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.
Install with Tessl CLI
npx tessl i github:waynesutton/convexskills --skill avoid-feature-creep60
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 well-crafted skill description with strong trigger terms and explicit usage guidance. The main weakness is that the specific capabilities could be more concrete - it describes the problem domain well but doesn't detail the specific actions or frameworks the skill provides. The description uses proper third person voice throughout.
Suggestions
Add 2-3 specific concrete actions the skill performs, such as 'evaluates feature requests against MVP criteria', 'creates prioritization matrices', or 'identifies scope creep indicators'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (feature creep prevention, software planning) and some actions (planning features, reviewing scope, managing backlogs), but lacks concrete specific actions like 'prioritize features using X framework' or 'evaluate feature requests against criteria'. | 2 / 3 |
Completeness | Clearly answers both what ('Prevent feature creep when building software') and when ('Use this skill when planning features, reviewing scope, building MVPs, managing backlogs, or when a user says just one more feature'). Has explicit 'Use this skill when...' clause. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'planning features', 'reviewing scope', 'building MVPs', 'managing backlogs', 'just one more feature', 'ship faster', 'bloated products'. These are phrases developers naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on feature creep prevention and scope management. Distinct triggers like 'just one more feature', 'MVPs', 'backlogs', and 'bloated products' make it unlikely to conflict with general coding or project management skills. | 3 / 3 |
Total | 11 / 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 templates buried under excessive explanation of concepts Claude already understands. The content would benefit from aggressive trimming to ~50 lines focusing on the decision checklist, MVP template, and scope decision log, with detailed sections moved to referenced files.
Suggestions
Cut 80% of explanatory content - remove all 'why feature creep is bad' sections, motivational quotes, and concept definitions Claude already knows
Extract templates (MVP Scope Document, Scope Decision Log, Backlog Audit) into separate referenced files like TEMPLATES.md
Consolidate the multiple checklists into a single, concise decision framework that fits on one screen
Remove or drastically shorten the AI-specific sections - the core principles apply regardless of whether an AI agent is involved
| 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 20% of current length. | 1 / 3 |
Actionability | Provides concrete checklists and templates (MVP scope document, decision framework, scope decision log), but much content is abstract advice rather than executable guidance. The bash example is trivial (just git commands). Templates are useful but buried in verbose explanations. | 2 / 3 |
Workflow Clarity | Contains clear checklists and decision frameworks with numbered steps. However, lacks validation checkpoints for the processes described - no feedback loops for when scope decisions fail or need revision. The 'Recovery' section has steps but no verification that bloat is actually reduced. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline despite being long enough to warrant splitting (AI guidelines, recovery steps, templates could each be separate files). No navigation structure beyond headers. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 12 / 16 Passed | |
- 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.