content-gold-miner-public
Skill2 starsChanged 2 months agoNo licenceView on GitHub
Mines a long, already-filmed video (a Descript project, webinar, masterclass, podcast, coaching call, or rambly talk) for the 3–5 strongest reel ideas already in it, ranked for YOUR ideal audience, each with the verbatim hook line and its timecode so it can be cut directly. It locates what's on tape and drafts the script for approval — it does NOT write new posts from scratch, and does NOT cut or caption. TRIGGER on "find the gold in this video," "mine this recording," "what reels are in here," "what's worth cutting from this," "find the hooks in this recording," or any variation of pulling reel-worthy moments out of a long raw video. Reads your creator profile (audience, voice, goal) from your Claude Project, or runs a quick setup if none.
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 14 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈14
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
In this repository127 other files it gives its agents.
- ab-testingSkill
- ab-test-setupSkill
- ad-creativeSkill
- adsSkill
- orchard-reviewSkill
- build-projectSkill
- check-testsSkill
- check-understandingSkill
- claude-certificationSkill
- course-guideSkill
- find-your-levelSkill
- learn-agent-skillsSkill
- learn-mcpSkill
- learnSkill
- mcpa-certificationSkill
- migration-reviewSkill
- orchard-releaseSkill
- release-publishSkill
- release-reviewSkill
- orchard-reviewSkill
- skill-catalog-builderSkill
- skill-contract-reviewerSkill
- skill-invocation-routerSkill
- skill-release-gateSkill
- skill-safety-reviewerSkill
- start-learningSkill
- ai-seoSkill
- analyticsSkill
- analytics-trackingSkill
- arxivSkill
- auto-review-loopSkill
- idea-discoverySkill
- kill-argumentSkill
- paper-writingSkill
- research-pipelineSkill
- research-reviewSkill
- semantic-scholarSkill
- aso-auditSkill
- asoSkill
- brandkitSkill
- canvas-designSkill
- career-opsSkill
- churn-preventionSkill
- remotion-motion-graphicsSkill
- clone-websiteSkill
- cold-emailSkill
- co-marketingSkill
- community-marketingSkill
- competitor-alternativesSkill
- competitor-profilingSkill
- competitorsSkill
- content-research-writerSkill
- content-strategySkill
- copy-editingSkill
- copywritingSkill
- croSkill
- customer-researchSkill
- design-taste-frontendSkill
- design-taste-frontend-v1Skill
- directory-submissionsSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.