agentleFS
scolladonscolladon/craft/skills/workspace/SKILL.md

workspace

Skill2 starsChanged 34 days agoMITView on GitHub

Craft phase 1 - create the feature branch and worktree, install dependencies in-worktree, establish repo tooling preconditions.

20 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

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write/Edit in the shared checkout until the session isolates (worktree.bgIsolation), so an in-place run could not edit.

    line 39
  2. Very specific:

    All subsequent work happens ONLY in this worktree/branch, reached by its absolute path: Bash as cd <abs-worktree-path> && …, file tools at …

    line 49

“Common” is measured: kept by at least 6 in 10 of the 18 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

craft:workspace

Preamble (always runs — non-overridable)

  1. "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/manifest-lint.sh" must pass; read the manifest.
  2. Probe: git repo present (else STOP — craft needs one); default branch (origin/HEAD → main → master → ask once).
  3. Memory read/write surface (advisory). READS: last toolchain entry for this repo (ecosystem + lockfile fingerprint). If the fingerprint matches the current lockfile, skip re-detection for the already-known ecosystem — still re-detect on a miss or a changed fingerprint. WRITES (appended to the run record as produced; saved to the store once at Done): the detected ecosystem + lockfile fingerprint produced by scripts/worktree-setup.sh lockfile detection. The hint never gates — a miss falls through to full detection.

Procedure (default body — a manifest override: replaces everything below)

  1. Infer the branch type from the brief (feat/fix/chore, default feat).
  2. Consult isolate action (default always, ADR-127 — proceeds silently unless policy forbids it; see docs/contributing/specs/policy.md for surface semantics). Then, strategy worktree (default), as one Bash call — a compaction cannot split the two:
    git worktree add ../<repo>-<slug> -b <type>/<slug> && \
    "${CRAFT_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/worktree-setup.sh" <abs-worktree-path> [manifest scripts.post-setup]
    The run ledger stays where §0 opened it, in the git common dir: nothing moves. Strategy in-place (manifest workspace: { strategy: in-place }): create the branch in the current checkout (git switch -c <type>/<slug>); deps assumed present or installed in place; later phases use the checkout root wherever they'd use the worktree (the run-lock path resolves from it too). In a Claude Code background session (CLAUDE_JOB_DIR set) → STOP before git switch: the Bash call that would run it tests [ -n "${CLAUDE_JOB_DIR:-}" ] first. The session's edit guard refuses Write/Edit in the shared checkout until the session isolates (worktree.bgIsolation), so an in-place run could not edit. Reason: in-place strategy cannot run in a background session; use strategy worktree or run attended. The STOP holds even where a repo turned worktree.bgIsolation off: Craft does not read that setting, because it merges across the user, project, local, managed and --settings layers, so the session's effective value is not observable from the run. Nothing was switched, so nothing needs undoing.
  3. Branch or worktree path collision → STOP and ask; never reuse silently.
  4. Apply the manifest's global/workspace context: file now: perform any tooling activation it declares (the session does this — agents will receive the same file and must find the tooling already active). Its teardown counterpart runs at integrate.
  5. All subsequent work happens ONLY in this worktree/branch, reached by its absolute path: Bash as cd <abs-worktree-path> && …, file tools at <abs-worktree-path>/…, agents spawned with it as their working directory. Never move the session itself with a working-directory relocation tool (Claude Code's EnterWorktree): for a worktree outside .claude/worktrees/ it raises a permission prompt that auto mode cannot approve, which halts a background session, and a background session's edit guard already accepts edits at the worktree's absolute path.

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.