agentleFS
DankosikDankosik/golang-backend-skills/skills/go-implement/SKILL.md

go-implement

Skill0 starsChanged 2 months agoMITView on GitHub

Implement clear Go backend requirements or an agreed design through working code and relevant checks.

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:

    Execution: When the intended behavior is clear, implement it directly.

    line 8
  2. Distinctive:

    Read the affected code and callers, then extend the existing path.

    line 10
  3. Distinctive:

    If a concrete contradiction prevents correct implementation, identify it and continue independent work.

    line 16

≈ “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

Go Implement

Execution. When the intended behavior is clear, implement it directly. Honor the requirements; preserve settled choices outside the requested change. An explicitly requested technical change is not an invitation to redesign unrelated parts.

Read the affected code and callers, then extend the existing path. Resolve local details using the project's Go version, package conventions, and selected infrastructure.

Reuse. Before adding a technical helper, look for a matching operation in nearby project code, the supported standard library, or declared dependencies. Keep the search proportional to the helper. Packages such as strings, slices, and maps cover many routine operations. Custom mechanics need a concrete semantic or operational gap; wrappers should add domain meaning or adaptation.

Clarity. Write intention-revealing names, cohesive responsibilities, explicit control flow, and visible effects and failure paths. Keep changes local and idiomatic. Apply SOLID, DRY, and YAGNI as heuristics: abstract shared knowledge, preserve distinct business rules, and add only structure justified by current requirements. New dependencies, configuration, and adjacent cleanup need a present requirement.

If a concrete contradiction prevents correct implementation, identify it and continue independent work. Ask only for information that materially changes the required outcome; routine implementation choices remain yours.

Work in small behavior-complete increments where they reduce feedback delay; do not build every layer before checking a usable path. Derive acceptance checks from the requirement, not from what the first implementation happens to do.

Format changed Go code. Use the project's build and focused tests for the affected behavior, including a meaningful failure case. Add race, transport, database, fuzz, or performance checks only for a concrete claim or required project gate. Reuse applicable results for the same revision and environment; loading another skill is not a reason to rerun them.

Within the environment's permissions, fix failures introduced by the change and rerun affected checks without stopping for review after the first patch. Finish when the requested outcome and required checks are satisfied, or state the concrete blocker and unavailable verification. Do not invent infrastructure, unrelated cleanup, or speculative checks as new completion gates.

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.