AB cm-twitter-thread-coach
Audit, restructure, and rewrite Twitter/X threads for engagement, follower growth, and click-through. Critiques hooks, thread length, visual hierarchy, closing CTAs, and reply-bait tactics. Use when asked to review a Twitter thread, fix a hook tweet, improve a thread's engagement, rewrite a draft thread, optimize for the X algorithm, increase follower conversion from threads, or coach a builder/founder/creator on thread structure. Triggers on "twitter thread", "x thread", "thread review", "thread coach", "hook tweet", "thread engagement", "tweet structure", "rewrite my thread", "thread template", "follower growth", "viral thread", "thread CTA".
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
- warning
body-longSKILL.md body ≈ 6669 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 14 mutating operations with no state check
- 40Consistency. Frontmatter name (cm-twitter-thread-coach) differs from the folder (twitter-thread-coach)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 8 branches
- 70Execution cost. Instruction body is 6669 tokens
- 100Tools and files. No external tools needed
- 100Steps. 71 steps
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 12 example trigger phrases
- +3Description length 652: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 71 items
- +3Output format is stated explicitly
- +4Has examples (30 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.