mcpField
W
workflow-from-chats

workflow-from-chats

github.com/cursorAgent workflows14.5k2.2k installsUpdated today
Repository

About workflow-from-chats

A skill for deriving reusable work preferences from recent chats rather than summarizing them. It guides agents through evidence review, confidence rating, and choosing whether to create a durable workflow artifact.

Key features

  1. 01Recent-chat preference extraction
  2. 02Transcript inventory and evidence review
  3. 03Confidence ratings for preferences
  4. 04Workflow-based preference grouping
  5. 05Guidance on artifact selection

Use cases

  1. 01Identify recurring preferences from chat history
  2. 02Choose whether to create a skill or rule
  3. 03Draft reusable workflow guidance

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cursor/plugins --skill workflow-from-chats

After installing, type/workflow-from-chatsin Claude Code to confirm it loaded.

Details

From the project README

Workflow From Chats

Infer durable working preferences from recent chats. Do not summarize chats; extract reusable workflow guidance.

Scope

  • Default to the last 7 days unless the user asks for a different window.
  • 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: 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, repeated parent-chat pattern, or 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.
  • Preference profile.
  • Adopt, consider, dismissed.
  • Proposed artifacts.
  • Open questions only if they block writing.

Comments

Markdown supported