Reads a site feature specification file and converts it into a structured, actionable development task list saved to the project memory bank. Use when you need to break down requirements into developer tasks, plan project work from a PRD or spec, convert feature specifications into tickets with acceptance criteria, or create a task breakdown from site-setup documentation. Produces per-task acceptance criteria, file references, and technical stack notes drawn exclusively from the specification — no scope creep or unspecified features added.
93
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is an excellent skill description that clearly articulates what the skill does, when to use it, and what it produces. It uses third person voice throughout, includes a comprehensive 'Use when' clause with multiple natural trigger scenarios, and adds valuable constraints (no scope creep). The description is specific enough to be distinctive while covering the natural language variations users might employ.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: reads a specification file, converts it into a structured task list, saves to project memory bank, produces per-task acceptance criteria, file references, and technical stack notes. Very detailed about what it does and its constraints (no scope creep). | 3 / 3 |
Completeness | Clearly answers both what (reads spec files, converts to structured task lists with acceptance criteria, file references, and tech stack notes) and when (explicit 'Use when' clause listing four distinct trigger scenarios including PRD breakdown, spec conversion, and task planning). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'break down requirements', 'developer tasks', 'plan project work', 'PRD', 'spec', 'feature specifications', 'tickets', 'acceptance criteria', 'task breakdown', 'site-setup documentation'. Good coverage of variations. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche: converting site feature specifications into development task lists with acceptance criteria. The specificity of reading a spec file and outputting to a 'project memory bank' with per-task details makes it unlikely to conflict with general project management or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 that provides a clear, actionable workflow for converting specifications into task lists. Its strengths are the concrete mapping example, the complete task list template, and the explicit validation checkpoint with anti-scope-creep guardrails. Minor redundancy in restating principles across steps slightly reduces conciseness, but overall the content is effective and well-organized.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundancy — the principles (no scope creep, quote don't paraphrase, flag gaps) are stated both as bullet points in Step 2 and reiterated in the validation step. The task list format template is lengthy but serves as a concrete reference. Some trimming is possible but it's not egregiously verbose. | 2 / 3 |
Actionability | The skill provides concrete, actionable guidance: specific file paths (ai/memory-bank/site-setup.md, ai/memory-bank/tasks/[project-slug]-tasklist.md), a complete copy-paste-ready task list template with example tasks, acceptance criteria patterns, and a concrete mapping example from spec text to task description. The workflow is fully executable. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation in Step 5 including a cross-check checkpoint. The feedback loop is present: draft tasks → validate against spec → remove or flag untraced tasks. The validation step specifically addresses the destructive risk of scope creep with concrete checks. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with a clear overview workflow followed by the detailed template format, and appropriately references the full methodology in a single external file (ai/agents/pm.md) — one level deep, clearly signaled at the end. Content is appropriately split between the workflow steps and the template. | 3 / 3 |
Total | 11 / 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 | |
010799b
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.