context-driven-development
Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a `conductor/` directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves. Use when setting up a project, creating or updating product docs, managing a tech stack file, defining development workflows, tracking work units, onboarding to an existing codebase, or running project scaffolding.
Install with Tessl CLI
npx tessl i github:wshobson/agents --skill context-driven-developmentOverall
score
85%
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/skillEvaluation — 98%
↑ 1.15xAgent success when using this skill
Validation for skill structure
Discovery
100%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 that excels across all dimensions. It provides specific concrete actions, names exact artifacts and directory structures, includes a comprehensive 'Use when...' clause with natural trigger terms, and establishes a clear niche through its unique artifact naming convention and conductor/ directory pattern.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Creates and maintains project context artifacts', 'Scaffolds new projects from scratch', 'extracts context from existing codebases', 'validates artifact consistency', and 'synchronizes documents'. Also names specific artifacts (product.md, tech-stack.md, workflow.md, tracks.md) and directory structure. | 3 / 3 |
Completeness | Clearly answers both what (creates/maintains artifacts, scaffolds projects, extracts context, validates consistency, synchronizes documents) AND when with explicit 'Use when...' clause listing seven specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'setting up a project', 'product docs', 'tech stack file', 'development workflows', 'tracking work', 'onboarding', 'project scaffolding', 'existing codebase'. Good coverage of variations and natural language terms. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche with distinct triggers around the 'conductor/' directory pattern and specific artifact names (product.md, tech-stack.md, workflow.md, tracks.md). The combination of project scaffolding, context extraction, and artifact management creates a unique profile unlikely to conflict with generic documentation or code skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive guidance on context-driven development with excellent workflow clarity and organization. However, it suffers from verbosity in philosophical sections that Claude doesn't need explained, and lacks concrete executable examples for the commands and processes it describes. The content would benefit from trimming explanatory prose and adding actual code/command examples.
Suggestions
Remove or significantly condense the 'Core Philosophy' and 'Benefits' sections - Claude understands these concepts and they consume tokens without adding actionable value
Add concrete examples of `/conductor:setup` command usage with sample input/output to make the guidance executable
Include a minimal copy-paste example of creating at least one artifact (e.g., a minimal product.md) rather than just describing what should be in it
Replace the abstract 'Update when' lists with specific trigger conditions or commands that detect when updates are needed
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized but includes verbose explanations of concepts Claude already understands (e.g., explaining what 'living documentation' means, extensive philosophy sections). The 'Core Philosophy' and 'Benefits' sections add little actionable value and could be significantly trimmed. | 2 / 3 |
Actionability | Provides good structural guidance and checklists, but lacks concrete executable examples. References commands like `/conductor:setup` without showing actual usage or output. The directory structure is helpful, but there's no copy-paste ready code for creating or validating artifacts. | 2 / 3 |
Workflow Clarity | Clear multi-step workflows are present with explicit sequences (Context → Spec & Plan → Implement). The 'Context Validation Checklist' provides explicit checkpoints, and the 'Session Continuity' section includes clear feedback loops for handling interruptions and state management. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections and appropriate references to external files (references/artifact-templates.md). Content is organized logically from philosophy to practical application, with clear navigation through headings. The single external reference is well-signaled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
91%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 | |
- 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.