Name: scope
Rating: 82.39999999999999 (1 reviews)
Author: majiayu000

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.

2.51x

Quality

77%

Does it follow best practices?

Impact

88%

2.51x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/1-scope/SKILL.md

The canonical home for this skill is scope in majiayu000/claude-skill-registry

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and actionable with concrete templates and checklists, scoring well on conciseness, actionability, and workflow clarity. The main defect is progressive disclosure: the body repeatedly references QUICK-SPEC.md and PROJECT-SCOPE.md, but these files are not present in the bundle.

Suggestions

Add the missing QUICK-SPEC.md and PROJECT-SCOPE.md files to the bundle (e.g., under references/), or remove the references and inline the essential template content so no link is broken.

Add an explicit validation checkpoint to each workflow (e.g., 'Review every section is filled before saving') so the spec is verified for completeness rather than only assembled.

Tighten the overlapping framing sections ('When to Use This Skill', 'Choose Your Approach', 'After Scoping', 'Success Looks Like') to reduce redundancy and free token budget.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, using checklists, a template, and a mistakes table rather than padded prose, but sections like 'When to Use', 'Choose Your Approach', 'After Scoping', and 'Success Looks Like' overlap somewhat and could be trimmed.	4 / 5
Actionability	Copy-paste templates ('Users can [ACTION] to [OUTCOME]'), a concrete worked example, and explicit checklists give actionable guidance; minor gaps remain where sections like Happy Path and Edge Cases only instruct to 'list' items without a worked example.	4 / 5
Workflow Clarity	Both workflows are laid out as ordered, checkbox-based checklists with a clear sequence, and the 'Common Mistakes' table plus 'When You're Stuck' provide loose recovery feedback, though an explicit 'review your spec for completeness' validation checkpoint is only implicit.	4 / 5
Progressive Disclosure	Structure is sound in principle (overview SKILL.md pointing one level deep to QUICK-SPEC.md and PROJECT-SCOPE.md with clear 'See:' links), but no bundle directories or referenced files exist, so the signaled references point to missing files and the progressive disclosure is broken in practice.	3 / 5
	Total	15 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states both capability and trigger conditions with concrete, natural language. It is specific and complete; the only minor weakness is some breadth in the planning triggers that could invite overlap with adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions and two named deliverables ('Creates Quick Feature Specs (10-15 min)' and 'Full Project Scopes (1-2 hours)'), but stops short of enumerating every output section, leaving minor coverage gaps rather than full comprehensiveness.	4 / 5
Completeness	Explicitly answers both 'what' (turn ideas into 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') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrases like 'starting features', 'planning projects', and 'when AI keeps building the wrong thing' map well to what a user would say, though synonym and extension variants are absent so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'spec for AI tools / stakeholder review' niche and the distinctive 'AI keeps building the wrong thing' trigger set it apart, but broad 'starting features, planning projects' phrasing leaves minor overlap risk with general planning skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: majiayu000/claude-skill-registry-data
Path: data/1-scope/SKILL.md
Commit: a1e9f44

Reviewed: about 18 hours ago

Table of Contents

Discovery Implementation Validation

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.