Chalk Labs
Need help deploying production-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/junmystery-production-audit
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, productivity
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. Checked Oct 25, 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/production-audit
What's inside
- Skill name
production-audit- Description
- Production readiness audit workflow. Use when asked whether an app, feature, release, PR, or deployment is ready to ship, what might break in production, or what blockers remain before launch.
- License
- MIT
- Instructions
- 23 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Production Audit Use this skill for release-readiness risk review, not as a replacement for formal compliance review. ## What to Apply - Build the audit from local evidence, CI status, docs, tests, configs, and observable behavior. - Inspect auth, data, background jobs, external integrations, environment setup, observability, and rollback paths where they exist. - Separate ship blockers from follow-up risks. - Do not upload repo contents or run external scanners unless the user explicitly approves. - Tie each recommendation to a file, command result, deployed behavior, or documented gap. ## Reference Files - [ai-agent-standards/quality-control/audit-ai-code-full.md](../../ai-agent-standards/quality-control/audit-ai-code-full.md) - [ai-agent-standards/quality-control/ci-cd-gates.md](../../ai-agent-standards/quality-control/ci-cd-gates.md) - [ai-agent-standards/engineering-practices/RELEASE_PROCESS.md](../../ai-agent-standards/engineering-practices/RELEASE_PROCESS.md) ## Output Expectation Return a ship, ship-with-caveats, or block recommendation with the highest-risk findings first.
From JunMystery/AI-Agent-Standards, MIT.
More from JunMystery/AI-Agent-Standards
- 0.463score
skill-stocktake
JunMystery
Local skill quality audit workflow.
SkillCFreshness: CClaude Code +9 - 0.463score
api-design
JunMystery
API contract design and review workflow.
SkillCFreshness: CClaude Code +9 - 0.463score
architecture-decision-records
JunMystery
Architecture decision record workflow.
SkillCFreshness: CClaude Code +9 - 0.463score
prompt-optimizer
JunMystery
Prompt analysis and optimization workflow for turning rough requests into clearer task prompts.
SkillCFreshness: CClaude Code +9 - 0.463score
rules-distill
JunMystery
Standards distillation workflow.
SkillCFreshness: CClaude Code +9 - 0.463score
skill-scout
JunMystery
Search-first workflow for finding an existing skill before creating or forking a new one.
SkillCFreshness: CClaude Code +9 - 0.463score
accessibility
JunMystery
Accessibility design and audit workflow for inclusive UI.
SkillCFreshness: CClaude Code +9 - 0.463score
codebase-onboarding
JunMystery
Fast repo reconnaissance and onboarding workflow for unfamiliar codebases.
SkillCFreshness: CClaude Code +9 - 0.463score
coding-standards
JunMystery
Baseline coding conventions for readability, naming, immutability, KISS, DRY, and code-quality review.
SkillCFreshness: CClaude Code +9 - 0.463score
context-budget
JunMystery
Token and context budget audit for agents, skills, rules, and MCP overhead.
SkillCFreshness: CClaude Code +9 - 0.463score
database-migrations
JunMystery
Database migration planning and review workflow.
SkillCFreshness: CClaude Code +9 - 0.463score
documentation-lookup
JunMystery
Live documentation lookup workflow for frameworks, libraries, and APIs.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 25, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/JunMystery/AI-Agent-Standards
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from JunMystery
- 0.556score
ai-behavior-trees-utility-ai
JunMystery
Build a production behavior-tree runtime (Blackboard, action/condition leaves, sequence/selector/parallel composites, decorators) and a Utility AI system…
SkillAFreshness: AClaude Code +9 - 0.497score
agent-workflow-ops
JunMystery
Canonical agentic and autonomous workflow operations for agent harnesses, agentic engineering, agentic OS design, continuous loops, dynamic workflow mode, and…
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
architecture-decision-records
JunMystery
Capture architectural decisions as structured ADRs, document APIs, write inline comments on intent, and maintain READMEs and changelogs.
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
browser-qa
JunMystery
Automate visual testing, UI interaction verification, accessibility audits, and runtime debugging using browser automation and Chrome DevTools MCP.
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
adaptive-language
JunMystery
Adjust terminology based on user technical level.
SkillCFreshness: C★ 2Claude Code +9 - 0.492score
agent-guidance
JunMystery
Core system standards check and token-optimized codebase context retrieval.
SkillCFreshness: C★ 2Claude 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 production-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
production-audit skill. Agent Mart. https://agentmart.dev/skills/junmystery-production-audit (last updated 2026-10-24)