audit-choices
Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code…
Skill by dzhng
Chalk Labs
Need help deploying audit-choices?
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/dzhng-audit-choices
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, agent-building
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/audit-choices
What's inside
- Skill name
audit-choices- Description
- Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or committing AI-implemented work, when integrating a delegated subagent's pass, or when a fix "works" but might be a point fix.
- License
- MIT
- Instructions
- 163 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
More from dzhng/skills
- 0.831score
explore-unknowns
dzhng
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.831score
cinematic-shot
dzhng
Shoot software UI like a film.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.831score
isometric-motion
dzhng
Build animations and interactive elements (explainers, figures, hero visuals, step-through walkthroughs) in the crafted isometric "Anatomy" style, with many…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.831score
xiaohei-illustrations
dzhng
Generate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.827score
screenshot-critique
dzhng
Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.827score
compare-screenshots
dzhng
Compare screenshots against the intended design, distinguishing approved references from historical baselines.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.825score
claude
dzhng
Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.825score
audit-tests
dzhng
Audit whether tests earn their maintenance cost and which suite owns each contract.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.825score
write-spec
dzhng
Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.825score
codex
dzhng
Use the local Codex CLI as an independent second agent.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.825score
refactor-clean
dzhng
Refactor cleanly instead of layering sediment.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.825score
code-review
dzhng
Review changed code for naming, stale references, unnecessary complexity, and comment quality.
SkillAFreshness: A★ 1.4KClaude Code +9
Signals
- Stars
- 1,379
- Forks
- 84
- Open issues
- 0
- Last commit (this folder)
- Aug 13, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dzhng/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dzhng
- 0.831score
cinematic-shot
dzhng
Shoot software UI like a film.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.831score
explore-unknowns
dzhng
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.831score
xiaohei-illustrations
dzhng
Generate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.831score
isometric-motion
dzhng
Build animations and interactive elements (explainers, figures, hero visuals, step-through walkthroughs) in the crafted isometric "Anatomy" style, with many…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.827score
screenshot-critique
dzhng
Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.827score
compare-screenshots
dzhng
Compare screenshots against the intended design, distinguishing approved references from historical baselines.
SkillAFreshness: A★ 1.4KClaude 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 audit-choices 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
audit-choices skill. Agent Mart. https://agentmart.dev/skills/dzhng-audit-choices (last updated 2026-10-24)