agentleFS
ttalkkaklabttalkkaklab/social-flow/skills/review-context/SKILL.md

review-context

Skill1 starsChanged 3 months agoApache-2.0View on GitHub

Reviews and improves audience comprehension; stops before camera design. Use only when the user asks for a context review.

2 other projects use a version of this.

Adopted by

Most recently taken up by

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:

    Follow the production order.

    line 12
  2. Distinctive:

    Read the existing text storyboard.

    line 14
  3. Distinctive:

    Use character scenarios for observable action.

    line 16
  4. Distinctive:

    Create an audience-only export with stable beat/cut IDs, in presentation order.

    line 18
  5. Distinctive:

    Check entrances, elapsed time, listening distance, object transfers and setup/payoff.

    line 27
  6. Distinctive:

    Stop after the review; this command does not authorize images or video.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Review Context

Runs only when the user asks for it (user directive 2026-10-31); no other step waits on it. Follow the production order.

Read the existing text storyboard; this command also accepts a completed episode or storyboard path. Preserve its ending and assets unless a demonstrated defect requires a change. Use character scenarios for observable action.

Create an audience-only export with stable beat/cut IDs, in presentation order. Include only visible action, audible dialogue and narration. Exclude synopsis, hidden motives, character biographies, necessity arguments, intended meaning and prior scores. At this stage a cut ID names a required presentation unit, not a finished camera specification.

Give a fresh independent host reviewer only that export and the frozen rubric. First ask them to reconstruct what happened without explaining the author's intention. For every consequential transition, ask who learned what, from which visible/audible evidence, why that supports the next choice, and what the viewer can understand at that point. Check entrances, elapsed time, listening distance, object transfers and setup/payoff. A character's knowledge cannot come from the writer's knowledge. A line such as “realizes the betrayal and leaves” is not evidence that the audience saw how they learned it.

Require quoted source evidence and beat/cut IDs in audienceRead.transitions. Cover the whole story, including silent events and the ending. Record uncertainty and missing context before revealing intentions for comparison. Do not reward familiarity with the premise or infer an omitted shot. Every required fact must have a planned presentation; withheld information is valid only if the intended uncertainty remains understandable.

Have the author repair actual actions, speech or missing presentation units, not the synopsis or reviewer report, and repeat the blind review on the revised export. Preserve failed reports. A new reviewer sees the revised audience export without earlier verdicts. Stop after the review; this command does not authorize images or video.

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.