skill-catalog
Skill2 starsChanged 7 months agoMITView on GitHub
List the shipped video-evaluator skills so an agent can discover the shared review and artifact-intake surface.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Starryboyjosh/skill-catalog-sortertheir own version, first seen Oct 13, 2026
- rongarede/claude-skills-orchestrationtheir own version, first seen Mar 27, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- rongarede/claude-skills-orchestration★ 1same name
- Starryboyjosh/skill-catalog-sorter★ 0same 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 repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- compare-video-runsSkill
- install-skill-packSkill
- layout-safety-reviewSkill
- package-review-promptSkill
- review-bundleSkill
- segment-evidenceSkill
- segment-storyboardSkill
- source-media-signalsSkill
- storyboard-extractSkill
- storyboard-ocrSkill
- storyboard-transitionsSkill
- storyboard-understandSkill
- video-artifact-intakeSkill
- video-shotsSkill
- video-technical-reviewSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 2 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this when an agent needs to discover the shipped capabilities in video-evaluator before choosing a narrower tool.
- Very specific: line 29
Run this first when you are dropped into an unfamiliar repo or an installed .video-evaluator pack and do not know which narrower skill is …
- Distinctive: line 31
After catalog discovery, choose the smallest skill that answers the task:
- Very specific: line 33
Use video-artifact-intake to map a run directory before reviewing it.
- Very specific: line 34
Use review-bundle for a fast status summary of one run.
- Very specific: line 35
Use storyboard-extract, storyboard-ocr, storyboard-transitions, and storyboard-understand in that order for visual evidence.
- Very specific: line 37
Use compare-video-runs only when two bundles are available.
- Very specific: line 38
Use package-review-prompt when another agent needs a grounded prompt.
- Distinctive: line 42
Do not run this repeatedly once you already know the needed skill.
- Very specific: line 47
If the catalog runner is missing, the skill pack may not be installed correctly.
- Very specific: line 48
Use the repo-side runner from the source checkout, or run install-skill-pack from the source repo if you need to materialize the pack …
≈ “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.
Files
Skill Catalog
Use this when an agent needs to discover the shipped capabilities in
video-evaluator before choosing a narrower tool.
Inputs
Pass an empty JSON object:
{}The runner reads JSON from stdin and returns JSON on stdout.
Outputs
The result lists each shipped skill with its name, description, example request path, and local runner hints. Treat the catalog as discovery metadata, not as a review result.
Sequencing Guidance
Run this first when you are dropped into an unfamiliar repo or an installed
.video-evaluator pack and do not know which narrower skill is appropriate.
After catalog discovery, choose the smallest skill that answers the task:
- Use
video-artifact-intaketo map a run directory before reviewing it. - Use
review-bundlefor a fast status summary of one run. - Use
storyboard-extract,storyboard-ocr,storyboard-transitions, andstoryboard-understandin that order for visual evidence. - Use
compare-video-runsonly when two bundles are available. - Use
package-review-promptwhen another agent needs a grounded prompt.
Abstention Rules
Do not run this repeatedly once you already know the needed skill. Do not use it as proof that artifacts exist; it only describes available capabilities.
Failure Modes
If the catalog runner is missing, the skill pack may not be installed correctly.
Use the repo-side runner from the source checkout, or run install-skill-pack
from the source repo if you need to materialize the pack elsewhere.
Repo-side runner:
node --import tsx scripts/harness/skill-catalog.ts
Installed-pack runner:
node ./.video-evaluator/agent/run-tool.mjs skill-catalog
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.