AF thread-writer
Use to write a thread — a connected sequence of posts on X/Twitter or Threads that tells one story or makes one argument across multiple posts. Run when the user says "write a thread," "turn this into a thread," "X thread," "Twitter thread," "thread about X," or has a multi-beat idea that won't fit one post. Reads brand-profile and voice first, uses hook-writer for the opening post (which must hook AND promise the payoff), builds one cohesive idea where every post earns the next, and lands a close with one CTA. Knows when a single post beats a thread. Naming trap: "write a thread" means this multi-post chain; "post on/to Threads" means a single post on Meta's Threads app — use threads-post for that. For a single caption use caption-writer; for just the opening hook use hook-writer.
Use to write a thread — a connected sequence of posts on X/Twitter or Threads that tells one story or makes one argument across multiple posts.
As a process F 44/100 · Will not run — References files that are not bundled: references/platform-and-when.md, references/post-craft.md, references/architecture.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/platform-and-when.md - warning
missing-refreference to a missing file: references/post-craft.md - warning
missing-refreference to a missing file: references/architecture.md - warning
missing-refreference to a missing file: references/examples.md
Process rating: all ten parameters 44/100
- 0Tools and files. 4 referenced file(s) missing: references/platform-and-when.md, references/post-craft.md, references/architecture.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1350 tokens
- low 11 top-level sections: this looks like several domains in one skill
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
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 792: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 27 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.