agentleFS
Sign inStart free
Beskars-CodeBeskars-Code/Skills/skills/task/SKILL.md

task

Skill0 starsChanged 5 days agoMITView on GitHub

Default build skill. Use when the user asks to build, implement, add, or fix a feature or a bug, refactor, upgrade, speed something up, or resume a build. Writes no tests; /verification proposes the checks worth coding as tests.

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use inbox, setup and 3 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.
  • kv0906Skill

    inbox

    Quick capture mode (with content) or batch processing mode (no content). GTD-style routing of inbox items to proper folders. Use "/inbox thought to capture" or "/inbox" to process.

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 4 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

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 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 23 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. Distinctive:

    Run the lifecycle in this order:

    line 26
  2. Very specific:

    Write no tests. /verification proposes the checks worth coding as tests and writes only the ones the user names.

    line 32
  3. Distinctive:

    After all gates pass, follow shipping.md when the user already authorized shipping, including an explicit request for stacked PRs.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 23 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

Task

Orchestrate one verifiable outcome end to end. Plans stay inline in chat unless the user requests a saved artifact and approves its destination.

Read when

  • Starting web services or debugging a browser preview? Open development-server logs before launch; reuse running services.
  • About to search the codebase, read a large file, or wade through long output? Open main-context.md.
  • About to grill? Open doctrine.md and the execution context.
  • About to grill or plan a Feature? Open strong-foundation.md. Skip it and the first provider is hardcoded into every caller, so the next ticket is a rewrite.
  • At a step that names a section? Open reference.md (lifecycle, plan contract, ship offer).
  • About to ask the user anything? Open Asking the user.
  • About to report progress or completion? Open Plain language.
  • About to commit, push, or open a PR from this chat? Open shipping.md. Skip it and you push to main, open a PR nobody approved, or track origin/main.

Process

  1. Apply the shared ready-ticket preflight, then establish or refresh the in-chat execution context. If a parent already supplied ticket, lane, Done when, non-goals, rules that must stay true, fixed point, and slice bounds, accept that brief. The parent keeps ticket and branch ownership. For a request to implement a parent ticket's children, use the whole-stack handoff.
  2. Run the lifecycle in this order:
    1. Reuse the ready ticket lock; grill only unresolved consequential choices.
    2. Plan.
    3. Implement. Apply code-quality.md and code-structure.md before every slice, and user-experience.md before every user-facing slice.
    4. Gate: apply verification scope and review the changed diff. Localized low-risk work can use focused checks and review in this context. Substantial/high-risk work uses independent /verification and /review agents together when available; judge their handoffs here. Honor explicitly requested independent/full workflows.
    5. Fix mode, as needed.
  3. Write no tests. /verification proposes the checks worth coding as tests and writes only the ones the user names.
  4. Announce completion.

Shared handoffs, remediation and recovery govern this loop. Progress, lookup, and route-specific steps live in the doctrine and reference.

If a parent already owns the ticket, branch, and PR

Return a completion summary plus evidence envelope to the parent. The parent handles shipping under the user's existing authorization.

If this chat owns shipping

After all gates pass, follow shipping.md when the user already authorized shipping, including an explicit request for stacked PRs. Otherwise end with the ship offer and wait for the user's reply.

Anti-patterns

  • Offering to ship, pushing, or opening a PR when a parent owns shipping
  • Writing a test in a build slice

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