workflow-coach

Produce ranked, evidence-backed, opt-in automation suggestions from Rune event JSONL, including repeated actions, bounded sequences, and recovery patterns…

Skill by mizuharaa

IndexedMIT

Write a review

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-coach

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

Produce ranked, evidence-backed, opt-in automation suggestions from Rune event JSONL, including repeated actions, bounded sequences, and recovery patterns, without executing them. Use for /workflow-coach or a forward-looking automation opportunity scan; use workflow-audit only for its legacy summary.

Use cases: security, productivity

Reviews

Write a review

No 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
Runs as: Python package

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/workflow-coach

What's inside

Skill name: workflow-coach
Description: Produce ranked, evidence-backed, opt-in automation suggestions from Rune event JSONL, including repeated actions, bounded sequences, and recovery patterns, without executing them. Use for /workflow-coach or a forward-looking automation opportunity scan; use workflow-audit only for its legacy summary.
License: MIT
Instructions: 12 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts

Files (3)

SKILL.md
openai.yaml · agents/
analyze.py · scripts/

SKILL.md (first lines)

# Workflow Coach

1. Run `python skills/workflow-coach/scripts/analyze.py` from the repository root to inspect the default event wire, or pass another readable JSONL path for an isolated fixture.
2. Add `--json` when a caller needs stable structured suggestions and supporting evidence.
3. Review only candidates observed at least three times. The CLI rejects lower thresholds, redacts credential-shaped evidence, and reports malformed input counts. Ignore directory navigation and listing noise.
4. Check the normalized family, affected sessions, and sample evidence before recommending a script, hook, skill, or deliberate manual checkpoint.
5. Treat failure/recovery correlations as leads, not proof; confirm the cause before changing retry behavior.
6. Present the smallest reversible improvement and ask before implementing it.

Never execute, schedule, or install a suggestion automatically.

From mizuharaa/wisp_os, MIT.

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: GitHub github-graphql