All skills
softaworks avatar

/gepetto

@1c0662a
by softaworkssoftaworks/agent-toolkit2.5k stars
230

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

Use this Skill: https://skilld.dev/gh/softaworks/agent-toolkit/gepetto

This session only. Nothing lands on disk.

referencessection-splitting.md

≈1k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Section File Writing

Write individual section files from the plan using parallel subagents for efficiency.

This step assumes sections/index.md already exists.

Input Files

  • <planning_dir>/claude-plan.md - implementation details
  • <planning_dir>/sections/index.md - section definitions and dependencies

Output

<planning_dir>/sections/
├── index.md (already exists)
├── section-01-<name>.md
├── section-02-<name>.md
└── ...

Parallel Execution Strategy

Launch one subagent per section in a single message for maximum parallelization:

┌─────────────────────────────────────────────────────┐
│  PARALLEL SUBAGENT APPROACH                         │
│                                                     │
│  1. Parse index.md to get SECTION_MANIFEST list     │
│  2. Check which sections already exist              │
│  3. Launch ALL missing sections as parallel Tasks:  │
│                                                     │
│     Task(prompt="Write section-01-...")             │
│     Task(prompt="Write section-02-...")             │
│     Task(prompt="Write section-03-...")             │
│     ... (all in ONE message)                        │
│                                                     │
│  4. Wait for all subagents to complete              │
│                                                     │
└─────────────────────────────────────────────────────┘

Parse SECTION_MANIFEST

Extract section list from index.md:

<!-- SECTION_MANIFEST
section-01-foundation
section-02-config
section-03-api
END_MANIFEST -->

Launch Parallel Tasks

For each section in the manifest, include a Task in a single message:

Task(
  subagent_type="general-purpose",
  prompt="""
  Write section file: section-01-foundation

  Inputs:
  - <planning_dir>/claude-plan.md
  - <planning_dir>/sections/index.md

  Output: <planning_dir>/sections/section-01-foundation.md

  Requirements: [see Section File Template below]
  """
)

Task(
  subagent_type="general-purpose",
  prompt="Write section file: section-02-config ..."
)

# ... one Task per section

Why parallel? Each section is independent - they all read from the same source files (claude-plan.md, index.md) but write to different output files.

Resume Handling

If some sections already exist:

  1. Only launch Tasks for MISSING sections
  2. Skip sections that have corresponding section-*.md files

Section File Requirements

CRITICAL: Each section file must be completely self-contained.

The implementer reading a section file should NOT need to reference claude-plan.md or any other document. They should be able to:

  1. Read the single section file
  2. Create a TODO list
  3. Start implementing immediately

Include all necessary background, requirements, and implementation details within each section.

Section File Template

# Section NN: {Section Name}

## Background

{Why this section exists, what problem it solves}

## Requirements

{What must be true when this section is complete}

## Dependencies

- Requires: {list of prior sections that must be complete}
- Blocks: {list of sections that depend on this one}

## Implementation Details

{Detailed implementation guidance}

### {Subsection 1}

{Details}

### {Subsection 2}

{Details}

## Acceptance Criteria

- [ ] {Criterion 1}
- [ ] {Criterion 2}
- [ ] {Criterion 3}

## Files to Create/Modify

- `path/to/file1.ts` - {description}
- `path/to/file2.ts` - {description}

Completion

All sections are complete when every section in the SECTION_MANIFEST has a corresponding section-NN-name.md file.

After all parallel Tasks complete, update the main TODO list to mark section writing as done.

Source: SKILL.md on GitHub

3 warnings16d5 checks · Risk MEDIUM
  • Gen Agent Trust Hub16d

    The skill automates implementation planning by orchestrating research and multi-LLM reviews. However, it introduces security risks by invoking external CLI tools with flags that bypass manual approval and lacks sanitization for user-provided specification files that influence autonomous agent behavior.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 1 issue

  • Runlayer7mo

    7/7 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 1c0662a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Dormantupdated 8 months ago
  • planning
  • feature-development
  • requirements
  • specification
  • multi-agent
  • workflow
  • markdown
  • implementation

README badge

README badge for softaworks/agent-toolkit/gepetto

Orchestrates a multi-step planning workflow—research, stakeholder interview, spec synthesis, implementation plan, external LLM review, and sectionized breakdown—to produce detailed pre-implementation documentation and autonomous execution files. Targets feature planning that requires thorough analysis before coding begins.

Generated from the current SKILL.md.

Does this skill require a spec file to start?
Yes. Gepetto requires a markdown spec file path (ending in .md) passed at invocation. The skill will not proceed without it.
Can I resume a plan that was started earlier?
Yes. Gepetto scans the planning directory for existing files and resumes from the appropriate step, or starts fresh if no files exist.
What external models does this skill use for review?
Gepetto launches Gemini and Codex as parallel subagents in step 10 to review the implementation plan independently.
Does this skill write files to disk?
Yes. Gepetto writes markdown files to the planning directory inferred from your spec file's parent directory, including research, interviews, specs, plans, reviews, and section files.
Can I use the generated plan with other tools?
Yes. Gepetto outputs two execution files: claude-ralph-loop-prompt.md for the ralph-loop plugin and claude-ralphy-prd.md for the Ralphy CLI, both designed for autonomous implementation.

Generated from the current SKILL.md. These answers refresh after source changes.