pm-spec-writing
Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we should build, can we make, what is the plan for, how do we implement, dev brief, feature spec, PRD, user story, acceptance criteria, scope this, prioritize. Also triggers when the user has a list of things they want to build and needs help converting them into well-formed tasks.
68
83%
Does it follow best practices?
Impact
—
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 is a strong skill description with excellent trigger term coverage and completeness. It clearly communicates both what the skill does and when to use it, with an extensive list of natural language triggers. The main weakness is that the core capability description could be slightly more specific about the concrete outputs or actions performed (e.g., does it produce structured markdown briefs, estimate effort, define acceptance criteria as outputs?).
Suggestions
Add more specificity about concrete outputs—e.g., 'Produces structured briefs with acceptance criteria, scope estimates, and implementation steps' to strengthen the specificity dimension.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (translating ideas into dev briefs) and some actions ('spec out', 'file', 'scope', 'convert'), but the core action is somewhat singular—translating ideas into briefs. It doesn't list multiple distinct concrete operations like 'extract, fill, merge' would. | 2 / 3 |
Completeness | Clearly answers both 'what' (translate ideas into actionable dev briefs) and 'when' (explicit 'Use this skill whenever...' clause plus detailed trigger phrases). The when guidance is thorough and explicit. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would actually say: 'I want to add', 'we should build', 'can we make', 'dev brief', 'feature spec', 'PRD', 'user story', 'acceptance criteria', 'scope this', 'prioritize'. These are highly natural and varied. | 3 / 3 |
Distinctiveness Conflict Risk | The skill occupies a clear niche—converting vague ideas into structured dev briefs/specs. The trigger terms like 'dev brief', 'feature spec', 'PRD', 'acceptance criteria' are highly specific to this domain and unlikely to conflict with other skills like coding, documentation, or project management execution 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 strong, actionable PM spec-writing skill with clear workflows, concrete templates, and good failure-pattern documentation. Its main weaknesses are moderate verbosity (some explanatory asides and repeated guidance) and the fact that referenced bundle files don't exist, meaning the progressive disclosure structure is aspirational rather than functional. The three spec formats are the standout strength—they're immediately usable and well-structured.
Suggestions
Trim explanatory asides and commentary (e.g., 'This is not a perfect framework', 'The verify section is the most-skipped and most-important') to reduce token usage while preserving the actionable content.
Create the referenced bundle files (references/feature-spec-template.md, references/dev-brief-template.md, references/prioritization-frameworks.md) and move the full templates there, keeping only abbreviated versions inline to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-written but includes some unnecessary verbosity. Phrases like 'This is not a perfect framework' and explanatory asides ('Not what does it do. The problem comes first; the feature is the proposed solution.') add tokens without adding value for Claude. The failure patterns section partially repeats guidance already embedded in the templates. However, it avoids explaining basic PM concepts Claude already knows. | 2 / 3 |
Actionability | Highly actionable with three concrete, copy-paste-ready spec templates (Feature spec, Dev brief, Bug report), each with specific fields and examples. The impact/effort grid includes concrete examples. The four clarification questions are specific and directly usable. The workflow steps are clear and executable. | 3 / 3 |
Workflow Clarity | The 4-phase framework provides a clear sequence (Clarify → Scope → Write → Sequence), and the 7-step workflow section reinforces this with explicit checkpoints. Phase 1 includes a validation gate ('If any answer is I don't know, go back to the user'). Step 5 explicitly validates that verify steps must be unambiguous. The failure patterns section serves as an additional error-catching checklist. | 3 / 3 |
Progressive Disclosure | References to three external files (feature-spec-template.md, dev-brief-template.md, prioritization-frameworks.md) are well-signaled at the bottom, but none of these bundle files actually exist. The main content is fairly long and could benefit from moving the full templates into the referenced files, keeping only summaries inline. The 'When NOT to use' section nicely cross-references other skills. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rampstackco/claude-skills
- Commit
8e70d03
- 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.