agentleFS
d-o-hubd-o-hub/github-template-ai-agents/.agents/skills/implementer/SKILL.md

implementer

Skill2 starsChanged 9 days agoMITView on GitHub

Execution agent skill focused on implementing changes based on an approved Blueprint. Use this skill when implementing targeted, atomic code changes once the plan is solid — even if they just say "implement this" or "make the changes". Gated by human or primary agent approval of the implementation strategy.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 7

    Distinctive

    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:

    Before making any changes, verify the Blueprint (ADR) exists and includes:

    line 26
  2. Distinctive:

    If the Blueprint is missing or incomplete, stop and request it before proceeding.

    line 33
  3. Distinctive:

    Blueprint Check: Verify that a clear implementation strategy (ADR) with TRIZ analysis exists.

    line 37
  4. Distinctive:

    Verification: Run tests and the quality gate after each atomic change.

    line 39
  5. Distinctive:

    Never bundle unrelated changes in a single commit — if the quality gate fails, you can't tell which change caused it.

    line 54
  6. Distinctive:

    If the Blueprint says "modify files X, Y, Z" but you find a better approach mid-implementation, update the Blueprint first rather than …

    line 55
  7. Distinctive:

    Run the quality gate locally before pushing — CI failures are expensive to diagnose remotely.

    line 56

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

Implementer Skill

The Implementer skill is an execution-focused tier responsible for making atomic, high-quality code changes.

When to Use

  • Implementing features based on a solid technical specification
  • Applying identified bug fixes
  • Executing planned refactoring tasks
  • Ensuring all changes pass quality gates and tests
  • Even if they just say "implement this" or "make the changes"

Blueprint Validation

Before making any changes, verify the Blueprint (ADR) exists and includes:

  • Clear problem statement
  • Proposed solution with specific files to modify
  • TRIZ contradiction analysis (if applicable)
  • Success criteria and test plan
  • Rollback strategy

If the Blueprint is missing or incomplete, stop and request it before proceeding.

Workflow

  1. Blueprint Check: Verify that a clear implementation strategy (ADR) with TRIZ analysis exists.
  2. Atomic Edits: Apply changes one concern at a time. Each edit should be independently committable.
  3. Verification: Run tests and the quality gate after each atomic change.

Atomic Edit Pattern

1. Identify the single concern to change
2. Make the edit
3. Run: ./scripts/quality_gate.sh
4. If pass → commit with conventional format
5. If fail → fix, re-run quality gate, then commit
6. Move to next concern

Gotchas

  • Never bundle unrelated changes in a single commit — if the quality gate fails, you can't tell which change caused it.
  • If the Blueprint says "modify files X, Y, Z" but you find a better approach mid-implementation, update the Blueprint first rather than deviating silently.
  • Run the quality gate locally before pushing — CI failures are expensive to diagnose remotely.

Rationalizations

RationalizationReality
"I'll just fix it now"Skipping the Blueprint phase leads to scope creep and architectural regressions.
"The change is obvious, no need for a Blueprint"Obvious changes still need atomic edits and quality gate verification.

Red Flags

  • Making non-atomic changes that touch multiple unrelated areas
  • Committing code without running the required quality gate
  • Deviating from the Blueprint without updating it first
  • Skipping the Blueprint Check step because "it's a small change"

See Also

  • delegate — Context retrieval before implementation
  • goap-agent — Orchestrator that assigns implementer tasks

Voice & Context

  • Default: professional + blog
  • Reference: voice-profiles skill for definitions and auto-detection.

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.