agentleFS
clairelily2020clairelily2020/creator-workflows/skills/comic-review/SKILL.md

comic-review

Skill0 starsChanged 21 days agoMITView on GitHub

Review comic, storyboard, short-video, panel, cover, script, character design, or scene plan work from multiple creative roles. Use when the user asks to review, check, critique, or improve visual storytelling assets.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not score the work out of 10.

    line 73
  2. Distinctive:

    Do not list more than 10 findings.

    line 74
  3. Distinctive:

    If the work is an early draft, review structure before details.

    line 75
  4. Distinctive:

    If character consistency is weak, flag it before style polish.

    line 76
  5. Distinctive:

    If the first seconds or first panel fail, treat it as high severity.

    line 77
  6. Distinctive:

    If the user asks for a rewrite, provide it after the review.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Comic Review

Review the work for story clarity, visual continuity, pacing, and publishing fit.

Lead with problems and fixes. Do not pad the review with praise.

Identify The Asset

First identify what the user provided:

  • logline
  • script
  • storyboard
  • panel sequence
  • character sheet
  • cover
  • image prompt set
  • rough cut
  • final video

Then choose only the relevant review roles.

Review Roles

RoleChecks
Writermotivation, conflict, stakes, dialogue, ending
Directorpacing, emotional rhythm, camera logic, scene focus
Storyboard artistshot clarity, panel flow, composition, readability
Art directorstyle consistency, character continuity, color, lighting
Editorfirst seconds, transitions, timing, sound and subtitle rhythm
Distributionplatform fit, cover frame, title, aspect ratio, thumbnail readability

Severity

  • Blocker: must fix before generation or publishing.
  • Fix: should fix, but not fatal.
  • Consider: optional improvement.

Output Format

## Review: {asset}

Asset type:
{script / storyboard / panel sequence / rough cut / etc.}

Findings:

1. [Blocker] {role}: {issue}
   Fix: {specific change}

2. [Fix] {role}: {issue}
   Fix: {specific change}

What to keep:
- {only if useful}

Ship or continue?
{ready / revise first / not ready}

Next step:
{one concrete action}

Rules

  • Do not score the work out of 10.
  • Do not list more than 10 findings.
  • If the work is an early draft, review structure before details.
  • If character consistency is weak, flag it before style polish.
  • If the first seconds or first panel fail, treat it as high severity.
  • If the user asks for a rewrite, provide it after the review.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.