type — design honestly-curated, scannable, AI-citable listicles ("7 ways to X", "best tools for Y") and expert / product / link…
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 6. 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 56/100
- 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
- 30Running it twice. 4 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1685 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low No test case covers injection arriving through data
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)
- +3Description length 971: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 9 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.