agentleFS
ahonnahonn/dotfiles/.claude/skills/slow-is-fast/SKILL.md

slow-is-fast

Skill62 starsChanged 2 months agoMITView on GitHub

Plan changes with unresolved behavior, cross-module tradeoffs, or costly implementation decisions.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Check installed versions and official documentation when external behavior is uncertain or version-dependent.

    line 15
  2. Distinctive:

    Keep bug fixes scoped to the failure.

    line 26
  3. Distinctive:

    Follow the selected test mode.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Slow is Fast

Reduce the uncertainty that could change the implementation before committing to an approach. Use Research → Plan → Code at a depth proportional to the task; do not turn each phase into a mandatory deliverable or approval gate.

Research

  • Inspect the relevant implementation, callers, and existing checks. Reuse findings already established in the conversation.
  • Identify which unknowns affect correctness, compatibility, or scope. A local edit with an established pattern may need only nearby code; a cross-module change may need contract and lifecycle analysis.
  • Check installed versions and official documentation when external behavior is uncertain or version-dependent. Choose available tools; no specific search provider or agent type is required.
  • Delegate only a bounded question that can run independently alongside useful local work.

For a difficult reuse or dependency decision, consult research-patterns.md. It is not required reading for ordinary edits.

Plan

State the intended outcome, the constraints that affect the solution, and how completion will be assessed. Include the test mode from global AGENTS.md when verification requires an explanation.

Choose the simplest approach that meets the requirements and correctness constraints. Compare alternatives only when they differ meaningfully in behavior, maintenance cost, or reversibility. Do not invent extra options to fill a quota.

Keep bug fixes scoped to the failure. For features, finish the requested behavior and its necessary error paths without adding speculative capabilities. Identify consequential decisions before implementing them; ask only for unresolved decisions that materially change scope or risk.

Resolve unknowns that block a sound implementation. Describe bounded assumptions or verification limits for the rest. A numerical confidence score is not evidence and is not an exit requirement.

Implement and Finish

  • Continue directly when the approach is clear and authorized. Do not wait for approval merely because planning is complete.
  • Make reviewable changes, inspect intermediate results, and revise the approach if new evidence contradicts it.
  • Follow the selected test mode. Fix failures caused by the change and rerun affected checks; broaden validation when new evidence or repository requirements justify it.
  • Finish the requested delivery scope. Report the resulting behavior, observed validation, and concrete remaining limits.

Correctness and the user's requirements constrain the solution. Within those constraints, prefer readability and maintainability over speculative performance gains or shorter code.

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.