social-source-miner
Skill0 starsChanged 3 months agoMITView on GitHub
Turn notes, changelogs, transcripts, or research into a traceable source brief for social content.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- social-brand-voiceSkill
- social-carousel-storyboardSkill
- social-content-calendarSkill
- social-platform-adapterSkill
- social-quality-auditorSkill
- social-repurposerSkill
- social-short-video-scriptSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 42
No claim appears without a traceable source or an unverified label.
- Distinctive: line 49
Do not browse private locations or files outside the user-provided scope.
- Distinctive: line 51
Never convert assumptions into facts.
- Distinctive: line 52
Stop at the source brief; do not draft or publish automatically.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Social Source Miner
Purpose
Extract useful, defensible social angles from real source material before drafting begins.
Inputs
- One or more user-approved source documents
- Target audience and campaign objective
- Optional time window and topics to exclude
Workflow
- List the sources and label their reliability.
- Extract claims, examples, decisions, mistakes, and surprising details.
- Attach each claim to a source location or mark it unverified.
- Rank angles by usefulness, specificity, novelty, and evidence strength.
- Separate facts from interpretation and opinion.
- Recommend the best three angles with a reason for each.
Output
# Source brief
## Source inventory
## Verified claims
| Claim | Source | Confidence |
## Human stories and examples
## Candidate angles
## Claims requiring verification
## Recommended lead angleQuality gate
- No claim appears without a traceable source or an unverified label.
- Recommendations contain concrete detail, not generic topic labels.
- The brief preserves meaningful disagreement between sources.
- The lead angle matches the stated audience and objective.
Safety
- Do not browse private locations or files outside the user-provided scope.
- Redact customer, employee, and partner information unless approved for use.
- Never convert assumptions into facts.
- Stop at the source brief; do not draft or publish automatically.
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.

