AC reels-script
Use to write an Instagram Reels script — a native, sound-off-first short-video script optimized for Instagram's discovery engine, built around a 3-second hook, watch-through, and sends (DM shares). Run when the user says "Reels script," "Instagram Reel," "make a Reel," "Reel hook," "trial reel," or wants short-form video for Instagram specifically. Reads brand-profile and voice first; writes the muted version first; structures for watch-through + sends; places IG-search keywords; picks original vs trending audio (trending audio is added natively in-app — not via WoopSocial); briefs the cover frame; outputs a production doc (shot - on-screen text - spoken - audio - timing) plus a Veo prompt pack for faceless/b-roll shots. The generic scripting craft lives in short-form-video-script; for TikTok use tiktok-script; for Shorts use youtube-shorts; hands the caption to caption-writer, publishing to instagram-reels-publishing, and scheduling to scheduling-and-queue.
Use to write an Instagram Reels script — a native, sound-off-first short-video script optimized for Instagram's discovery engine, built around a 3-second…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 7. 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 62/100
- 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. 18 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
- 100Tools and files. No external tools needed
- 100Steps. 36 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1790 tokens
- low 13 top-level sections: this looks like several domains in one skill
- medium 9 test cases, all positive: not one "should refuse" or "should ask first"
- 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 972: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 36 items
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.