跳到正文
cccskills
免费在 GitHub 公开

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.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

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

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

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.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

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.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

af-xdp

免费

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.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

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

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

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.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

agents-md

免费

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.

中文简介正在准备中。当前显示原文说明。

OutlineDriven/odin-claude-plugin372026年9月29日 更新

查看 OutlineDriven 的全部技能

报告此技能的问题