CtrlK
BlogDocsLog inGet started
Tessl Logo

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

1.57x
Quality

26%

Does it follow best practices?

Impact

85%

1.57x

Average score across 3 eval scenarios

SecuritybySnyk

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.md
SKILL.md
Quality
Evals
Security

Quality

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 relies heavily on proper nouns and methodology-specific terminology without explaining what concrete actions the skill performs. While it has a 'Use when...' structure and mentions specific file names that aid distinctiveness, the lack of concrete capability descriptions makes it difficult for Claude to understand what this skill actually does versus when to invoke it.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Creates and maintains product.md, tech-stack.md, and workflow.md files that define project scope, technology choices, and development workflows.'

Expand trigger terms with natural language variations users might say, such as 'project setup', 'initialize project context', 'define tech stack', 'project documentation', or 'development workflow'.

Clarify the 'what' portion by describing outputs or outcomes, e.g., 'Generates structured project context files that guide development decisions and maintain consistency across the codebase.'

DimensionReasoningScore

Specificity

The description mentions 'managing project context artifacts' and 'understanding the relationship between' files, but these are vague actions. It doesn't list concrete actions like 'create', 'update', 'generate', or 'validate' specific artifacts. The language is abstract rather than action-oriented.

1 / 3

Completeness

It has a 'Use when...' clause addressing when to use the skill, but the 'what does this do' part is weak — 'managing project context artifacts' and 'understanding the relationship' are vague descriptions of capability. The 'when' is present but the 'what' is insufficiently concrete.

2 / 3

Trigger Term Quality

It includes some relevant keywords like 'product.md', 'tech-stack.md', 'workflow.md', and 'context-driven development', which are useful trigger terms. However, 'Conductor' is a proper noun that users might not naturally use, and it lacks common variations of what users might say (e.g., 'project setup', 'initialize project', 'project configuration').

2 / 3

Distinctiveness Conflict Risk

The mention of specific file names (product.md, tech-stack.md, workflow.md) and 'Conductor's context-driven development methodology' provides some distinctiveness, but 'managing project context artifacts' is generic enough to overlap with other 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 a high-level conceptual guide that reads more like a methodology whitepaper than an actionable skill for Claude. It is extremely verbose, explaining many concepts Claude already knows (what documentation is, why consistency matters, what anti-patterns are), while lacking the concrete examples, executable commands, and specific templates that would make it truly actionable. The content would benefit enormously from being split into a concise overview with references to detailed artifact templates and examples.

Suggestions

Cut the skill to ~50-80 lines: remove 'Benefits', 'Core Philosophy', 'Common Anti-Patterns', 'Best Practices', and 'Integration with Development Tools' sections entirely—these are generic advice Claude already knows.

Add concrete, copy-paste-ready templates for each artifact (product.md, tech-stack.md, workflow.md) showing actual example content rather than abstract descriptions of what they should contain.

Split detailed content (artifact templates, session continuity procedures, validation checklists) into separate referenced files and keep SKILL.md as a concise overview with clear navigation links.

Add at least one concrete end-to-end example showing the Context → Spec → Plan → Implement workflow with actual file contents at each stage.

DimensionReasoningScore

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, anti-patterns like 'stale context'). Sections like 'Benefits', 'Core Philosophy', 'Common Anti-Patterns', and 'Best Practices' are largely generic advice that doesn't earn its token cost. The skill could be reduced to ~30% of its size without losing actionable information.

1 / 3

Actionability

Despite its length, the skill contains no executable code, no concrete commands (beyond mentioning `/conductor:setup`), no specific file content examples, and no copy-paste ready templates. It describes what each artifact should contain in abstract terms but never shows a concrete example of a product.md, tech-stack.md, or workflow.md. Guidance like 'Pin conductor/product.md for quick reference' and 'Consider pre-commit hooks' is vague direction, not actionable instruction.

1 / 3

Workflow Clarity

The high-level workflow (Context → Spec & Plan → Implement) is stated, and there are numbered steps for session continuity and context maintenance. However, validation steps are checklist-style without concrete verification commands, and the 'Context → Spec & Plan → Implement' workflow lacks specific validation checkpoints or error recovery loops. The context validation checklist is a good start but lacks executable verification.

2 / 3

Progressive Disclosure

The entire skill is a monolithic wall of text with no references to supporting files despite the directory structure suggesting many exist (index.md, code_styleguides/, etc.). No bundle files are provided, and the skill doesn't reference any external documents for deeper content. Everything is inlined, making it both too long for an overview and too shallow for a reference.

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
Dicklesworthstone/pi_agent_rust
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.