agentleFS
jimy-rjimy-r/agent-workspace-starter/.claude/skills/orient/SKILL.md

orient

Skill1 starsChanged 36 days agoMITView on GitHub

Use at the start of a new session when the user says "orient", "/orient", or asks to get up to speed on the workspace. Produces a briefing of active state, in-flight work, staleness flags, and a recommended next action.

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use retro, ui-ux-pro-max and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 3 projects that use this

  • StrayDragonSkill

    ui-ux-pro-max

    UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the fixed file set below. Do not wander: If a file listed here doesn't exist, note it and move on — don't improvise replacements.

    line 12
  2. Distinctive:

    Do NOT read project source code or docs beyond the file set above.

    line 43
  3. Distinctive:

    Do NOT fire subagents during orient — the file set is small and bounded.

    line 44
  4. Distinctive:

    Do NOT write to any file during orient — this is read-only.

    line 45
  5. Very specific:

    Do NOT include the ## Completed historical tables in what you summarize.

    line 46
  6. Distinctive:

    If a listed file is missing, note it in the briefing as a structural flag — don't skip silently.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 25 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Purpose

Bring Claude up to speed on this workspace quickly and deterministically at session start, without burning context on speculative exploration. Output is a concise briefing the user can redirect.

Iron Law

Read the fixed file set below. Do not wander. If a file listed here doesn't exist, note it and move on — don't improvise replacements.

Procedure

1. Read (in parallel)

  • CLAUDE.md — workspace working context (includes the Command shortcuts table)
  • tasks/todo.md — current implementation plan
  • tasks/lessons.md — self-improvement rules to apply this session
  • tasks/notes.md — master task list (scan active sections; skip the ## Completed table)

2. Freshness scan

Glob for */CONTEXT.md and */PLAN.md across project folders and check mtime. Flag any older than 30 days as potentially stale. Do NOT read the files — just check mtime.

3. Produce the briefing

Output under 300 words, structured as:

Active state — one line on where the workspace is right now.

In-flight work — anything with an open plan or checklist that isn't closed. Cite file paths.

Staleness flags — any CONTEXT.md / PLAN.md older than 30 days.

Lessons active this session — one-line summary per entry in lessons.md.

Recommended next action — one task with a one-sentence tradeoff. Present as "I'd pick X because Y; alternatives are Z" — something the user can redirect, not a decided plan.

Rules

  • Do NOT read project source code or docs beyond the file set above. The user can ask for depth on a specific project after orienting.
  • Do NOT fire subagents during orient — the file set is small and bounded.
  • Do NOT write to any file during orient — this is read-only.
  • Do NOT include the ## Completed historical tables in what you summarize.
  • If a listed file is missing, note it in the briefing as a structural flag — don't skip silently.
  • End with one question offering direction: "Want depth on any of these, or start on the recommended next action?"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.