avoid-feature-creep
Prevent feature creep when building software, apps, and AI-powered products. Use this skill when planning features, reviewing scope, building MVPs, managing backlogs, or when a user says "just one more feature." Helps developers and AI agents stay focused, ship faster, and avoid bloated products.
69
54%
Does it follow best practices?
Impact
96%
1.24xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/avoid-feature-creep/SKILL.mdQuality
Discovery
82%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 solid description with excellent trigger term coverage and clear completeness (both what and when are addressed). The main weaknesses are moderate specificity—it describes the problem space well but doesn't detail concrete methods or techniques—and some potential overlap with general project management skills.
Suggestions
Add 2-3 specific concrete actions the skill performs, such as 'applies the 80/20 rule to feature lists' or 'identifies must-have vs nice-to-have features'
Include more distinctive terminology to reduce conflict with general project management skills, such as 'scope reduction', 'feature prioritization matrix', or 'MVP scoping'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (feature creep prevention, software planning) and some actions ('planning features, reviewing scope, building MVPs, managing backlogs'), but lacks concrete specific actions like 'prioritize features using X framework' or 'cut scope by Y method'. | 2 / 3 |
Completeness | Clearly answers both what ('Prevent feature creep', 'stay focused, ship faster, avoid bloated products') and when ('Use this skill when planning features, reviewing scope, building MVPs, managing backlogs, or when a user says just one more feature'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'planning features', 'reviewing scope', 'building MVPs', 'managing backlogs', and the clever inclusion of 'just one more feature' which captures a common user phrase indicating scope creep. | 3 / 3 |
Distinctiveness Conflict Risk | While 'feature creep' and 'MVP' are somewhat distinctive, terms like 'planning features' and 'managing backlogs' could overlap with general project management or agile/scrum skills. The scope prevention angle helps but isn't fully unique. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from severe verbosity - ironically, a document about avoiding bloat is itself bloated. It contains useful frameworks and checklists buried under excessive explanation of concepts Claude already understands. The content would benefit dramatically from aggressive trimming and splitting into referenced sub-documents.
Suggestions
Cut 70%+ of explanatory content - remove sections explaining what feature creep is, why it's bad, and motivational quotes. Claude knows this.
Extract templates (MVP Scope Document, Scope Decision Log) into separate referenced files like TEMPLATES.md
Move AI-specific guidelines and Recovery sections to separate files, keeping only brief pointers in the main skill
Add explicit validation steps with failure recovery paths, e.g., 'If stakeholder rejects deferral, escalate to [specific process]'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Explains concepts Claude already knows (what feature creep is, why it's bad, basic project management). Contains motivational content, quotes, and extensive rationale that doesn't add actionable value. Could be reduced to 1/4 the length. | 1 / 3 |
Actionability | Contains concrete checklists and templates (MVP scope document, decision framework, scope decision log) which are useful. However, much content is philosophical rather than executable - templates are markdown examples rather than copy-paste tools, and guidance is often abstract ('validate the problem' without specific methods). | 2 / 3 |
Workflow Clarity | Has clear sequences (decision framework checklist, monthly backlog audit, session checks) but lacks validation checkpoints and feedback loops. The 'Recovery' section has steps but no verification that bloat was actually reduced. No explicit 'if this fails, do that' guidance. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline regardless of depth or frequency of use. Could easily split AI-specific guidelines, templates, and recovery steps into separate referenced documents. | 1 / 3 |
Total | 6 / 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
- waynesutton/convexskills
- Commit
8ef49c9
- 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.