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.

53

1.57x
Quality

33%

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 leads with a 'Use when' clause but fails to articulate what the skill actually does in concrete terms. It relies on vague verbs like 'working with,' 'managing,' and 'understanding' rather than listing specific actions. The mention of Conductor and specific filenames provides some distinctiveness, but the lack of concrete capabilities makes it hard for Claude to confidently select this skill.

Suggestions

Replace vague verbs with specific actions — e.g., 'Creates and maintains product.md, tech-stack.md, and workflow.md files to define project scope, technology choices, and development workflows.'

Add concrete capability descriptions before the 'Use when' clause — e.g., 'Generates project context artifacts, scaffolds new projects with Conductor methodology, and synchronizes product requirements with technical implementation plans.'

Use third person voice consistently and avoid starting with 'Use this skill' — instead describe what the skill does first, then add trigger guidance.

DimensionReasoningScore

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 'working with,' 'managing,' and 'understanding' without specifying concrete capabilities. The 'what' is essentially missing.

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). However, it's unclear what natural user phrases would trigger this — users are unlikely to say 'context-driven development methodology' naturally.

2 / 3

Distinctiveness Conflict Risk

The mention of 'Conductor' and specific file names (product.md, tech-stack.md, workflow.md) 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

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is significantly over-engineered for its purpose, containing extensive explanatory content that Claude doesn't need (philosophy, benefits, generic best practices) while lacking concrete executable examples. The content reads more like a methodology whitepaper than an actionable skill guide. It would benefit greatly from aggressive trimming, splitting detailed sections into referenced files, and adding concrete examples of artifact creation/modification.

Suggestions

Cut the 'Core Philosophy', 'Benefits', and generic 'Best Practices' sections entirely — these explain concepts Claude already understands and waste token budget.

Split detailed content (anti-patterns, IDE/CI integration, session continuity) into separate referenced files, keeping SKILL.md as a concise overview with clear navigation links.

Add concrete examples showing what a minimal product.md or tech-stack.md looks like, rather than just listing what they 'contain'.

Replace the static 'Context Validation Checklist' with an integrated workflow that includes specific commands or tool invocations for validation, with explicit error recovery steps.

DimensionReasoningScore

Conciseness

Extremely verbose at ~300+ lines. Much of the content explains concepts Claude already understands (what product.md contains, what 'living documentation' means, benefits of team alignment, etc.). Sections like 'Core Philosophy', 'Benefits', 'Common Anti-Patterns', and 'Best Practices' are largely generic advice that doesn't add actionable value. The skill could be reduced to roughly 1/3 its size without losing meaningful guidance.

1 / 3

Actionability

Provides structured checklists and some concrete guidance (directory structure, update triggers, validation checklist), but lacks executable code/commands. References like '/conductor:setup' are mentioned without showing what they do. Most guidance is descriptive rather than instructive — it tells Claude what artifacts contain rather than how to create or modify them with specific examples.

2 / 3

Workflow Clarity

The high-level workflow (Context → Spec & Plan → Implement) is stated, and session continuity steps are sequenced. However, validation checkpoints are presented as a static checklist rather than integrated into the workflow with feedback loops. The 'Verify Context Before Implementation' section lists steps but lacks concrete validation commands or error recovery paths.

2 / 3

Progressive Disclosure

The entire skill is a monolithic wall of text with no references to external files for detailed content. Sections like 'Common Anti-Patterns', 'Integration with Development Tools', 'Session Continuity', and 'Best Practices' could easily be split into separate reference documents. Everything is inlined, making the skill overwhelming and poorly structured for quick reference.

1 / 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.

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.