scope
Turn ideas into clear, buildable specs for AI tools or stakeholder review. Use when starting features, planning projects, or when AI keeps building the wrong thing. Creates Quick Feature Specs (10-15 min) for immediate AI builds or Full Project Scopes (1-2 hours) for budget planning and contractor estimates.
83
77%
Does it follow best practices?
Impact
88%
2.51xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/data/1-scope/SKILL.mdQuality
Discovery
92%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 description that clearly communicates what the skill does and when to use it. The inclusion of specific deliverable types with time estimates (Quick Feature Specs at 10-15 min, Full Project Scopes at 1-2 hours) adds excellent concreteness. The 'Use when...' clause with the relatable trigger 'when AI keeps building the wrong thing' is particularly effective, though there's minor overlap risk with general project planning skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and outputs: 'Turn ideas into clear, buildable specs', 'Creates Quick Feature Specs (10-15 min) for immediate AI builds' and 'Full Project Scopes (1-2 hours) for budget planning and contractor estimates.' These are specific deliverables with time estimates and use cases. | 3 / 3 |
Completeness | Clearly answers both what ('Turn ideas into clear, buildable specs', 'Creates Quick Feature Specs' and 'Full Project Scopes') and when ('Use when starting features, planning projects, or when AI keeps building the wrong thing'). The 'Use when...' clause is explicit and covers multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'specs', 'features', 'planning projects', 'AI keeps building the wrong thing', 'budget planning', 'contractor estimates', 'starting features'. These cover multiple natural phrasings a user might employ when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | While it carves out a niche around spec writing and project scoping, terms like 'planning projects' and 'starting features' could overlap with general project management or task planning skills. The specific mention of 'AI keeps building the wrong thing' and the two distinct output types (Quick Feature Specs vs Full Project Scopes) help differentiate it, but some overlap risk remains. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
62%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 well-structured framework for spec writing with clear workflows and checklists, but it reads more like a human coaching guide than an AI skill instruction. Several sections ('When You're Stuck', 'Success Looks Like', 'Common Mistakes') are oriented toward human users rather than Claude, and the referenced bundle files (QUICK-SPEC.md, PROJECT-SCOPE.md) are missing, undermining the progressive disclosure structure.
Suggestions
Remove or significantly trim human-oriented sections like 'When You're Stuck', 'Success Looks Like', and 'Common Mistakes' — Claude doesn't need motivational guidance or tips about using competitor products.
Provide the referenced QUICK-SPEC.md and PROJECT-SCOPE.md bundle files, and reduce the inline content in SKILL.md to avoid duplication between the overview and the detailed files.
Reframe the skill as instructions for Claude (e.g., 'When the user asks for a feature spec, gather the following information and produce output in this format') rather than as a tutorial teaching someone how to write specs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary sections like 'When You're Stuck' and 'Success Looks Like' that explain things Claude already understands. The 'Common Mistakes' table and 'Using Your Spec With AI Tools' sections add moderate value but could be tighter. The core workflow sections are reasonably efficient. | 2 / 3 |
Actionability | Provides templates and checklists which are somewhat actionable, but the guidance is more about teaching humans how to write specs than giving Claude executable instructions. The templates use fill-in-the-blank patterns rather than concrete executable code. The examples are helpful but the skill is more of a coaching guide than a precise instruction set. | 2 / 3 |
Workflow Clarity | Both the Quick Feature Spec and Full Project Scope workflows have clear checklists with explicit sequencing. The progress trackers with checkboxes provide good validation checkpoints. The 'After Scoping' section gives clear next steps. For a non-destructive spec-writing task, this level of workflow clarity is appropriate. | 3 / 3 |
Progressive Disclosure | References to QUICK-SPEC.md and PROJECT-SCOPE.md are well-signaled and one level deep, which is good. However, no bundle files are provided, so these references lead nowhere. Additionally, the SKILL.md itself inlines substantial content (all the Quick Feature Spec sections, the 7 Required Sections list) that overlaps with what the referenced files presumably contain, creating potential redundancy. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- majiayu000/claude-skill-registry
- Commit
3bed9b9
- 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.