tessl install https://github.com/softaworks/agent-toolkit --skill gepettogithub.com/softaworks/agent-toolkit
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
Average Score
81%
Content
85%
Description
67%
Generated
Validations
Total score
14/16| Criteria | Score |
|---|---|
skill_md_line_count SKILL.md line count is 346 (<= 500) | |
frontmatter_valid YAML frontmatter is valid | |
name_field 'name' field is valid: 'gepetto' | |
description_field 'description' field is valid (189 chars) | |
description_voice 'description' uses third person voice | |
description_trigger_hint Description includes an explicit trigger hint | |
compatibility_field 'compatibility' field not present (optional) | |
allowed_tools_field 'allowed-tools' field not present (optional) | |
metadata_version 'metadata' field is not a dictionary | |
metadata_field 'metadata' field not present (optional) | |
license_field 'license' field is missing | |
frontmatter_unknown_keys No unknown frontmatter keys found | |
body_present SKILL.md body is present | |
body_examples Examples detected (code fence or 'Example' wording) | |
body_output_format Output/return/format terms detected | |
body_steps Step-by-step structure detected (ordered list) |
Content
Total score
11/12| Dimension | 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 explanatory text could be tightened. | 2/3 |
actionability Provides highly concrete, executable guidance with specific file paths, exact tool calls (Task with subagent_type), precise file naming conventions, and copy-paste ready banner templates. The workflow is fully specified with clear inputs and outputs for each step. | 3/3 |
workflow_clarity Excellent multi-step workflow with 17 clearly numbered steps, explicit validation checkpoints (step 12 user review, step 16 file verification), a resume state table for error recovery, and clear dependency ordering. The feedback loop for external review integration is well-defined. | 3/3 |
progressive_disclosure Appropriately structures content with the main workflow in SKILL.md and detailed protocols in clearly-signaled one-level-deep references (research-protocol.md, interview-protocol.md, external-review.md, section-index.md, section-splitting.md). Navigation is clear and references are well-organized. | 3/3 |
Overall Assessment
This is a well-structured, highly actionable skill for orchestrating complex multi-step planning workflows. Its strengths are exceptional workflow clarity with explicit state management, resume capability, and validation checkpoints, plus excellent progressive disclosure to referenced protocols. Minor verbosity in banner templates and some explanatory text prevents a perfect conciseness score.
Description
Suggestions 3
Total score
9/12| Dimension | 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 actions are performed. | 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', 'technical spec', 'design doc', 'architecture plan', or 'roadmap'. | 2/3 |
distinctiveness_conflict_risk The focus on 'implementation plans' and 'multi-LLM review' provides some distinction, but 'planning features' could overlap with general project management or documentation skills. The unique 'stakeholder interviews' and 'multi-LLM review' aspects help but aren't strongly emphasized as triggers. | 2/3 |
Suggestions
Add more specific concrete outputs (e.g., 'Creates technical specifications, architecture diagrams, task breakdowns, and risk assessments')
Expand trigger terms to include natural variations like 'project plan', 'technical spec', 'design document', 'architecture planning', or 'feature breakdown'
Clarify what makes this distinct from general planning - emphasize the unique multi-LLM review process or stakeholder interview methodology in the trigger clause
Overall Assessment
This description has good structure with explicit 'what' and 'when' clauses, earning full marks for completeness. However, it lacks specificity about concrete deliverables and misses common trigger terms users might naturally use when requesting planning help. The description could better differentiate itself from general planning or documentation skills.