agentleFS
cekrauseeecekrauseee/harness/skills/work/SKILL.md

work

Skill0 starsChanged 13 days agoMITView on GitHub

Create, reuse, or organize Harness work records for an ongoing purpose.

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 8 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

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    Also in 5 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 37 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:

    Use work list, work show ID, and work create ID --title TITLE --purpose PURPOSE with an explicit environment.

    line 12
  2. Very specific:

    Use record conventions for structure.

    line 16

“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

A work record preserves context that will be useful to continue a recognizable purpose. It can be small, iterative, or continuous. It does not require a plan, an agent tree, or a prescribed lifecycle.

Reuse a work record when the purpose and relevant decisions remain shared. Create one when continuity would otherwise be lost. Separate independent purposes or contexts that repeatedly interfere with one another; size, branches, PR count, and agent count alone do not justify splitting. A transient question may need no work record.

Use work list, work show ID, and work create ID --title TITLE --purpose PURPOSE with an explicit environment. Add plans, reviews, decisions, or handoffs only as needed through record write. Keep the current objective and useful state easy to find; link detailed records instead of repeating their contents.

Keep repository changes for continuous work in an open PR for each coherent delivery, following the Git policy. Independent delivery contexts use separate PRs; individual implementation steps need not. A merge completes a delivery, not necessarily the work. Synchronize the local target and clean its temporary resources while preserving useful ongoing context, then use a new branch and PR for the next delivery. Archive through the tool when the record no longer needs to be active; do not manufacture a completion state for continuous work.

Use record conventions for structure. The plan, review, and handoff skills cover those processes when they are actually needed.

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.