context-driven-development
Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structured project documentation.
21
10%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/context-driven-development/SKILL.mdQuality
Discovery
0%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 description is highly abstract and reads like a marketing tagline rather than a functional skill description. It fails to specify concrete actions, lacks natural trigger terms users would use, provides no 'Use when...' guidance, and is too generic to be distinguishable from other documentation-related skills.
Suggestions
Replace abstract language with concrete actions, e.g., 'Creates and updates CONTEXT.md files that document project structure, conventions, and AI interaction guidelines.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about creating context files, setting up AI project documentation, writing CONTEXT.md, or establishing project conventions for Claude.'
Include specific file types or artifacts involved (e.g., 'CONTEXT.md', 'CLAUDE.md', '.context/' directory) to make the skill distinctive and reduce conflict with generic documentation skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'implementing and maintaining context', 'managed artifact', 'consistent AI interactions', and 'team alignment'. No concrete actions are listed — it reads more like a mission statement than a capability description. | 1 / 3 |
Completeness | The 'what' is vague (implementing and maintaining context as a managed artifact) and there is no 'when' clause or explicit trigger guidance at all. Both components are weak or missing. | 1 / 3 |
Trigger Term Quality | The description lacks natural keywords a user would say. Terms like 'managed artifact', 'structured project documentation', and 'consistent AI interactions' are abstract jargon. A user would more likely say things like 'context file', 'CONTEXT.md', 'project docs for AI', or 'Claude context'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic — 'structured project documentation', 'team alignment' — that it could easily overlap with any documentation, project management, or onboarding skill. Nothing clearly carves out a distinct niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a lengthy conceptual guide about context-driven development that reads more like a methodology whitepaper than an actionable skill for Claude. It explains many things Claude already knows (benefits of documentation, what anti-patterns are, why consistency matters) while providing almost no concrete, executable guidance—no code examples, no template contents, no specific commands. The content would benefit enormously from being cut to ~25% of its current size and replaced with concrete artifacts and examples.
Suggestions
Replace the verbose conceptual sections (Core Philosophy, Benefits, Common Anti-Patterns) with a brief 2-3 line summary and provide concrete, copy-paste ready templates for each artifact (product.md, tech-stack.md, etc.) with example content.
Add executable examples: show a concrete product.md template, a sample tech-stack.md with real entries, and example commands for setup and validation rather than abstract descriptions.
Split the monolithic content into referenced files—move IDE Integration, CI/CD Integration, Session Continuity, and Anti-Patterns into separate reference documents and link to them from a concise overview.
Add concrete validation steps with actual commands or scripts rather than manual checklists—e.g., a script to check tech-stack.md against package.json, or a specific diff command to verify artifact synchronization.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, with extensive sections explaining concepts Claude already understands (what product.md is, benefits of documentation, anti-patterns, IDE integration tips). Much of this is general knowledge padding—e.g., the 'Benefits' section, 'Core Philosophy', and 'Common Anti-Patterns' explain obvious documentation principles rather than providing novel, actionable guidance. | 1 / 3 |
Actionability | Despite its length, the skill contains zero executable code, no concrete commands (beyond references to `/conductor:setup`), no example file contents, and no copy-paste ready templates. Instructions like 'Read all context artifacts' and 'Flag any outdated information' are vague directions rather than concrete, actionable steps. | 1 / 3 |
Workflow Clarity | There is a clear high-level workflow sequence (Context → Spec & Plan → Implement) and checklists for validation, but validation steps lack concrete tooling or commands to execute. The 'Context Validation Checklist' is a good structure, but there are no feedback loops for error recovery or specific verification mechanisms beyond manual review. | 2 / 3 |
Progressive Disclosure | The skill references `resources/implementation-playbook.md` for detailed examples, which is good progressive disclosure, but no bundle files are provided so this reference is unverifiable. The main file itself is a monolithic wall of text that should have been split—sections like anti-patterns, IDE integration, CI/CD integration, and session continuity could easily be separate reference files. | 2 / 3 |
Total | 6 / 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
- sickn33/antigravity-awesome-skills
- Commit
f5dc9e3
- 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.