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.

Quality

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-awesome-skills-claude/skills/context-driven-development/SKILL.md

Quality

Content

12%Scale 1-3

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 document about context-driven development that reads more like a methodology whitepaper than an actionable skill for Claude. It lacks concrete code examples, executable commands, or specific templates, instead providing abstract process descriptions and general best practices that Claude already understands. The content would benefit enormously from being condensed to ~50 lines of core workflow with concrete examples, splitting detailed reference material into separate files.

Suggestions

Reduce the main skill to a concise overview (~50-80 lines) covering the core workflow and artifact structure, moving detailed sections (anti-patterns, benefits, IDE integration, CI/CD, session continuity) into separate referenced files.

Add concrete, executable examples: provide actual file templates for product.md, tech-stack.md, etc. with sample content that Claude can copy and adapt.

Replace abstract instructions like 'Flag any outdated information' with specific, actionable steps such as comparing dependency versions in tech-stack.md against package.json using a concrete command or code snippet.

Create and include the referenced `resources/implementation-playbook.md` bundle file, and add additional reference files for the detailed content currently bloating the main skill.

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 about documentation practices that doesn't add actionable value. The 'Benefits' section, 'Common Anti-Patterns' section, and 'Integration with Development Tools' section are largely unnecessary padding.	1 / 3
Actionability	Despite its length, the skill provides almost no concrete, executable guidance. There are no code examples, no specific commands (beyond vague references to `/conductor:setup`), no file templates, and no copy-paste ready content. Instructions like 'Read all context artifacts' and 'Flag any outdated information' are abstract descriptions rather than actionable steps.	1 / 3
Workflow Clarity	The skill does outline a multi-step workflow (Context → Spec & Plan → Implement) and includes checklists and sequenced steps for various processes like session continuity and context validation. However, there are no concrete validation commands or feedback loops with error recovery—validation steps are abstract checklists rather than executable verification steps.	2 / 3
Progressive Disclosure	The skill is a monolithic wall of text with all content inline. It references `resources/implementation-playbook.md` but no bundle files are provided, making this a dead reference. The massive amount of content (artifact descriptions, anti-patterns, IDE integration, CI/CD, session continuity, best practices) should be split across referenced files but is instead dumped into a single document with no clear navigation structure.	1 / 3
	Total	5 / 12 Passed

Description

0%Scale 1-3

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 heavily padded with abstract buzzwords and lacks concrete actions, natural trigger terms, and explicit 'when to use' guidance. It reads like a marketing tagline rather than a functional skill description, making it nearly impossible for Claude to reliably select this skill from a pool of alternatives.

Suggestions

Replace abstract language with concrete actions, e.g., 'Creates and updates CONTEXT.md files that document project goals, architecture decisions, and conventions for AI-assisted development.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about context files, CONTEXT.md, project documentation for AI, or maintaining shared context across AI sessions.'

Differentiate from generic documentation skills by specifying the unique artifact type and purpose, e.g., referencing specific file formats, AI context patterns, or tooling conventions.

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. The description fails to answer either question clearly.	1 / 3
Trigger Term Quality	The description lacks natural keywords a user would say. Terms like 'managed artifact', 'structured project documentation', and 'team alignment' are abstract buzzwords. A user needing this skill would more likely say things like 'context file', 'CONTEXT.md', 'project context', or 'AI prompt documentation'.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic — 'structured project documentation' and 'consistent AI interactions' could overlap with many documentation, project management, or AI-related skills. Nothing clearly carves out a distinct niche.	1 / 3
	Total	4 / 12 Passed

Validation

90%

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 — 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: popey/claude-code-skills
Path: plugins/antigravity-awesome-skills-claude/skills/context-driven-development/SKILL.md
Commit: a5a6601

Reviewed: 5 days 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.