generate-tasks
Convert PRD to structured task list with automatic linking
56
45%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/product-design/skills/generate-tasks/SKILL.mdQuality
Discovery
32%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 identifies a specific conversion task (PRD to task list) but is too terse to be effective for skill selection. It lacks explicit trigger guidance, misses natural keyword variations, and doesn't elaborate on the specific capabilities or use cases that would help Claude distinguish it from similar planning or requirements skills.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user provides a PRD, product requirements document, or asks to break down requirements into tasks'
Include natural keyword variations: 'product requirements document', 'requirements', 'backlog items', 'work breakdown'
Expand on specific capabilities: what kind of linking (dependencies, parent-child), what format for the task list (markdown, JSON), what PRD formats are supported
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PRD conversion) and one action (convert to structured task list with automatic linking), but doesn't list multiple concrete actions or elaborate on what 'structured task list' or 'automatic linking' entails. | 2 / 3 |
Completeness | Only describes what the skill does (convert PRD to task list) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'PRD' and 'task list' which are relevant keywords, but misses common variations like 'product requirements document', 'requirements', 'tasks', 'backlog', or 'work items' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The PRD-to-task-list niche is somewhat specific, but could overlap with general task management, project planning, or requirements processing skills without clearer boundaries. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable structure for task generation from PRDs with clear file format templates and usage examples. However, it lacks concrete task generation logic (deferring to external docs), validation checkpoints for error handling, and includes some unnecessary explanatory content that Claude doesn't need.
Suggestions
Add validation checkpoints: what to do if PRD parsing fails, how to verify generated tasks are complete/correct before saving
Either inline the core task generation logic from 'task-generation.md' or provide more specific extraction rules (e.g., 'Extract tasks from sections titled Requirements, Features, User Stories')
Remove the 'Implementation Tips' section - these are concepts Claude already understands and add token overhead without value
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary sections like 'Implementation Tips for Claude Code' that explain concepts Claude already understands (smart task generation, path management). The format examples are helpful but slightly verbose. | 2 / 3 |
Actionability | Provides concrete file format templates and examples, but the actual task generation logic is deferred to an external file ('task-generation.md') rather than being executable here. The instruction 'Analyze PRD content to generate a comprehensive task list' is vague. | 2 / 3 |
Workflow Clarity | Steps are listed (1-6) but lack validation checkpoints. No guidance on what to do if PRD parsing fails, if the output directory can't be created, or how to verify the generated tasks are correct. Missing feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | Good structure with clear sections (Usage, Arguments, Execution Instructions, Format, Example). Appropriately references external documentation ('task-generation.md') for full process details without nesting multiple levels deep. | 3 / 3 |
Total | 9 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- jpoutrin/product-forge
- Commit
0ebe7ae
- Reviewed
Table of Contents
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.