Skip to content
FunCoding

Search

Search docs, Skills and MCP

review-cockpit

AI 与智能体1.3kskills/review-cockpit/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/huytieu/cog-second-brain/review-cockpit/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

review-cockpit

Purpose

A single, living review document that doubles as the control surface for a session. Instead of scattering a meeting note here, a ticket there, two drafts in chat, everything lands in one file you can open in the Obsidian side panel (or Claude side panel) and drive: see progress at a glance, review each item in place, approve or request changes inline, and watch the doc update as the agent works. Mirrors a "co-work" cockpit (Progress / Working folder / Context).

When to use

  • Any session with ≥2 things you need to review or approve (the default for "process X then plan/draft Y, Z").
  • Meeting-processing + pod planning, multi-ticket runs, briefs with several drafts, spec + plan + drafts.
  • NOT for a single trivial deliverable (one file, no approval loop) — a plain file is fine there.

Pairs with closed-loop (verification), harvest (learnings), and the V-model checkpoints. This skill governs how the deliverable is presented and driven, not the verification pipeline.

The one rule

One doc per session. It opens with a cockpit, then one review card per item. Every artifact the session produces is linked from the Working folder table (fan-out to sub-files mid-run is fine; the cockpit is the single front door). Never hand the user "see files A, B, C" — hand them the cockpit.

Structure

Copy references/session-review-template.md. Save the working copy in the relevant project folder as YYYY-MM-DD-<slug>-review.md (or -plan.md).

Cockpit (top):

  1. Status line — one line: how many items await review + last-updated timestamp.
  2. 🧭 Progress — a checklist, one row per item, each with a status glyph; a text progress bar + "X/N done · A awaiting review · B pending". Make each item a clickable anchor to its review card — [N. Title](#n-title) using GitHub-slug rules (lowercase, spaces→-, drop punctuation/emoji). Keep item headings free of + # ← → ( ) so slugs stay clean single-hyphen and the links resolve in Obsidian + the Claude side panel.
  3. 📁 Working folder — table of every artifact produced this session with its ~/vault/... path or link (meeting note, this doc, evidence dir, external issues/PRs, posted messages).
  4. 🔌 Context — sources the work is grounded in (recordings, Slack threads, issues), tools/connectors used, related tickets.

Review items (below): one card per item:

  • Status — glyph + word (see vocabulary).
  • Action — what was done or is proposed.
  • Deliverable — link/path, or an inline draft placed directly under the card so you review it in place (messages to send, doc bodies).
  • Checklist — the item's acceptance criteria as checkboxes.
  • 🗒 Your call — the approval slot you edit (approve / your requested changes).
  • Decision log — append-only record of what happened / what you decided.

Footer: "How to drive this doc" (approve/change mechanics + status vocabulary), so the doc is self-explaining.

Status vocabulary: ⏳ pending · 🔄 in progress · 📝 needs review · ✏️ changes requested · ✅ done · ⛔ blocked

Update protocol (keep it live)

  • After every meaningful step, refresh: the Progress checklist + bar, the affected item's Status, the Working folder (add new artifacts), and the item's Decision log. Bump the updated: frontmatter + status line.
  • Prefer targeted Edits over full rewrites so your inline edits/approvals are never clobbered. Before editing, re-read the file — you may have typed approvals or change requests into 🗒 Your call or ticked boxes.
  • When you approve an item, execute it, move it to ✅, and log the outcome (with the external link — issue/PR/message URL) in the Decision log.
  • When you request changes, set the item to ✏️ changes requested, apply them, re-draft in place, then return it to 📝 needs review.

Interaction contract

The doc is the shared surface; you drive it two ways, both valid:

  • In the doc / side panel: you edit 🗒 Your call or tick checkboxes. Re-read and act.
  • In chat: "3 is ok", "approve 2 and 4", "change the tone on the requirement comms". Map to item numbers and act.

Distinguish draft items (agent proposes, waits — e.g. a Slack message you own sending) from auto items (agent may execute directly — e.g. filing a GitHub issue you explicitly asked for). Draft items stay 📝 until approved; auto items go straight to ✅ with the artifact linked. When unsure whether an item is draft or auto, leave it 📝.

Post-condition

Read-only for the doc itself, but the items it tracks often mutate external state — obey each item's own post-condition (fetch back the issue, confirm the Slack message landed, etc.) and record the verified link in the Decision log. Never mark ✅ from a mutation call alone.

Optional: rendered view

The markdown doc is primary (you edit it to approve). If you want a richer at-a-glance view, additionally render an HTML Artifact of the cockpit (Progress + Working folder + Context + item statuses) — but the markdown stays the source of truth and the editable surface.

Similar Skills

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI & agents

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI & agents

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI & agents

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI & agents

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI & agents

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI & agents