agentleFS
abigaylehabigayleh/claude-workflow-plugin/skills/work/SKILL.md

work

Skill0 starsChanged 46 days agoMITView on GitHub

Run the full idea-to-shipped-code pipeline for a new feature or fix — grill requirements, brainstorm/design, write tests first, implement, iterate until green, then a thermo-nuclear code quality review. Use when the user wants to "just build" something end-to-end rather than run each step by hand, or explicitly invokes /work.

42 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use authoring, done 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.
  • automagik-devSkill

    authoring

    Write or revise a Genie skill so it survives the shipped contract — frontmatter, house size, starter card, and runtime-neutral voice.

    Also in 3 projects that use this

  • robzolkosSkill

    done

    Reset the working directory for the next task by ensuring no uncommitted changes exist, then switching to the main branch and pulling latest.

    Also in 3 projects that use this

  • Google CloudSkill

    fix

    Plan a remediation strategy after a test failure.

    Also in 4 projects that use this

  • AlexPEClubSkill

    refine

    Always use when the user wants to discuss an exsiting feature or specification. Open an existing feature spec to improve, extend, or fundamentally challenge it. Pass the feature ID as argument (e.g. /refine PROJ-2).

    Also in 3 projects that use this

  • MicrosoftSkill

    merge

    Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    test

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 37 edited versions we read keep these.

  • 2

    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. Very specific:

    If brainstorming escalates to architectural and calls for the writing-plans skill, that skill isn't installed here.

    line 14
  2. Distinctive:

    Run the steps in order. Don't reorder or skip one because the request "looks simple" — that call belongs to the grill/brainstorm steps …

    line 22
  3. Distinctive:

    If any step's own gate isn't met (e.g.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 37 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

Work

Chains five existing skills into one fixed pipeline. Each step's own hard gates (approvals, STOP conditions) still apply in full — this skill sequences them, it does not skip or soften them.

Pipeline

  1. Grill — Skill(mattpocock-skills:grilling). Interview the user until the design tree is settled: what's being built, for whom, the constraints. Do this first, even if the request already looks simple.
  2. Brainstorm — Skill(brainstorming). Hand it what the grill settled. Let it classify the work itself (spike / bounded / architectural) and run its own approval gate — the grill answering "what" doesn't satisfy brainstorming's separate "present design, get approval" step; that still has to happen.
    • If brainstorming escalates to architectural and calls for the writing-plans skill, that skill isn't installed here. Stop and tell the user rather than inventing a plan-document format or skipping the step.
  3. Tests first — Skill(mattpocock-skills:tdd). Only once the design is approved: write the failing tests for it before any implementation code (the red half of the TDD loop).
  4. Implement — Skill(mattpocock-skills:implement), against the approved design and the tests just written. It will itself lean on TDD at pre-agreed seams — expected, not a deviation.
  5. Iterate to green — keep implementing/fixing and rerunning the suite until every test this pipeline wrote passes, plus a typecheck if the project has one. Don't advance to step 6 on a red suite.
  6. Review — with tests green, run Skill(thermo-nuclear-code-quality-review). This replaces implement's own suggested /code-review step — this pipeline's review is the strict one.

Notes

  • Run the steps in order. Don't reorder or skip one because the request "looks simple" — that call belongs to the grill/brainstorm steps themselves, not to this wrapper.
  • If any step's own gate isn't met (e.g. brainstorming's bounded/architectural approval), stop there and wait. This skill grants no blanket authorization to bypass a downstream skill's gate.
  • Branching/committing follows whatever this repo's own git conventions are (see the git-workflow skill where installed) — work doesn't add its own branch or commit handling on top.

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.