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.

1.57x

Quality

56%

Does it follow best practices?

Impact

85%

1.57x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/context-driven-development/SKILL.md

The canonical home for this skill is context-driven-development in wshobson/agents

Quality

Content

38%Weight 40%Scale 1-5

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

The skill body is well-organized and clearly structured, but it is verbose and descriptive rather than actionable, offering high-level guidance over concrete, executable instructions. Validation feedback loops for cross-artifact maintenance are missing.

Suggestions

Trim descriptive prose sections (Benefits, Core Philosophy, anti-patterns) to the minimum needed, removing explanations of concepts Claude already knows.

Replace high-level hints with concrete, executable guidance: artifact templates, exact slash commands, and step-by-step procedures Claude can follow directly.

Add explicit validate→fix→retry checkpoints for cross-artifact synchronization (e.g., after updating tech-stack.md, verify product.md and tracks.md still align).

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with padded sections (Benefits, Core Philosophy, Common Anti-Patterns) restating concepts Claude already knows and describing rather than instructing.	2 / 5
Actionability	Guidance is largely descriptive (artifact contents, 'update when' triggers, 'Consider...') with minimal concrete, executable steps beyond the single /conductor:setup command and no templates to directly apply.	2 / 5
Workflow Clarity	Multi-step sequences (Context → Spec & Plan → Implement, lifecycle, session start/end) and a validation checklist are present, but explicit validate→fix→retry feedback loops for cross-artifact updates are absent.	3 / 5
Progressive Disclosure	No bundle files exist and the single document is well-sectioned with clear headers and no nested references; minor organization gaps exist but structure is good overall.	4 / 5
	Total	11 / 20 Passed

Description

73%Weight 40%Scale 1-5

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 is well-structured with an explicit trigger clause and a distinct, named niche that lowers conflict risk. Its main weakness is limited specificity of concrete actions and missing synonym/variation coverage in trigger terms.

Suggestions

List more concrete actions the skill performs (e.g., 'create, validate, and update context artifacts') rather than only 'managing' and 'understanding'.

Add common natural-language trigger variations and synonyms (e.g., 'project context', 'context documents', 'Conductor setup') to broaden trigger-term coverage.

Separate the 'what it does' and 'when to use it' into distinct clauses with concrete trigger phrases to push completeness toward a 5.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple concrete actions ('managing project context artifacts', 'understanding the relationship between') plus specific filenames, but coverage of actions is limited rather than comprehensive.	3 / 5
Completeness	Has an explicit 'Use this skill when...' trigger clause and states what the skill does, but what and when are bundled into one clause without separate concrete trigger phrases.	4 / 5
Trigger Term Quality	Natural triggers like 'context-driven development', 'managing project context artifacts', and the named artifact files (product.md, tech-stack.md, workflow.md) match what a user would say, though some common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Tied to a named tool (Conductor), a specific methodology, and named artifact files, giving it a clear niche with minimal conflict risk.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/context-driven-development/SKILL.md
Commit: 6453c0b

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

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.