# Workflow From Chats

> Explicit-only workflow mining across Codex, Pi, and Claude Code chats. Use only when the user invokes $workflow-from-chats or explicitly asks to learn durable preferences from those harnesses and turn them into skills, rules, or workflow docs.

- Skill: `aliceisjustplaying/workflow-from-chats` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add aliceisjustplaying/workflow-from-chats`
- Raw SKILL.md: https://api.skillmd.com/api/skills/aliceisjustplaying/workflow-from-chats/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: aliceisjustplaying (https://skillmd.com/u/aliceisjustplaying)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/aliceisjustplaying/workflow-from-chats

---


# Workflow From Chats

Infer durable working preferences from Codex, Pi, and Claude Code chats. Do not summarize chats; extract reusable workflow guidance.

## Scope

- Default to the last 7 days unless the user asks for a different window.
- Search all three harnesses unless the user limits the scope. Use their native task/session metadata and transcript stores; discover locations at runtime because versions and user configuration can move them.
- Treat Codex tasks, Pi sessions and missions, and Claude Code transcripts as one evidence corpus while preserving the originating harness on every internal evidence record.
- Read parent transcripts and relevant subagent transcripts. Use subagent content as evidence, but cite only parent conversations.
- Do not expose local transcript paths, secrets, customer data, private chat content, or credentials.

## Workflow

1. State the target workflow or preference surface in one paragraph.
2. Build an internal transcript inventory across Codex, Pi, and Claude Code: harness, title/topic, parent conversation ID, approximate date, completion state, relevant subagents, and why it may contain preference evidence.
3. Scan for explicit preferences, corrections, and workflow markers such as "I prefer", "always", "never", "not what I asked", "stop", "review", "PR", "CI", "logs", and "skill".
4. Extract preference atoms: trigger, workflow step, decision rule, quality bar, stop condition, evidence, and confidence.
5. Rate confidence as strong, medium, weak, or contradicted.
6. Cluster by workflow shape rather than transcript: shipping, review, simplification, debugging, capture, communication, delegation, or validation.
7. Choose the artifact: new skill, skill edit, rule, workflow doc, or no artifact.
8. Draft only the reusable guidance. Filter anecdotes that will not help future tasks.

## Confidence

- Strong: explicit user preference, workflow-changing correction, a repeated pattern within one harness or across harnesses, or a direct request to encode behavior.
- Medium: accepted workflow, repeated tool/model/validation preference, or subagent consensus that the parent used successfully.
- Weak: agent-chosen behavior with no user feedback, one ambiguous transcript, or a likely task-specific correction.
- Contradicted: evidence points in incompatible directions; ask the user before writing files.

## Artifact Choice

- Skill: recurring multi-step workflow with clear triggers.
- Rule: general behavior that should apply broadly.
- Workflow doc: useful context that is not reliably triggerable.
- No artifact: situational, stale, or low-confidence observation.

## Output

Return a concise synthesis first:

- Target workflow.
- Evidence corpus with parent conversation citations only.
- Harness coverage and any unavailable source.
- Preference profile.
- Adopt, consider, dismissed.
- Proposed artifacts.
- Open questions only if they block writing.