AGENT SKILL

brain

Read/write brain files at brain/. Use when modifying any file in brain/. Use for any task that persists knowledge - reflection, planning, or direct edits. Use after debugging sessions, mistakes, corrections, architectural decisions, or any insight worth preserving across sessions. Use when the user says 'add to brain', 'remember this', or 'write a note'.

License 许可
MIT
所属仓库
japurcell/skills
最近更新
2026-11-11
Stars
★ 0
Forks
0

01 前言 Front Matter

name
brain
description
Read/write brain files at brain/. Use when modifying any file in brain/. Use for any task that persists knowledge - reflection, planning, or direct edits. Use after debugging sessions, mistakes, corrections, architectural decisions, or any insight worth preserving across sessions. Use when the user says 'add to brain', 'remember this', or 'write a note'.
compatibility
Requires Python 3.12+ only for manual indexing when hooks are unavailable.

03 SKILL.md 正文

Brain

Persistent memory across sessions at brain/.

The brain is the foundation of the entire workflow - every agent, skill, and session reads it. Low-quality or speculative content degrades everything downstream. Before adding anything, ask: "Does this genuinely improve how the system operates?" If the answer isn't a clear yes, don't write it.

Before Writing

Read brain/index.md first. Then read the relevant entrypoint for your topic:

  • brain/principles.md for principle updates
  • brain/plans/index.md for plan-related notes

For other topics, read the dedicated index when present. Otherwise scan nearby files directly and edit an existing note when possible.

Structure

brain/
├── index.md              ← root entry point, links to everything
├── principles.md         ← index for principles/
├── todos.md              ← product backlog
├── vision.md             ← elevator pitch + link to architecture
├── architecture.md       ← full technical reference
├── principles/           ← engineering and design principles
├── codebase/             ← project-specific knowledge and gotchas
├── plans/                ← numbered feature plans (02-arrow-bindings/, etc.)
└── audits/               ← design and quality audits (date-prefixed filenames, e.g. 2026-02-20-quality-audit.md)

Rules:

  • One topic per file. brain/codebase/noodle-spawn-gotchas.md, not a mega-file.
  • Maintain existing index entrypoints: brain/index.md, brain/principles.md, brain/plans/index.md.
  • If you introduce a new top-level category, add an index-style entrypoint for it (links only, no inlined content).
  • brain/index.md is the root. Every brain file must be reachable from it.
  • File names: lowercase, hyphenated. worktree-gotchas.md.
  • Plan directories: prefixed with the todo ID from brain/todos.md. 02-arrow-bindings/ with overview.md and phase-N-*.md inside.

Links

Use standard Markdown links with destinations relative to the file containing the link, including the file extension: [Topic](relative/topic.md). Use ../ for parent directories, preserve heading fragments such as #section-heading, and percent-encode spaces or special destination characters. Keep explicit link labels when converting existing references. Do not use Obsidian note-link syntax.

Writing Style

  • Bullets over prose. No preamble.
  • Plain markdown with # Title. No Obsidian frontmatter.
  • Keep notes under ~50 lines. Split if longer.

After Writing

Let the brain hooks reconcile the machine-owned brain/index.md after additions or removals. If hooks are unavailable, run a standalone brain indexer as described in brain/codebase/brain-hooks.md. Keep human prose in topic notes. Also update the relevant entrypoint (brain/principles.md, brain/delegation.md, or brain/plans/index.md) when applicable. Keep indexes link-only and scannable.

Durability Test

Ask: "Would I include this in a prompt for a different task?"

  • Yes → write to brain/. It's durable knowledge.
  • No, it's plan-specific → update the plan's phase doc instead.
  • No, it's a skill issue → update the skill file directly.
  • No, it needs follow-up work → file a todo with the todo skill.

Maintenance

  • Delete outdated or subsumed notes.
  • Delete random-named files in brain/plans/ - stale plan-mode artifacts.
  • Merge overlapping notes before adding new ones.

04 同仓库更多 Skills

japurcell
japurcell/skills

spec-create

Create or revise a portable behavioral SPEC for a feature or whole product. Use when specifying a new idea, documenting an existing system for reimplementation, or defining a change while preserving compatibility. Implementation planning is a separate task.

产品经理
★ 0
japurcell
japurcell/skills

prd-ralph

Complete at most one eligible unfinished PRD task, verify it, log progress, and optionally create one scoped commit.

产品经理
★ 0
japurcell
japurcell/skills

fsdp-style-guide

Mandatory for all UI/UX design, implementation, review, audit, or visual regression tasks. Always use for any work that affects user-facing appearance, behavior, accessibility, branding, layout, navigation, forms, dialogs, alerts, tables, or visual design.

设计师
★ 0
japurcell
japurcell/skills

agency-priorities

Provide self-contained USDA strategic goals and Forest Service priorities for agency briefings, proposals, and work-plan alignment. Use when explaining agency direction or evaluating how a project contributes to USDA and Forest Service priorities.

★ 0
japurcell
japurcell/skills

accomplishment-report

Create a concise Forest Service executive accomplishment report when all work in an ExecPlan is completed, or update its existing report. Use at ExecPlan closeout and when asked to report completed work, agency alignment, and estimated AI-assisted versus human-only time and cost savings.

行政与办公人员
★ 0
japurcell
japurcell/skills

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

内容创作者写作与文案
★ 0