Break down a change into an implementation task checklist. Trigger: "tasks", "breakdown", "task list", "desglosar", "tareas", "sdd tasks", "plan de implementación", "/sdd:continue (when design exists but tasks don't)".
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is strong in trigger coverage and completeness, with explicit trigger terms in multiple languages and clear usage conditions. The main weakness is limited specificity about what the breakdown process actually produces or involves beyond 'a checklist'. The description effectively distinguishes itself from other planning-related skills.
Suggestions
Add more specific actions describing what the breakdown includes (e.g., 'identifies dependencies, estimates complexity, sequences tasks by priority')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (implementation planning) and one action (break down a change into a checklist), but lacks detail on what specific actions are involved in the breakdown process or what the output looks like. | 2 / 3 |
Completeness | Clearly answers both what (break down a change into implementation task checklist) and when (explicit 'Trigger:' clause with multiple specific trigger terms and conditions like 'when design exists but tasks don't'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'tasks', 'breakdown', 'task list', plus Spanish equivalents ('desglosar', 'tareas'), and specific command triggers ('/sdd:continue'). These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on implementation task breakdown with specific triggers. The '/sdd:continue' command and context about 'when design exists but tasks don't' make it distinct from general task or planning skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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-structured, highly actionable skill for task breakdown generation. Its strengths are the concrete templates, clear workflow steps, and comprehensive error recovery guidance. The main weakness is moderate verbosity - some tables and guidelines could be condensed without losing clarity, and the skill could benefit from extracting reference material to separate files.
Suggestions
Consider extracting the Estimation Guide and Phase Organization Guidelines to a separate reference file to reduce the main skill's length
Condense the 'Task Writing Rules' table - Claude understands what makes tasks specific/actionable without the anti-examples column
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (e.g., the task writing rules table and definition of done could be tighter). The TDD detection chain and phase organization guidelines are well-structured but slightly verbose for Claude's capabilities. | 2 / 3 |
Actionability | Provides fully concrete guidance with specific file formats, markdown templates, estimation tags, and exact examples. The task file format template is copy-paste ready, and the tables provide clear criteria with good/bad examples. | 3 / 3 |
Workflow Clarity | Clear 5-step workflow with explicit validation through the TDD detection chain, persistence contract, and error recovery table. Each step has defined inputs/outputs, and the phase organization provides clear sequencing with dependency awareness. | 3 / 3 |
Progressive Disclosure | References external files appropriately (persistence-contract.md, engram-convention.md, openspec-convention.md) but the main content is quite long. Some sections like the Phase Organization Guidelines and Estimation Guide could potentially be extracted to separate reference files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 10 / 11 Passed | |
d9bf9a4
Table of Contents
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.