updating-noridocs
Use this when you have finished making code changes and you are ready to update the documentation based on those changes.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 4.9k
- Forks
- 590
01 前言 Front Matter
- name
- updating-noridocs
- description
- Use this when you have finished making code changes and you are ready to update the documentation based on those changes.
03 SKILL.md 正文
Updating Noridocs
Overview
Noridocs are docs.md files throughout the codebase that document each folder's purpose, architecture, and implementation. Update them after code changes using the nori-change-documenter subagent.
Core principle: Provide context → Dispatch subagent → Verify updates.
Announce at start: "I'm using the Updating Noridocs skill to update documentation."
The Process
Step 1: Gather Context
Prepare information for the subagent:
- [ ] What changed? (feature added, bug fixed, refactor, etc.)
- [ ] Why was it changed? (motivation, problem being solved)
- [ ] Which folders/files were modified?
- [ ] Any architectural changes or new patterns?
Step 2: Dispatch nori-change-documenter Subagent
Use Task tool with nori-change-documenter type:
Task(subagent_type: nori-change-documenter)
In the prompt, provide:
- Clear description of what changed and why
- File paths that were modified
- Relevant context from PR/commits
- Any architectural implications
- Any out of date documentation that you noticed that is not directly related to your change
Step 3: Verify Updates
Check that documentation was updated:
- [ ] Run
git statusto see which docs.md files changed - [ ] Review the diffs to ensure updates are accurate
- [ ] Verify updates focus on system architecture, not minutiae
Noridocs Format
Each docs.md follows this structure:
# Noridoc: [Folder Name]
Path: [Path to the folder from the repository root. Always start with @. For
example, @/src/endpoints or @/docs ]
### Overview
[2-3 bullet summary of the folder]
### How it fits into the larger codebase
[2-10 bullet description of how the folder interacts with and fits into other
parts of the codebase. Focus on system invariants, architecture, internal
depenencies, places that call into this folder, and places that this folder
calls out to]
### Core Implementation
[2-10 bullet description of entry points, data paths, key architectural
details, state management]
### Things to Know
[2-10 bullet description of tricky implementation details, system invariants,
or likely error surfaces]
Created and maintained by Nori.
Noridocs should NOT list files, maintain counts, or track line numbers. These are brittle documentation patterns that will break very quickly.
Common Mistakes
Providing vague context
- Problem: Subagent can't understand what changed
- Fix: Be specific about what/why/where
Skipping verification
- Problem: Inaccurate or missing documentation updates
- Fix: Always check git diff after subagent runs
Documenting trivial changes
- Problem: Noise in documentation, wasted effort
- Fix: Only update docs for significant architectural changes
Red Flags
Never:
- Skip providing context to the subagent
- Assume docs were updated without verifying
- Update docs manually instead of using the subagent
Always:
- Provide detailed context about what changed and why
- Verify the subagent updated appropriate docs.md files
- Focus on architectural/system-level changes
04 同仓库更多 Skills
trigger-pipelines-for-copilot-pr
Trigger ADO pipelines for a Copilot-created PR by posting /azp run comments. Use when the user asks to trigger CI pipelines for a specific PR.
review
Review changes relative to a prior state, such as a diff, pull request, branch, commit, or working-tree changes. Use for change-focused code review and regression analysis. Do not use to assess an existing file, API, design, implementation, or other artifact without a comparison; if the request is ambiguous, ask whether the user wants a change review and what prior state to compare against.
review-pr-local
The authority on pulling a pull request — Azure DevOps or GitHub — into an isolated local worktree so a human can review it in their editor, and on posting human-controlled review comments back to the PR (ADO via the ado PR-thread MCP tools or the Azure DevOps REST API, GitHub via the gh CLI). Auto-detects the platform and all identifiers from the PR URL; not tied to any specific repository. The AI assists an interactive human review and only ever posts comments the human explicitly requests. If you find yourself checking out a PR branch over the user's own working tree, or posting AI-authored review prose the human did not ask for, invoke this skill instead.
policy-check
This skill should be used when the user asks to "run policy check", "check policy", "policy-check", or needs to validate package compliance. Provides guidance on running policy checks for specific packages or the entire repository.
pipeline-test-triage
Triage test failures in an Azure DevOps pipeline run for Fluid Framework. Use when the user shares an ADO build/pipeline URL or build ID and wants failures analyzed, when they ask "why did this pipeline fail", "summarize the test failures", "is this test flaky or a real bug", "compare these runs", or wants bugs filed for genuine failures. Covers the Real Service End to End Tests pipeline as the worked example but applies to any FF test pipeline.
fluid-release
Fluid Framework client release group — minor releases, patch releases, and post-release type test updates. Covers release prep, branching, version bumps, changelogs, release notes, and type test baselines. In autonomous mode, auto-detects state from the repo, attempts to execute, and falls back to a GitHub issue on failure. Triggers on "release", "do the release", "release status", version bump, release notes, changelog, release branch, or release engineering.