context-driven-development
Use this skill when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md, and workflow.md files.
49
26%
Does it follow best practices?
Impact
85%
1.57xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/context-driven-development/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description focuses heavily on when to use the skill but fails to articulate what concrete actions it performs. It relies on abstract verbs like 'managing' and 'understanding' rather than specific capabilities. The mention of Conductor-specific terminology and file names provides some distinctiveness but not enough to compensate for the lack of concrete action descriptions.
Suggestions
Replace vague verbs ('managing,' 'understanding') with specific actions like 'Creates and updates product.md files, configures tech-stack.md definitions, generates workflow.md templates.'
Add concrete outcomes or use cases, e.g., 'Scaffolds project context files for new projects, synchronizes context artifacts when requirements change, validates consistency across product, tech-stack, and workflow definitions.'
Expand trigger terms to include natural user phrases like 'set up project context,' 'initialize Conductor project,' 'create product definition,' or 'configure development workflow.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'working with,' 'managing,' and 'understanding the relationship between' without listing any concrete actions. It names some files (product.md, tech-stack.md, workflow.md) but doesn't describe what specific operations are performed on them. | 1 / 3 |
Completeness | It has a 'Use when...' clause addressing the 'when' question, but the 'what does this do' part is extremely weak — it only says 'managing project context artifacts' and 'understanding the relationship between' files without explaining what concrete outcomes or actions the skill performs. | 2 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'context-driven development,' 'project context artifacts,' and specific file names (product.md, tech-stack.md, workflow.md), but these are fairly niche/technical terms. It's missing natural user phrases like 'set up project,' 'initialize workflow,' or 'define tech stack.' | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Conductor's context-driven development methodology' and specific file names (product.md, tech-stack.md, workflow.md) provides some distinctiveness, but 'managing project context artifacts' is broad enough to overlap with general project management or documentation skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely verbose and largely descriptive rather than actionable. It reads more like a methodology whitepaper than an operational guide for Claude—explaining concepts Claude already understands (documentation benefits, anti-patterns of team collaboration) while lacking concrete examples, templates, or executable commands. The content would benefit enormously from being cut to ~25% of its current size and replaced with concrete artifact templates and specific commands.
Suggestions
Replace the descriptive artifact sections (product.md, tech-stack.md, etc.) with concrete template examples showing actual file content Claude should generate or maintain.
Cut the 'Benefits', 'Core Philosophy', 'Common Anti-Patterns', and 'Integration with Development Tools' sections entirely—these explain concepts Claude already knows and add no actionable guidance.
Add executable examples: show a concrete `/conductor:setup` interaction, a sample product.md with actual content, and a specific context update diff.
Split detailed content (session continuity, greenfield vs brownfield, context maintenance) into separate referenced files, keeping SKILL.md as a concise overview with clear navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Much of the content explains concepts Claude already understands (what product vision is, what tech stacks are, benefits of documentation). Sections like 'Benefits', 'Core Philosophy', and 'Common Anti-Patterns' are largely things Claude knows. The 'Integration with Development Tools' section gives vague IDE/CI suggestions that add little actionable value. | 1 / 3 |
Actionability | Despite its length, the skill contains zero executable code, no concrete commands (beyond mentioning `/conductor:setup`), no specific file content examples, and no templates showing what these artifacts should actually look like. Instructions like 'Update product.md to reflect new capabilities' are vague descriptions rather than concrete guidance. | 1 / 3 |
Workflow Clarity | The high-level workflow (Context → Spec & Plan → Implement) is stated and the context validation checklist provides some structure. However, there are no explicit validation checkpoints with concrete verification steps, and the 'Context Maintenance Principles' section lists steps without clear error recovery or feedback loops. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files for detailed content. Everything is inlined in one massive document—artifact descriptions, anti-patterns, best practices, IDE integration, session continuity, etc.—when much of this could be split into referenced documents. The directory structure hints at other files but doesn't link to them. | 1 / 3 |
Total | 5 / 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
- Dicklesworthstone/pi_agent_rust
- Commit
47823e3
- 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.