run-build
Skill0 starsChanged 5 months agoMITView on GitHub
Build the final render for a content item — narration then stitch/captions/finalize — by running the project's configured build command(s). Thin runner for the build stage of a content-pipeline shorts project. Use when advancing an item whose clips are done and need assembling into the final video.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- morethanwords/twebtheir own version, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- morethanwords/tweb★ 2.7ksame name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository57 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ask-mattSkill
- cast-memberSkill
- check-feedbackSkill
- codebase-designSkill
- content-pipeline-initSkill
- content-pipelineSkill
- data-analystSkill
- decision-mappingSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- draft-asset-promptsSkill
- edit-articleSkill
- fableSkill
- game-concept-interviewSkill
- git-guardrails-claude-codeSkill
- global-guidelinesSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- karpathy-guidelinesSkill
- launch-sessionSkill
- lesson-reviewSkill
- link-claude-skillsSkill
- loop-meSkill
- migrate-to-shoehornSkill
- obsidian-vaultSkill
- opusSkill
- prototypeSkill
- publish-metadataSkill
- resolving-merge-conflictsSkill
- retrieve-lessonsSkill
- reviewSkill
- rotate-sessionSkill
- run-clipsSkill
- scaffold-exercisesSkill
- session-sandboxSkill
- setup-matt-pocock-skillsSkill
- setup-pre-commitSkill
- setup-status-lineSkill
- showrunner-shortSkill
- sonnetSkill
- tddSkill
- teachSkill
- to-issuesSkill
- to-prdSkill
- triageSkill
- verify-outputsSkill
- wrap-allSkill
- wrapSkill
- writing-beatsSkill
- writing-fragmentsSkill
- writing-great-skillsSkill
- writing-shapeSkill
The file
Files
Thin runner for the build stage: assemble locked clips into the final render by
running the project's own build script(s). It owns running and recovering, not the
engine — the engine lives in the project's scripts, invoked via project.md.
Steps
- Run the configured command(s). Take
commands.buildfromproject.md, substitute{item}with the item's directory, and run it. It typically chains narration → stitch → captions → finalize; run them in the given order. This is the authoritative command — don't guess from prose. Ifcommands.buildis missing, stop and ask. - On failure, re-run only the failing subcommand, not the whole chain — each stage's output feeds the next, so a captions failure shouldn't force a re-stitch.
- Respect engine conventions in
context.md(clip-native vs. stripped audio, bgm, logo bumper, caption style, word-timing source).context.mdoverrides on conflict — don't assume; check. - Output the final render plus any QA artifact the charter expects (e.g.
qa_checklist.md) so the render gate has something to attach. Leavepipeline.mdupdates to the orchestrator.
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
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.

