roadmap-planning
When the user needs to organize product initiatives into a prioritized, time-sequenced plan with outcomes and dependencies.
70
63%
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 ./skills/roadmap-planning/SKILL.mdQuality
Discovery
50%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 provides a reasonable 'when to use' trigger but lacks explicit capability statements (the 'what it does'). It misses key natural trigger terms like 'roadmap' that users would commonly say. The description is concise but would benefit from separating capabilities from triggers and including more user-facing vocabulary.
Suggestions
Add explicit capability statements before the trigger clause, e.g., 'Creates product roadmaps with prioritized initiatives, milestone timelines, outcome definitions, and dependency mapping.'
Include common natural trigger terms users would say: 'roadmap', 'product roadmap', 'release plan', 'product planning', 'initiative prioritization'.
Restructure to separate 'what' from 'when': list concrete actions first, then add a 'Use when...' clause with trigger terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (product initiatives) and some actions (organize, prioritize, time-sequence), but doesn't list multiple concrete specific actions like 'create roadmap timelines, map dependencies, define milestones, assign outcomes to quarters.' | 2 / 3 |
Completeness | The description answers 'when' ('When the user needs to...') but the 'what' is only implied through the trigger clause rather than explicitly stated as separate capability descriptions. The 'what does this do' portion is weak — it's bundled into the 'when' clause rather than clearly articulated. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'prioritized', 'dependencies', 'product initiatives', and 'time-sequenced plan', but misses common natural user terms like 'roadmap', 'product roadmap', 'release plan', 'backlog prioritization', or 'sprint planning'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'product initiatives', 'prioritized', 'time-sequenced', 'outcomes', and 'dependencies' provides moderate specificity, but could overlap with general project management, sprint planning, or backlog grooming skills without clearer niche definition. | 2 / 3 |
Total | 8 / 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 that provides clear workflows, concrete output formats, and useful examples. Its main weakness is verbosity in the Frameworks & Best Practices section, which explains several concepts Claude likely already understands and could be more concise or split into a reference file. The workflow and output format sections are excellent and provide genuinely useful, specific guidance.
Suggestions
Trim the Frameworks & Best Practices section by removing explanations of why outcomes are better than outputs (Claude knows this) and condensing to just the actionable rules and formats.
Consider moving RICE scoring details and stage-appropriate planning guidance into a separate reference file to improve progressive disclosure and reduce the main file's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary elaboration. The 'Frameworks & Best Practices' section explains concepts like outcomes vs outputs at length, and the 'When to Use' section over-specifies trigger conditions. Some bullet points in best practices (e.g., 'Outcome roadmaps are resilient to change' explanation) could be trimmed since Claude understands these concepts. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: a clear outcome statement template ('Enable [segment] to [outcome] so that [impact]'), specific RICE scoring definitions with scales, concrete table formats for output, and two worked examples showing input-to-output transformations. Every step in the workflow is specific enough to execute. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with logical progression from gathering state through validation. It includes a capacity validation checkpoint (step 7) that acts as a reality check, and the 'Not Doing' section serves as an explicit exclusion validation. The three-horizon structure (Now/Next/Later) provides clear sequencing with appropriate commitment levels. | 3 / 3 |
Progressive Disclosure | The skill references related skills (prd-writing, mvp-scoping, user-research-synthesis) which is good navigation. However, the Frameworks & Best Practices section is quite long and inline — some of this content (like stage-appropriate planning details or RICE scoring specifics) could be split into a reference file. The document is a single monolithic file that's on the longer side. | 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
- shawnpang/startup-founder-skills
- Commit
4ad31b4
- 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.