public-release-audit
Fail closed on privacy, provenance, license, history, and integration risks before a public catalog release.
Skill by RobGonWin
Chalk Labs
Need help deploying public-release-audit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/robgonwin-public-release-audit-c73265
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
public-release-audit- Description
- Fail closed on privacy, provenance, license, history, and integration risks before a public catalog release.
- License
- MIT
- Instructions
- 16 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Public release audit Run against the exact candidate tree. 1. Confirm only the approved catalog projects and skills exist. 2. Run `python scripts/validate_catalog.py` and the unit tests. 3. Verify all project declarations remain self-declared and unverified. 4. Verify upstream revisions are full commit pins and sources without reuse terms remain metadata-only. 5. Search for credentials, account exports, identifying records, recordings, generated captures, and external integration fields. 6. Confirm actions are immutable pins with `contents: read` permissions. 7. Confirm the candidate contains no inherited history, submodules, large-file objects, or unexpected remotes. 8. Require human review for publication, submission, attestation, or license changes. Any uncertain result blocks release until a human reviewer resolves it.
From RobGonWin/deving-research-ecosystem, MIT.
More from RobGonWin/deving-research-ecosystem
- 0.521score
github-cloud-loop
RobGonWin
Review the public ecosystem catalog's Loop Engineering readiness locally or in a cloud agent using read-only repository context and the allowlisted Loop MCP…
SkillBFreshness: BClaude Code +9 - 0.517score
physionet-public-data
RobGonWin
Plan, acquire, or verify only allowlisted open PhysioNet fixtures for public Deving-Senses research, with exact hashes, bounded storage, and no…
SkillBFreshness: BClaude Code +9 - 0.516score
contribute-to-deving-senses
RobGonWin
Prepare a scoped contribution to Deving Senses with synthetic multimodal fixtures, provenance, and bounded research claims.
SkillBFreshness: BClaude Code +9 - 0.516score
contribute-to-memory-provenance
RobGonWin
Prepare a scoped contribution to public memory-provenance tooling with source separation and calibrated evidentiary language.
SkillBFreshness: BClaude Code +9 - 0.516score
graphify
RobGonWin
Build a code-and-documentation dependency map for this public catalog while excluding history, generated files, and protected inputs.
SkillBFreshness: BClaude Code +9 - 0.516score
review-memory-provenance-contributions
RobGonWin
Review memory-provenance contributions for source independence, uncertainty, citation quality, and safe public boundaries.
SkillBFreshness: BClaude Code +9 - 0.516score
contribute-to-aave
RobGonWin
Prepare a scoped contribution to the AAVE public archival-evidence tooling using synthetic examples and explicit provenance.
SkillBFreshness: BClaude Code +9 - 0.513score
public-release-audit
RobGonWin
Fail closed on privacy, provenance, license, history, and integration risks before a public catalog release.
SkillBFreshness: BClaude Code +9 - 0.513score
review-aave-contributions
RobGonWin
Review AAVE public contributions for archival rigor, synthetic-test boundaries, compatibility, and release safety.
SkillBFreshness: BClaude Code +9 - 0.513score
review-deving-senses-contributions
RobGonWin
Review Deving Senses contributions for provenance, consent boundaries, reproducibility, and calibrated claims.
SkillBFreshness: BClaude Code +9 - 0.513score
context-loop
RobGonWin
Run a bounded maker-checker loop for catalog changes with explicit budgets, gates, and human approval points.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 25, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from RobGonWin
- 0.521score
github-cloud-loop
RobGonWin
Review the public ecosystem catalog's Loop Engineering readiness locally or in a cloud agent using read-only repository context and the allowlisted Loop MCP…
SkillBFreshness: BClaude Code +9 - 0.517score
physionet-public-data
RobGonWin
Plan, acquire, or verify only allowlisted open PhysioNet fixtures for public Deving-Senses research, with exact hashes, bounded storage, and no…
SkillBFreshness: BClaude Code +9 - 0.516score
contribute-to-deving-senses
RobGonWin
Prepare a scoped contribution to Deving Senses with synthetic multimodal fixtures, provenance, and bounded research claims.
SkillBFreshness: BClaude Code +9 - 0.516score
contribute-to-memory-provenance
RobGonWin
Prepare a scoped contribution to public memory-provenance tooling with source separation and calibrated evidentiary language.
SkillBFreshness: BClaude Code +9 - 0.516score
graphify
RobGonWin
Build a code-and-documentation dependency map for this public catalog while excluding history, generated files, and protected inputs.
SkillBFreshness: BClaude Code +9 - 0.516score
review-memory-provenance-contributions
RobGonWin
Review memory-provenance contributions for source independence, uncertainty, citation quality, and safe public boundaries.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get public-release-audit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
public-release-audit skill. Agent Mart. https://agentmart.dev/skills/robgonwin-public-release-audit-c73265 (last updated 2026-10-24)