Chalk Labs
Need help deploying compliance-evidence?
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/paulthorson-compliance-evidence
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
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/compliance-evidence
What's inside
- Skill name
compliance-evidence- Description
- Stateless skill. Checks whether there is evidence the work is compliant Returns findings with severity.
- License
- Apache-2.0
- Instructions
- 20 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Compliance Evidence Checks whether there is evidence the work is compliant This is the shared check that any reviewer can run. ## Method 1. Read the work in full. 2. Apply the check to the work. 3. Assign severity (BLOCKER/CONCERN/NOTE) to each finding. ## Output ``` ## Findings - <finding> | Severity: BLOCKER/CONCERN/NOTE | What would clear it ``` A BLOCKER finding is a veto: only a human clears it.
From paulthorson/agentic-governance, Apache-2.0.
More from paulthorson/agentic-governance
- 0.609score
adversarial-engineer
paulthorson
Run engineering work (code, architecture, config, infrastructure) through a governed adversarial loop instead of producing it in one pass.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
framework-technical-writing
paulthorson
Use when writing or reviewing public framework git docs.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
complexity-analysis
paulthorson
Map cyclomatic, coupling, and state-space hotspots in a proposed change, without a verdict, so the Critic can check maintainability against facts.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
constraint-elicitation
paulthorson
Elicit the non-negotiable constraints on an engineering change (performance, budget, stack, ops, security) and their owners, so a fast-path can never silently…
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
ops-runbook
paulthorson
Produce deploy, rollback, monitor, and incident-runbook artifacts for an engineering change, so the Reliability Reviewer and Ops Advocate can check them.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
option-generation
paulthorson
Generate at least two distinct implementation options for an engineering problem, each with a "trades away X to get Y" sentence, without picking one.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
performance-check
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
altitude-check
paulthorson
Re-state the engineering request at problem altitude, naming the assumed solution so it can be examined rather than taken at face value.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
doc-usability-check
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
liability-scan
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
policy-alignment-check
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
regulatory-gate-check
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Sep 29, 2026 (1 month ago)
- Last release
- Oct 15, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Website
- www.agenticgovernance.app
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from paulthorson
- 0.609score
adversarial-engineer
paulthorson
Run engineering work (code, architecture, config, infrastructure) through a governed adversarial loop instead of producing it in one pass.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
framework-technical-writing
paulthorson
Use when writing or reviewing public framework git docs.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
constraint-elicitation
paulthorson
Elicit the non-negotiable constraints on an engineering change (performance, budget, stack, ops, security) and their owners, so a fast-path can never silently…
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
altitude-check
paulthorson
Re-state the engineering request at problem altitude, naming the assumed solution so it can be examined rather than taken at face value.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
complexity-analysis
paulthorson
Map cyclomatic, coupling, and state-space hotspots in a proposed change, without a verdict, so the Critic can check maintainability against facts.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
ops-runbook
paulthorson
Produce deploy, rollback, monitor, and incident-runbook artifacts for an engineering change, so the Reliability Reviewer and Ops Advocate can check them.
SkillAFreshness: A★ 4Claude 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 compliance-evidence 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
compliance-evidence skill. Agent Mart. https://agentmart.dev/skills/paulthorson-compliance-evidence (last updated 2026-10-24)