Chalk Labs
Need help deploying workflow-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/mizuharaa-workflow-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: not checked yet.
What's inside
- Skill name
workflow-audit- Description
- None
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- missing YAML frontmatter
- name: missing
- description: missing
Files (2)
- SKILL.md
- audit.py
SKILL.md (first lines)
# workflow-audit
Read the event wire, find what I keep doing by hand, flag it for automation.
Choose this legacy audit for a compact event-type and repeat summary. Use
`workflow-coach` when you need ranked suggestions, bounded sequences,
failure/recovery evidence, confidence, or structured JSON.
- **Trigger:** /audit ("audit my workflow", "what am I repeating")
- **Command:** `python skills/workflow-audit/audit.py`
- **Earn:** `python skills/engine.py use workflow-audit` after each real use
## Process
1. Run the audit command — it summarizes `state/events.jsonl` by event type,
session, and repeated command verbs (≥3 repeats = automation candidate).
2. For each candidate, decide: automate (see `skills/automation`), skill-ify
(see `skills/skill-creation`), or consciously keep manual.
3. Log the decision on the wire:
`python .claude/hooks/mirror.py --event audit --detail "<decision>"`From mizuharaa/wisp_os, MIT.
More from mizuharaa/wisp_os
- 0.474score
workflow-coach
mizuharaa
Produce ranked, evidence-backed, opt-in automation suggestions from Rune event JSONL, including repeated actions, bounded sequences, and recovery patterns…
SkillCFreshness: CClaude Code +9 - 0.467score
recovery-supervisor
mizuharaa
Diagnose failed, stalled, exhausted, or permission-blocked agent tasks and recover them with preserved context, bounded retries, explicit approval gates, and…
SkillCFreshness: CClaude Code +9 - 0.251score
web-design
mizuharaa
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.251score
design-intelligence
mizuharaa
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.251score
3d-interaction
mizuharaa
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.251score
automation
mizuharaa
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.251score
loop-engineering
mizuharaa
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.247score
orchestration
mizuharaa
No description from the publisher yet.
SkillCFreshness: CClaude Code +9 - 0.247score
skill-creation
mizuharaa
No description from the publisher yet.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 16, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mizuharaa/wisp_os
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mizuharaa
- 0.474score
workflow-coach
mizuharaa
Produce ranked, evidence-backed, opt-in automation suggestions from Rune event JSONL, including repeated actions, bounded sequences, and recovery patterns…
SkillCFreshness: CClaude Code +9 - 0.467score
recovery-supervisor
mizuharaa
Diagnose failed, stalled, exhausted, or permission-blocked agent tasks and recover them with preserved context, bounded retries, explicit approval gates, and…
SkillCFreshness: CClaude 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 workflow-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
workflow-audit skill. Agent Mart. https://agentmart.dev/skills/mizuharaa-workflow-audit (last updated 2026-10-24)