agentleFS
Sign inStart free
Domek-LabsDomek-Labs/stagecrew-oss/skills/loop/SKILL.md

loop

Skill0 starsChanged 50 days agoMITView on GitHub

Loop-workflow umbrella. Routes to /init-agents (bootstrap), /create-issue (genesis), /plan-issues (backlog planning) or /work-issue (5-stage execution, merges in-loop). Triggers: "loop", "loop workflow", "work issue", "spec build", "coding loop", "github workflow", "github loop", "spec build loop". Routes when intent is unclear.

55 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-bugbot, origin and 10 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.
  • 0mlkrizzz655335vSkill

    review-bugbot

    缺陷导向代码审查。用 Bugbot 子代理找 bug。

    Also in 4 projects that use this

  • 0mlkrizzz655335vSkill

    origin

    origin CLI 管理。安装、登录、更新、修复 origin.cursor.com 的 CLI。"disabled-environments:

    Also in 3 projects that use this

  • PandelisZSkill

    update-cli-config

    View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

    Also in 4 projects that use this

  • 32103210Skill

    migrate-to-skills

    Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

    Also in 4 projects that use this

  • 32103210Skill

    update-cursor-settings

    Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

    Also in 4 projects that use this

  • MicrosoftSkill

    automate

    Propose an automation from a completed task or a new idea, then create it after approval. Use when the user asks to create an automation or wants scheduled local or cloud agent work.

    Also in 4 projects that use this

  • +3 more from 0mlkrizzz655335v
  • +1 more from 32103210

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All sub-skills are pure-readers — they read AGENTS.md at the repo root as the single source of truth for standards.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 50 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

/loop — Loop-Engineering Workflow (Umbrella)

Type: umbrella / router

Purpose

Central entry point for the stagecrew pipeline: GitHub issue → reviewed, merged PR (or research findings) via a multi-stage agent pipeline.

Four sub-skills cover the full lifecycle:

PhaseSub-skillWhatDirect trigger
Bootstrap/init-agentsCreate AGENTS.md for a repo (one-time per repo, pure-reader prerequisite)"init agents", "create agents.md", "coding spec bootstrap", "initialize repo standards"
Genesis/create-issueIdea → fully-specified GitHub issue (spec standard with Idea/AC/Files/Test-Plan/OoS)"create issue", "new issue", "create feature", "spec issue", "idea as ticket"
Planning/plan-issuesDerive the actionable work-list (<goal> minus <waiting-on>:*) from the open issues before work starts; resolve area:/bundle: labels; print the start-time collision report"plan issues", "backlog plan", "work-list", "plan before work"
Execution/work-issueIssue → reviewed, merged PR via 5 stages (Validator → Implementer → Tester → Critic → Closer); the Closer merges in-loop (squash-merge, issue close, remote-branch delete, deploy — semantics: skills/work-issue/SKILL.md, "Closer merge behavior")"work issue", "drive issue", "loop workflow", "spec build loop"

Workflow at a glance

Bootstrap          Genesis          Planning        Execution
    │                 │                │                │
    ▼                 ▼                ▼                ▼
/init-agents  →  /create-issue  →  /plan-issues  →  /work-issue
(AGENTS.md)     (GitHub issues)   (work-list)     (5 stages →
                                                   merged PR
                                                   + deploy)

All sub-skills are pure-readers — they read AGENTS.md at the repo root as the single source of truth for standards.

Typical sequence for new repos

1. /init-agents --repo <owner>/<slug>      # create AGENTS.md (once per repo)
2. /create-issue "<idea>"                  # spec the issue(s)
3. /plan-issues                            # derive the work-list (for multi-issue runs)
4. /work-issue <num>                       # drive each issue (Validator → ... → Closer merges in-loop)

Steps 2–4 are called one at a time; there is no single-command wrapper around them. Step 3 is optional for a single issue and recommended once several are in flight.

What happens when /loop is invoked directly

Clarify intent with a single question, then route:

What do you want to do?

  1) Create AGENTS.md for a new repo                    → /init-agents
  2) Capture a new idea as an issue                     → /create-issue
  3) Plan the work-list for open issues                 → /plan-issues
  4) Drive an existing issue (5-stage loop)             → /work-issue

When to use which skill

SituationSkill
New repo, no AGENTS.md yet/init-agents --repo <slug>
New idea, no issue yet (AGENTS.md exists)/create-issue "..."
New idea, AGENTS.md missing/create-issue "..." (calls /init-agents as a pre-step)
Multiple issues to run in parallel/plan-issues first, then /work-issue per work-list issue
Issue exists with a complete spec/work-issue <num>
Issue exists without a spec/create-issue --refine <num> then /work-issue
/work-issue Validator returned STOP/create-issue --refine <num>, then /work-issue retry
/work-issue returns STOP "AGENTS.md missing"/init-agents --repo <slug>, then /work-issue retry
AGENTS.md exists but has gaps/init-agents --refine --repo <slug>
Want to go from an idea to a merged PR/create-issue "...", then /work-issue <num> (with /plan-issues in between for several issues)

Example calls

# New repo, full loop
/init-agents --repo myorg/myrepo
/create-issue --repo myorg/myrepo "add JWT refresh endpoint"
/plan-issues --repo myorg/myrepo
/work-issue 42 --repo myorg/myrepo

# Drive an existing issue
/work-issue 17

# Plan and launch parallel loops for open issues
/plan-issues --repo myorg/myrepo --milestone "v2.0"
# → shows the work-list, user confirms → /work-issue runs per issue

# Unclear intent
/loop
# → asks one question, then routes to one of the four sub-skills

Why an umbrella

Four sub-skills, one umbrella. The full lifecycle of a feature:

  • /init-agents = capture standards (AGENTS.md)
  • /create-issue = capture intent (GitHub issue)
  • /plan-issues = determine the work-list (goal + waiting-on)
  • /work-issue = execute intent (issue → reviewed, merged PR)

Roadmap

See the repo issues (labelled roadmap) for the rolling roadmap. Version numbers for roadmap items are intentionally not tracked here — see AGENTS.md version_policy for the bump policy. The current version lives only in .claude-plugin/plugin.json.

See also

  • skills/init-agents/SKILL.md
  • skills/create-issue/SKILL.md
  • skills/plan-issues/SKILL.md
  • skills/work-issue/SKILL.md
  • skills/github/SKILL.md — reference skill (git/gh interaction conventions), not a pipeline phase
  • ../CLAUDE.md (plugin quickstart)

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.

Check your setup, free