Github ghec
[MIRROR] My personal AI skills
npx -y skills add papanito/ai-skills --skill github-ghecAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
specialized protocol for GHEC on ghe.com with EU Data Residency. Handles enterprise governance, IAM, audit streaming, and EU-specific compliance verification.
SKILL.md
1.9 KB, 445 tokens by cl100k_base, as published. Nobody here has run it
github-enterprise-eu-admin
CONTEXT
- Platform: GitHub Enterprise Cloud (GHEC) on
*.ghe.comsubdomains. - Data Residency: EU-specific storage for code and selected metadata.
- Tenant Isolation: Separate from public github.com.
PRE-FLIGHT CHECK
Before answering, confirm:
- License/Plan: GHEC with Data Residency (ghe.com)?
- Entity Level: Enterprise Account, Organization, or Repository?
- Data Scope: Code-at-rest (EU) vs telemetry/support paths (Global)?
PROTOCOLS
1. Governance & IAM
- Enterprise Account level overrides for child orgs.
- Least Privilege roles (Enterprise Owner vs Org Owner vs Member).
- SAML/OIDC as IAM source of truth.
2. Audit & Retention
- >90 days retention: Use Audit Log Streaming (not UI export).
- Address buffering, latency, downstream SIEM/storage config.
- Focus on Actor, Action, Repository, Timestamp for compliance.
3. Residency Verification
- "Is all data in the EU?" → STOP. Provide checklist:
- Code/Git data location
- Action logs/Artifacts location
- Exception disclosure (Telemetry, Global Profiles, Support Access)
OUTPUT SCHEMA
- TL;DR: 1-2 sentence summary.
- Context & Assumptions: Tenant state (e.g. "Assumes EU residency active").
- Operational Steps: Admin UI click-path or CLI/API commands.
- Compliance & Retention: Impact on audit logs / data residency.
- Verification Artifacts: What an auditor needs (e.g. "Export log JSON").
GUARDRAILS
- No hallucination. Beta/tenant-dependent → "Verification Required" + docs link.
- Terminology.
github.com(Standard) vsghe.com(Residency). - Neutrality. Separate documentation-backed facts from recommendations.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most audit compliance skills give in 445 tokens
Counted across 937 of the 1,487 authors here whose files we hold, read 2026-08-07
- Fetch latest guidelines before each reviewin 43 of 937, across 3 files
- group findings by severityin 43 of 937
- Check files against all fetched rulesin 42 of 937, across 2 files
- Output findings in terse file:line formatin 41 of 937, across 3 files
- Ask user which files to review if none specifiedin 41 of 937, across 3 files
- Read specified files or prompt user for filesin 39 of 937, across 1 file
- generate the audit reportin 33 of 937, across 30 files
- assign a severity to every findingin 25 of 937
- run automated accessibility scansin 23 of 937, across 13 files
- output a markdown audit reportin 22 of 937
- map findings to WCAG criteriain 20 of 937, across 10 files
- confirm audit scopein 19 of 937, across 9 files
Said here and by no other author read
- verify license, entity level, and data scope before answering
- apply enterprise account level overrides for child organizations
- use SAML or OIDC as the IAM source of truth
- use audit log streaming for retention over 90 days
- include actor, action, repository, and timestamp for compliance
- provide a residency checklist when asked if all data is in the EU
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.