policy-research
Skill8 starsChanged 2 months agoMITView on GitHub
Research a jurisdiction's policy or compliance question with official sources, effective dates, applicability, and product implications.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- parkjui92/policy-research-kittheir own version, first seen Oct 10, 2026
- jgeorgeai11/claude_code_resourcestheir own version, first seen Sep 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- parkjui92/policy-research-kit★ 10same name
- jgeorgeai11/claude_code_resources★ 1same 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 repository77 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- archive-milestoneSkill
- assess-product-opportunitySkill
- automate-testsSkill
- bump-versionSkill
- capture-work-itemsSkill
- commit-workSkill
- competitive-researchSkill
- consume-nats-messageSkill
- decontextualize-textSkill
- deep-researchSkill
- define-docs-normsSkill
- define-missionSkill
- define-north-starSkill
- define-roadmapSkill
- define-strategic-pillarsSkill
- define-visionSkill
- deliver-featureSkill
- design-strategic-goalsSkill
- eli5Skill
- establish-delivery-workflowSkill
- execute-delivery-workflowSkill
- generate-agent-entrySkill
- generate-github-workflowSkill
- generate-standard-readmeSkill
- inspect-artifact-stateSkill
- integrate-branchesSkill
- manage-secretSkill
- map-item-dependenciesSkill
- market-researchSkill
- orchestrate-code-reviewSkill
- orchestrate-governance-stepSkill
- orchestrate-repair-loopSkill
- orchestrate-repair-requirements-loopSkill
- orchestrate-roadmap-planningSkill
- plan-milestonesSkill
- plan-nextSkill
- ponytailSkill
- prepare-presales-responseSkill
- prepare-version-notesSkill
- prioritize-backlogSkill
- product-opportunity-analysisSkill
- promote-roadmap-itemsSkill
- publish-nats-messageSkill
- record-milestone-achievementSkill
- redeploy-localSkill
- refine-skill-designSkill
- review-architectureSkill
- review-codebaseSkill
- review-diffSkill
- review-dotnetSkill
- review-error-surfacingSkill
- review-functional-designSkill
- review-goSkill
- review-implementation-alignmentSkill
- review-javaSkill
- review-observabilitySkill
- review-orm-usageSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 28
Every obligation has an official locator, effective date and affected actor.
≈ “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: Policy Research
Purpose
Answer a bounded policy question for a named jurisdiction and date. This Skill applies the method in deep-research and emits the shared Research Report. It explains potential product implications; it does not issue a legal opinion or certify compliance.
Procedure
- Fix jurisdiction, regulated activity, actor, relevant period and as-of date. If jurisdiction is missing and material, ask or state a narrow assumption; never generalize one country's rule.
- Decompose into instruments, scope of applicability, binding obligations, official guidance, enforcement or transition timing, and product implications.
- Prioritize current official text and amendment history, then regulator guidance, then attributed interpretations. Inspect original wording and cite section or article locators. Record promulgation and effective dates separately.
- Apply deep-research's source, classification, corroboration and conflict discipline. A binding text's wording can be a Fact; an interpretation or enforcement prediction is a Claim or Inference. Mark ambiguous applicability Unknown.
- In the narrative, give an instrument table with issuer, force, effective date, affected actors, relevant clause and finding ID. Separate what the law says, what a source claims it means, and the product implication derived from cited findings.
- Explain jurisdictional or temporal conflicts, unknowns, and what legal or regulatory review could resolve them. Preserve the report's evidence core; add
domain: "policy"anddomain_detailsonly if useful.
Self-check
Every obligation has an official locator, effective date and affected actor. Every product implication traces to source-backed findings. An unresolved interpretation stays unresolved, and no compliance verdict is asserted from incomplete evidence.
Examples
Effective-date check
Input: assess how a named regulation affects a product in one jurisdiction. Output: cite the official instrument and clause, distinguish promulgation from effective date, identify affected actors, and trace each possible product change to a finding.
Jurisdiction omitted
Input: “Does this feature comply with privacy law?” with no jurisdiction or regulated actor. Output: ask for the boundary when it changes applicability; do not generalize one country's rule or issue a compliance verdict.
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.

