AB content-repurpose
Transform one piece of long-form content (transcript, blog post, article, video script, doc) into platform-tailored variants — X/Twitter threads, LinkedIn posts, blog excerpts, short-video hooks, and newsletter snippets. Use when the user wants to adapt a single source into multiple social/marketing formats while preserving the source's voice, claims, and intent. Triggers on phrases like "repurpose this", "turn this into tweets/LinkedIn/social posts", "create a content pack from this", "adapt for [platform]", "spin this off into shorts/threads".
As a process B 76/100 · Nearly there — weak spots: running it twice, progress reporting
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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 76/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (read, 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
- 100Steps. 46 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1104 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 551: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.