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

freddie-spec

Skill0 starsChanged 16 days agoMITView on GitHub

Freddie Suite spec writer (Tier 1). Turns an approved architecture plan into a deterministic technical spec with exact file-by-file changes, interfaces, pseudocode, and acceptance criteria, saved as Spec_<Topic>.md in the project's Specs/ folder. Use when the user types /freddie-spec, or when an approved Plan needs to become implementable work.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Read the plan, then read the actual target files in the repo.

    line 18

≈ “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-Spec: Technical Blueprinting

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

Boundaries

  • Gate: requires a Plan_*.md the user has approved. For a small, clear change the user may waive the plan explicitly. Otherwise, stop and route to /freddie-plan.
  • Output: a blueprint deterministic enough that freddie-implement needs no design decisions.
  • Not your job: production code. Signatures, types, and short pseudocode are fine.

Execution

  1. Read the plan, then read the actual target files in the repo. Specs must reference real paths, symbols, and conventions, not guessed ones.
  2. Break the plan into ordered, independently verifiable steps. Each step names:
    • the file (path), then create, modify, or delete
    • the exact functions, types, or contracts added or changed, with signatures
    • edge cases and error behavior
  3. Define acceptance criteria as testable statements (input → expected output). freddie-test will turn these into tests.
  4. Name the verification command (test, lint, and build commands as they actually exist in the repo).
  5. Write 10 - Projects/<P>/Specs/Spec_<Topic>.md:
    # Technical Specification: <Topic>
    **Status**: Draft · **Plan**: [[Plan_<Topic>]] · **Date**: YYYY-MM-DD
    ## Overview
    ## Implementation Steps
    ### 1. <Component> (`path/to/file`)
    ## Acceptance Criteria
    - [ ] AC1: …
    ## Verification
    ## Out of Scope
  6. Link it on the dashboard and stop for approval. The next step is /freddie-test (TDD) or /freddie-implement.

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.