design-adr-audit
Audit a blueprint against the repository's Accepted ADRs to find where it violates or contradicts a binding decision, using parallel sub-agents that each own…
Skill by kapetan-io
Chalk Labs
Need help deploying design-adr-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/kapetan-io-design-adr-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: design, 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. 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/design-adr-audit
What's inside
- Skill name
design-adr-audit- Description
- Audit a blueprint against the repository's Accepted ADRs to find where it violates or contradicts a binding decision, using parallel sub-agents that each own a slice of the ADR corpus, then a synthesized verdict. Use when `design-review` calls for it, or when asked to check a blueprint or plan against the ADRs. Read-only: it reports findings and edits nothing.
- License
- unknown
- Instructions
- 71 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from kapetan-io/dispatch
- 0.565score
design
kapetan-io
Design a feature with the user: one long conversation that settles what it must do, tests the design's shape against independent sketches, and ends in a…
SkillAFreshness: AClaude Code +9 - 0.559score
pr-respond
kapetan-io
Respond to what a build worker's PR raised (review comments, questions, failing checks) and follow it to merge.
SkillAFreshness: AClaude Code +9 - 0.559score
breakdown
kapetan-io
Break a design or a ticket into build tickets, one per piece in dependency order, then start the work or hold it.
SkillAFreshness: AClaude Code +9 - 0.559score
build
kapetan-io
Build one approved Linear ticket into a pull request as an autonomous dispatch worker.
SkillAFreshness: AClaude Code +9 - 0.559score
design-review
kapetan-io
Review a feature ticket's blueprint with the user, audit it against the repo's ADRs, then break the design down into build tickets.
SkillAFreshness: AClaude Code +9 - 0.559score
hillclimb
kapetan-io
Improve a skill's wording against a frozen `claude plugin eval` suite, one measured change at a time.
SkillAFreshness: AClaude Code +9 - 0.556score
autobots
kapetan-io
Review and merge a feature ticket's pieces as they finish, without asking, while every other ticket keeps waiting on the user.
SkillAFreshness: AClaude Code +9 - 0.553score
dispatch
kapetan-io
Drives dispatch from a session, covering how to file tickets, review worker PRs and handle what workers report.
SkillAFreshness: AClaude Code +9 - 0.553score
converse
kapetan-io
Sets how a session talks with the user, covering how to verify claims, delegate reading and ask questions.
SkillAFreshness: AClaude Code +9 - 0.553score
commit-message
kapetan-io
Write the commit message for the staged diff.
SkillAFreshness: AClaude Code +9 - 0.551score
principle-confidence-from-many-perspectives
kapetan-io
Apply when you are about to call a design, plan, ticket or root-cause claim done, or a change that would be costly if wrong.
SkillAFreshness: AClaude Code +9 - 0.536score
how
kapetan-io
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 22, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/kapetan-io/dispatch
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kapetan-io
- 0.565score
design
kapetan-io
Design a feature with the user: one long conversation that settles what it must do, tests the design's shape against independent sketches, and ends in a…
SkillAFreshness: AClaude Code +9 - 0.559score
build
kapetan-io
Build one approved Linear ticket into a pull request as an autonomous dispatch worker.
SkillAFreshness: AClaude Code +9 - 0.559score
breakdown
kapetan-io
Break a design or a ticket into build tickets, one per piece in dependency order, then start the work or hold it.
SkillAFreshness: AClaude Code +9 - 0.559score
design-review
kapetan-io
Review a feature ticket's blueprint with the user, audit it against the repo's ADRs, then break the design down into build tickets.
SkillAFreshness: AClaude Code +9 - 0.559score
hillclimb
kapetan-io
Improve a skill's wording against a frozen `claude plugin eval` suite, one measured change at a time.
SkillAFreshness: AClaude Code +9 - 0.559score
pr-respond
kapetan-io
Respond to what a build worker's PR raised (review comments, questions, failing checks) and follow it to merge.
SkillAFreshness: AClaude 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 design-adr-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
design-adr-audit skill. Agent Mart. https://agentmart.dev/skills/kapetan-io-design-adr-audit (last updated 2026-10-24)