Skip to content
cccskills
FreePublished on GitHub

workflow-from-chats

Use when a user asks to mine recent chats for workflow preferences. Don't use for tasks that require source or remote-system changes.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md2.6 KB
  • agents/openai.yaml140 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Workflow from chats

Contract

FieldBound contract
TriggerMine recent chats for workflow preferences.
AuthorityRead-only. No file, VCS, credential, paid, published, deployed, or remote mutation.
Side effectChat-output: proposes workflow artifacts only; writes nothing.
DoneReport-returned: evidence-backed preference synthesis and proposed artifacts.

Inputs

  • Required: chat history or a path from which chat history can be read.
  • Optional: time window, topic filter, or named agent/session identifier to narrow the scope.

Procedure

  1. Confirm the chat history source and time window. Done when: source and window are confirmed, or the step has stopped on no readable chat source.
  2. Enumerate chat sessions within the window, bounded by the supplied filter. Done when: sessions are enumerated within the filtered window.
  3. Extract recurring intent patterns, explicit preference statements, tool-use frequencies, and rejected suggestions from each session. Done when: signals are extracted from each session.
  4. Classify extracted signals into workflow categories: automation, prompting, tooling, routing, and escalation. Done when: every signal is classified into a workflow category.
  5. Synthesize a preference profile from the classified signals. Flag low-confidence signals; exclude uncorroborated single-instance claims. Done when: preference profile is synthesized with confidence ratings.
  6. Propose named workflow artifacts that satisfy high-confidence preferences. Each proposal names the trigger, inputs, steps, and done criterion. Done when: proposals are generated for high-confidence preferences, or the step returns the profile without proposals.
  7. Return the preference profile and proposed artifacts as a structured report. Done when: report is returned.

Failure and recovery

  • No chat source: report failure with a specific error. Do not proceed.
  • No extractable signals: return a report stating zero preferences found. Do not fabricate patterns.
  • Partial synthesis: return the partial result with explicit gaps listed. Do not fill gaps.
  • Proposal failure: return the preference profile without proposed artifacts. Do not invent artifacts.

Output

A structured report with sections in order: extracted preference signals with source citations, synthesized preference profile with confidence ratings, and proposed workflow artifacts with trigger, inputs, steps, and done criterion.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for the DMA stream itself: use dma-baremetal.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

af-xdp

Free

Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy versus zero-copy mode. Not for full kernel bypass: use dpdk.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

Use when a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body, with human approval and preview. Not for automated or model-initiated insertion.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential, publish, deploy, or irreversible changes.

The English summary is being prepared. Showing the original description.

OutlineDriven/odin-claude-plugin37Updated Sep 29, 2026

See all skills by OutlineDriven

Report a problem with this skill