gepetto

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

2.40x

Quality

76%

Does it follow best practices?

Impact

96%

2.40x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./dist/plugins/gepetto/skills/gepetto/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-crafted skill for a complex multi-step planning workflow. It excels at actionability with specific Task() syntax and file paths, has excellent workflow clarity with numbered steps and resume logic, and properly delegates detailed protocols to reference files. Minor verbosity in banner templates and some repeated information slightly impacts token efficiency.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some verbose elements like the full banner templates and detailed file listings that could be condensed. The step-by-step format is appropriate for the complexity but some sections repeat information (e.g., file paths mentioned multiple times).	2 / 3
Actionability	Provides highly concrete, executable guidance with specific file paths, exact Task() call syntax, table-based decision logic for resume states, and copy-paste ready banner outputs. The workflow steps are specific about what to write and where.	3 / 3
Workflow Clarity	Excellent multi-step workflow with 17 clearly numbered steps, explicit validation checkpoints (step 2 validates input, step 12 requires user confirmation, step 16 verifies file creation), and a clear resume table showing exactly where to continue based on existing files.	3 / 3
Progressive Disclosure	Well-structured with clear references to external protocol files (research-protocol.md, interview-protocol.md, external-review.md, section-index.md, section-splitting.md) that are one level deep and clearly signaled with 'See [filename]' pattern. Main file serves as orchestration overview.	3 / 3
	Total	11 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description has good structure with explicit 'what' and 'when' clauses, meeting completeness requirements. However, it lacks specificity about concrete deliverables and misses natural trigger terms users would commonly use when requesting planning help. The methodology mentions (research, interviews, multi-LLM review) are interesting but don't clearly differentiate it from other planning-related skills.

Suggestions

Add more specific concrete outputs (e.g., 'Creates implementation plans with architecture diagrams, task breakdowns, risk assessments, and timeline estimates')

Expand trigger terms to include natural variations like 'project plan', 'feature spec', 'technical design', 'architecture planning', or 'roadmap'

Dimension	Reasoning	Score
Specificity	Names the domain (implementation planning) and some actions ('research, stakeholder interviews, multi-LLM review'), but 'detailed, sectionized implementation plans' is somewhat vague about what concrete outputs or steps are involved.	2 / 3
Completeness	Clearly answers both what ('Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review') and when ('Use when planning features that need thorough pre-implementation analysis') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'implementation plans', 'planning features', and 'pre-implementation analysis', but misses common variations users might say like 'project plan', 'feature spec', 'technical design', 'architecture plan', or 'roadmap'.	2 / 3
Distinctiveness Conflict Risk	The focus on 'implementation plans' with 'multi-LLM review' and 'stakeholder interviews' provides some distinction, but could overlap with general planning, documentation, or project management skills. The 'pre-implementation analysis' trigger is somewhat specific but not highly distinctive.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: softaworks/agent-toolkit
Commit: 3027f20

Reviewed: 4 months ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.