agentsclimarketplace

Security compliance gate

Skill jukrap/ai-agent-playbook/skills/security/security-compliance-gate

Reusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.

Install
npx -y skills add jukrap/ai-agent-playbook --skill security-compliance-gate

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 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

Use when deciding security or compliance gates before merge, release, publication, or handoff.

SKILL.md

1.2 KB, 214 tokens by cl100k_base, as published. Nobody here has run it

Security Compliance Gate

Use this as the primary security skill for deciding whether a change can proceed through a merge, release, publication, or handoff gate.

Workflow

  1. Identify the artifact, audience, environment, data scope, trust boundary, and required policy or compliance evidence.
  2. Route implementation-specific questions to security-review, auth-access-control, dependency-supply-chain-review, or license-notice-review instead of duplicating their checks.
  3. Classify findings as block, warn, or document, and record the owner, expiry, compensating evidence, and verification path for any accepted risk.
  4. Verify public-doc hygiene, translation or notice coverage, runtime evidence safety, and required local scanner or repository-defined check output before calling the gate passed.

Reference

Read references/gate-severity-model.md before recording block, warn, document, or accepted-risk outcomes.

Read references/evidence-routing.md when connecting security, dependency, license, runtime schema, locator, or public documentation checks.

What ships with it: 2 files

5.5 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most audit compliance skills give in 214 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

  • identify artifact, audience, environment, and trust boundary
  • route implementation questions to specific review skills
  • do not duplicate checks from other security skills
  • classify findings as block, warn, or document
  • record owner, expiry, and evidence for accepted risk
  • verify public-doc hygiene before passing gate

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.

Keep looking

Skills are one crate of 326,970. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.