research-packager
Skill2 starsChanged 4 months agoMITView on GitHub
Create sanitized export packs from canonical memory for research pool
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- Academic Paper SummarizationSkill
- Accessibility WCAG AuditSkill
- API Error TroubleshootingSkill
- CI/CD Pipeline TroubleshootingSkill
- Competitor Analysis SynthesisSkill
- Customer Onboarding AssistanceSkill
- Dependency Audit ResolutionSkill
- Docker Image OptimizationSkill
- GDPR Data MappingSkill
- genome-analyzerSkill
- incident-distillerSkill
- Kubernetes Pod DebuggingSkill
- nve-genome-explorerSkill
- OWASP Input ValidationSkill
- repo-auditorSkill
- rule-patcherSkill
- Secret Leak RemediationSkill
- skill-curatorSkill
- skill-package-builderSkill
- SOC2 Policy VerificationSkill
- tama-community-summarizerSkill
- Technology Stack EvaluationSkill
- Ticket Triage and RoutingSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
When user wants to contribute data to the research pool or share with trusted users.
- Distinctive: line 58
ALWAYS ask for human confirmation before sharing.
≈ “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
Research Packager
Produces redacted, shareable packs from incident data.
When to Use
When user wants to contribute data to the research pool or share with trusted users.
Procedure
1. Select Incidents
Choose which incidents and genomes to include.
2. Redact
For each item, strip:
- agent_id
- project name
- file paths (absolute or relative)
- dates (keep only month-year)
- code snippets > 3 lines
- API keys, URLs with credentials
Keep:
- failure family
- violated invariant
- repair operator
- verifier evidence TYPE
- transferability tags
- utility scores
3. Package
Create pack file:
{
"pack_id": "PACK-YYYYMMDD-NNN",
"source_hash": "sha256 of repo manifest (for dedup)",
"redaction_version": "v1",
"genomes": [...],
"experience_units": [...],
"metadata": {
"total_incidents": 14,
"total_genomes": 5,
"stack_tags": ["node", "supabase", "cloud-run"],
"repo_maturity": "hybrid"
}
}4. Save
Output to .evolution/exports/PACK-YYYYMMDD-NNN.json
5. Human Review
ALWAYS ask for human confirmation before sharing.
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.

