agentleFS
sschemelsschemel/second-brain-starter/.agents/skills/freddie-implement/SKILL.md

freddie-implement

Skill0 starsChanged 15 days agoMITView on GitHub

Freddie Suite execution engine (Tier 2). Writes production code that satisfies an approved Spec and its tests, with no redesign and no silent assumptions. Use only when the user types /freddie-implement or explicitly asks to implement an approved Spec.

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:

    If the spec contradicts the codebase or itself, halt, describe the contradiction precisely, and ask for a spec update.

    line 18
  2. Distinctive:

    Read the spec, its linked plan, and the target repo's AGENTS.md/CLAUDE.md invariants.

    line 22
  3. Distinctive:

    After each meaningful step, run the targeted tests for what you changed (one file or test).

    line 24

≈ “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

Freddie-Implement: Code Generation

You are the execution engine of the Freddie Engineering Suite (pipeline and artifact rules: AGENTS.md §4). Input: $ARGUMENTS

Gate (hard rule)

Before writing any code, confirm an approved Spec_*.md exists for this work. If it doesn't, stop and route to /freddie-plan or /freddie-spec. This includes follow-ups from reviews and audits: findings go back through Plan and Spec first. The only exception is the user explicitly waiving the gate for a trivial change.

Boundaries

  • Implement exactly what the spec says. Do not re-architect, add features, or refactor unrelated code.
  • If the spec contradicts the codebase or itself, halt, describe the contradiction precisely, and ask for a spec update. Make no silent assumptions.
  • Work on a feature branch named for the change, never the default branch. Don't merge, and don't mark PRs ready without explicit approval.

Execution

  1. Read the spec, its linked plan, and the target repo's AGENTS.md/CLAUDE.md invariants.
  2. Work step by step through the spec's Implementation Steps, matching the surrounding code's style, naming, and comment density.
  3. After each meaningful step, run the targeted tests for what you changed (one file or test). Before handing off, run the spec's full verification command once and show the real output. Fix failures within the spec's scope.
  4. Circuit breaker: after about 3 failed verify cycles, stop and hand off to /freddie-troubleshoot with the failure trace instead of grinding.
  5. Finish with the verification output, a changed-files summary, and a note of any deviations from the spec (there should be none). Tick the completed items on the project dashboard. The next step is /freddie-review.

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.