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.
70
56%
Does it follow best practices?
Impact
97%
1.14xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/conductor/skills/context-driven-development/SKILL.mdQuality
Discovery
92%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 strong skill description that clearly articulates specific capabilities and provides explicit trigger guidance via a 'Use when...' clause. The named artifacts and directory structure add concreteness. The main weakness is moderate overlap risk with other project management or documentation skills due to some broad trigger terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creates/maintains context artifacts (with named files), scaffolds new projects, extracts context from existing codebases, validates artifact consistency, and synchronizes documents. Very concrete and detailed. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates/maintains specific artifacts, scaffolds, extracts context, validates, synchronizes) and 'when' with an explicit 'Use when...' clause listing seven distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms users would say: 'setting up a project', 'product docs', 'tech stack', 'development workflows', 'tracking work', 'onboarding', 'project scaffolding'. These cover a wide range of natural user phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | While the specific artifact names (product.md, tech-stack.md, etc.) and the `conductor/` directory provide some distinctiveness, terms like 'setting up a project', 'product docs', and 'development workflows' are broad enough to potentially overlap with general project management or documentation skills. | 2 / 3 |
Total | 11 / 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 comprehensive conceptual guide to context-driven development but fails as an actionable skill for Claude. It is extremely verbose, spending most of its token budget on philosophy, benefits, anti-patterns, and best practices that Claude doesn't need explained. The most critical gap is the complete absence of concrete, executable examples—no template content, no actual file examples, no commands—making it descriptive rather than instructive.
Suggestions
Replace the artifact description sections with actual template content or concrete examples showing what a minimal product.md, tech-stack.md, etc. should look like, rather than just listing what they contain.
Remove or drastically condense the 'Benefits', 'Core Philosophy', 'Common Anti-Patterns', 'Best Practices', and 'Integration with Development Tools' sections—these explain concepts Claude already understands and consume significant token budget.
Add executable commands or code for context validation (e.g., a script that checks tech-stack.md against package.json, or a concrete validation command) instead of abstract checklists.
Move detailed sections like 'Session Continuity', 'IDE Integration', 'CI/CD Integration', and 'Common Anti-Patterns' into separate reference files and link to them from a concise overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Much of the content explains concepts Claude already knows (what product docs are, benefits of documentation, what 'institutional memory' means). Sections like 'Benefits', 'Core Philosophy', 'Common Anti-Patterns', and 'Best Practices' are largely generic advice that doesn't add actionable value. The skill could be reduced to ~30% of its size without losing meaningful guidance. | 1 / 3 |
Actionability | Despite its length, the skill contains zero executable code, no concrete commands (references like `/conductor:setup` are mentioned but never defined), no file content examples, and no copy-paste ready templates. The artifact descriptions list what should be in each file but never show actual content. The reference to 'artifact-templates.md' defers the most actionable content to another file. | 1 / 3 |
Workflow Clarity | The high-level workflow (Context → Spec & Plan → Implement) is stated, and there are sequenced steps for greenfield/brownfield setup and session continuity. However, validation steps are checklists rather than executable verification commands, and the 'verify context before implementation' step is vague ('Flag any outdated information'). Missing concrete validation mechanisms caps this at 2. | 2 / 3 |
Progressive Disclosure | There is one reference to an external file (references/artifact-templates.md) and the directory structure is clearly shown. However, the massive amount of inline content (anti-patterns, benefits, best practices, IDE integration, CI/CD integration, session continuity) should be split into separate reference files. The skill is a monolithic wall of text that would benefit greatly from splitting. | 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
- wshobson/agents
- Commit
27a7ed9
- 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.