agentleFS
tom555mytom555my/skills-browser/.agents/skills/do-it/SKILL.md

do-it

Skill1 starsChanged 6 months agoMITView on GitHub

Execute engineering tasks end-to-end with a standard delivery workflow: gather context, define a concrete plan, implement in small increments, validate behavior, and report outcomes. Use when requests involve building features, fixing bugs, refactoring code, integrating tools, or any 'just do it' coding task that needs reliable execution discipline.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. zahardev/aicontext★ 2same name
    2. hodgemann/do-it★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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:

    If the work is tied to a GitHub ticket or project item, use gh before implementation to move the ticket to in-progress.

    line 14
  2. Very specific:

    Prefer fast targeted discovery (rg, focused file reads, narrow command output).

    line 20
  3. Distinctive:

    Keep changes scoped to the user request.

    line 36
  4. Distinctive:

    Run a focused check immediately after each meaningful change.

    line 38
  5. Distinctive:

    Run targeted tests first, then broader checks as needed.

    line 42
  6. Distinctive:

    Verify edge cases, error paths, and user-visible behavior.

    line 43
  7. Distinctive:

    Call out risk, limitations, or follow-up work if present.

    line 55
  8. Distinctive:

    Prefer deterministic execution over speculative guidance.

    line 61
  9. Distinctive:

    Avoid unrelated refactors that increase review risk.

    line 62
  10. Distinctive:

    Keep communication concise, factual, and actionable.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Do-It Workflow

1) Align on the target outcome

  • Restate the requested outcome in concrete terms.
  • Identify explicit constraints (tech stack, style, deadlines, non-goals).
  • Infer practical done criteria before writing code.
  • Surface blockers that require a user decision before proceeding.
  • If the work is tied to a GitHub ticket or project item, use gh before implementation to move the ticket to in-progress.

2) Gather only the necessary context

  • Inspect only the files and docs needed for the task.
  • Prefer fast targeted discovery (rg, focused file reads, narrow command output).
  • Reuse existing project patterns instead of introducing novel structure.
  • Summarize key findings before making edits.

3) Plan the execution path

  • Break the work into a short ordered task list.
  • Prioritize the smallest meaningful increment first.
  • Declare assumptions that can affect behavior or architecture.
  • Revise the plan when new information invalidates assumptions.

4) Implement in tight feedback loops

For each task increment:

  • Edit the minimum set of files required.
  • Keep changes scoped to the user request.
  • Preserve existing conventions unless there is a strong reason to deviate.
  • Run a focused check immediately after each meaningful change.

5) Validate to production quality

  • Run targeted tests first, then broader checks as needed.
  • Verify edge cases, error paths, and user-visible behavior.
  • Validate in-browser for UI work and in-terminal/service context for CLI or backend work.
    • You should use the following tools if applicable:
      • agent-browser
      • playwright-cli
      • other relevant tools for the project and task at hand
  • State exactly what could not be validated and why.

6) Close with a clear handoff

  • Summarize what changed and the reason for each major change.
  • Report important commands run and relevant results.
  • Call out risk, limitations, or follow-up work if present.
  • Suggest next steps only when they add clear value.

Quality Bar

  • Finish end-to-end whenever feasible in the same turn.
  • Prefer deterministic execution over speculative guidance.
  • Avoid unrelated refactors that increase review risk.
  • Keep communication concise, factual, and actionable.

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.