agentleFS
Sign inStart free
iyakiiyaki/specralph/.agents/skills/agent-spec-creation/SKILL.md

agent-spec-creation

Skill7 starsChanged 11 days agoMITView on GitHub

Create or update agent integration specs before implementation. Use this whenever a request is about defining how a new or existing agent should behave in Ralph.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create implementation-ready agent integration specifications without changing production code.

    line 10
  2. Distinctive:

    Use this skill when the task is to define or revise agent behavior, inputs, outputs, error handling, or acceptance criteria in specs.

    line 14
  3. Distinctive:

    Read intent and existing spec context first:

    line 18
  4. Distinctive:

    Update spec files only.

    line 33
  5. Very specific:

    Do not implement code in internal/agent/* while using this skill.

    line 37
  6. Distinctive:

    Do not run iterative Ralph loop automation.

    line 38
  7. Distinctive:

    Keep the workflow linear: read, specify, and stop after spec updates.

    line 39

≈ “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

Agent Spec Creation Workflow

Purpose

Create implementation-ready agent integration specifications without changing production code.

When to Use

Use this skill when the task is to define or revise agent behavior, inputs, outputs, error handling, or acceptance criteria in specs.

Required Workflow

  1. Read intent and existing spec context first:
    • specs/README.md
    • specs/agents.md
    • relevant files in specs/agents/*.md
  2. Rely on the spec-creator skill for document structure and quality requirements.
  3. Study the target CLI behavior before writing spec details:
    • <agent-cli> --help
    • relevant subcommand help (for example <agent-cli> run --help)
  4. Define explicit, testable requirements:
    • canonical config name and accepted aliases: document one canonical name, list aliases explicitly (for example antigravity with alias agy)
    • command shape and required flags
    • environment variables
    • output parsing/streaming expectations
    • non-interactive execution behavior
    • failure modes and expected surfaced errors
  5. Update spec files only.

Constraints

  • Do not implement code in internal/agent/* while using this skill.
  • Do not run iterative Ralph loop automation.
  • Keep the workflow linear: read, specify, and stop after spec updates.

Completion Criteria

  • Spec changes are clear, deterministic, and testable.
  • Scope and non-goals are explicit.
  • Related index files (for example specs/README.md) are updated when new spec files are added.

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.

Check your setup, free