agentleFS
fainirfainir/agent-harness/skills/workspace/SKILL.md

workspace

Skill0 starsChanged 14 days agoMITView on GitHub

Give every project a workspace the owner can see in one place, like Notion or Monday but built from the project's own files - an overview with numbers and the one owner action, a task board by status, goals, strategy, bets and decisions, a knowledge reader for every doc, what the project learned, every file and the recent activity, plus live sections the project adds - and one all-projects page that links them. Use at the end of every ship, run-company or portfolio run, when a project starts, and whenever the owner asks "show me the project", "where can I see everything", "all my projects", "dashboard", "workspace", "תראה לי את הפרויקט".

  • Reads credentials

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use schedule, improve and 9 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.
  • bivexSkill

    schedule

    Управление расписанием занятий с специалистами по самосовершенствованию. Используй когда пользователь спрашивает о расписании, хочет добавить/удалить/перенести занятие, посмотреть план на день или неделю.

    Also in 3 projects that use this

  • AnasX7Skill

    improve

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

    Also in 3 projects that use this

  • GoogleSkill

    dashboard

    Configures and launches the GKE Capacity & Triage Dashboard scoped to a GCP project ID, GKE cluster name, or target ML workload ID. Uses the configure-and-launch-dashboard action and launch-workload-dashboard workflow to verify local dashboard health, discover cluster capacity, trigger live scans, and generate deep-linked URLs. Use when the user types "/dashboard", says "launch dashboard", "open dashboard", "show capacity", or "view triage dashboard" with a project, cluster, or workload. Don't use for general workload log querying or automated failure attribution (use the troubleshoot skill).

    Also in 3 projects that use this

  • renatorozasSkill

    grill

    Adversarial code review. Don't let me ship until the changes pass your scrutiny.

    Also in 3 projects that use this

  • GitHubSkill

    prd

    Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

    Also in 3 projects that use this

  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 3 projects that use this

The file

Files
SKILL.md

Project workspace

The project's files are its workspace; this skill only renders them. Nothing is kept anywhere else, so Claude Code, Codex and the owner always see the same thing.

The files (what each project keeps and updates)

PartFileUpdated
Goal and strategyGOAL.md; Goal, Stage, Thesis lines, bets and Decisions in the ledgerwhen the goal or a bet changes
Tasksrows with ID and Status in COMPANY.md, READINESS.md or PORTFOLIO.md (any folder level), and the checkbox tasks of .claude/plan.mdevery run
Numbersthe ledger's KPI table; live numbers from scripts/workspace-extra.pyevery run
Knowledgeroot docs (PRODUCT.md, OWNER.md), .claude/plan.md and handoff, research/, docs/, knowledge/, sub-project README, AGENTS.md, READINESS.mdwhen learned or decided
LearningAGENTS.md ## Working here (project-note.sh) and the shared learnings for this projectas lessons happen
Moneymoney/ notes and the ledger's Money sectionmonthly close
Files and activitygit: every tracked file (the folder's files outside git), the last 40 commits, the ledger's Logevery commit

A new project gets these from ship phase 0 or init-company.sh; add a missing part as a file, never as a separate tool.

Build and publish the view

  1. python3 -I ~/.agents/skills/workspace/scripts/workspace.py <project> [...] writes .workspace/index.html (open it locally), artifact.html and data.json, keeps .workspace/ out of git through the clone's own exclude list (no tracked file changes), and records the project in ~/.agents/workspaces/registry.json. Values from the project's .env files and anything shaped like a key, token or private key are redacted before anything is written; publish only a page whose line ends "secret check clean". Views: Overview, Tasks (board or table, filter by ledger, search), Strategy, Knowledge, Learning, Files, Activity, and one tab per live section.
  2. Claude Code: publish .workspace/artifact.html with the Artifact tool (icon dashboard; private to the owner), then record the URL: workspace.py --url <project> <url> (a Workspace: <url> line in the ledger is read too). A republish is read first without rereading the whole page: save the published page (Artifact read with path: index.html), run workspace.py --diff <saved page> .workspace/artifact.html, read every line it prints and publish only what you can stand behind. A later session reads that url once (Artifact action read) and publishes with it. Codex and headless runs open .workspace/index.html.
  3. All projects: workspace.py --hub writes ~/.agents/workspaces/hub/artifact.html, one card per registered project (goal, progress, what needs the owner, last commit) linking to its page, with the owner's open asks from every project at the top. Publish it the same way and record it with workspace.py --hub --url <url>; pages built after that link back to it.
  4. Refresh at the end of every run, after the ledger update and before the report; the report links the workspace. In bulk (a monitor, the portfolio run): workspace.py --stale lists the registered projects whose ledger, plan or commits changed since their last build (projects with live sections every time); rebuild and republish those, then the hub.

Custom views per project

A project adds live sections with an executable scripts/workspace-extra.py <repo> that prints {"sections": [{"id", "title", "kind", ...}]}; kinds: kpis (items: label, value, note), bars (bars: label, value), table (columns, rows), markdown (md). Read secrets from .env.local and never print them.

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.