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

—

Does it follow best practices?

Impact

85%

1.57x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

50%

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

The body is well-organized and covers its domain thoroughly with artifact schemas, a directory map, and validation checklists, but it is verbose and conceptual where it could be lean, and it keeps all detail inline rather than splitting reference material into bundled files. Workflows lack hard validation gates and feedback loops.

Suggestions

Trim conceptual padding (Core Philosophy, Benefits, Institutional Memory prose) that restates what Claude already knows about documentation and version control; keep the artifact schemas, directory map, and checklists.

Move the per-artifact content schemas and anti-patterns into bundled reference files (e.g. references/artifacts.md, references/anti-patterns.md) and link to them one level deep, leaving SKILL.md a lean overview.

Add explicit validate-then-proceed gates with feedback loops to the maintenance workflows (e.g. after 'Verify Context Before Implementation', a concrete 'if outdated: update and re-verify before proceeding' step).

Dimension	Reasoning	Score
Conciseness	The body contains useful structured reference material (artifact schemas, directory layout, checklists) but is padded with conceptual prose Claude largely already knows ('Decisions and rationale are preserved', 'Context survives team changes', the Benefits and Core Philosophy sections), fitting the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean anchor at 3.	2 / 3
Actionability	It gives concrete artifact contents and step lists ('Before adding any new dependency: 1. Check if existing dependencies...'), but the guidance is largely descriptive ('Read all context artifacts', 'Propose updates before proceeding') with no copy-paste-ready specifics, matching the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	Sequences are present (Context -> Spec & Plan -> Implement, greenfield/brownfield setup, session start/end) and a Context Validation Checklist exists, but checkpoints are soft ('Flag any outdated information') with no explicit validate-then-proceed gates or error-recovery feedback loops, fitting the 'steps listed but validation gaps; checkpoints implicit' anchor rather than the explicit-checkpoint anchor at 3.	2 / 3
Progressive Disclosure	The ~386-line body is well-sectioned but monolithic — no references/ or scripts/ bundle files exist and everything (artifact schemas, anti-patterns, checklists) is inline, so content that should be separate remains inline, matching the 'some structure but content that should be separate is inline' anchor; it is not a 1 (well-organized, not a nested-reference wall) nor a 3 (no one-level-deep references for a file of this size).	2 / 3
	Total	8 / 12 Passed

Description

75%

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 has an explicit 'Use when' trigger and a distinct, niche-specific scope tied to Conductor's named artifacts, scoring well on completeness and distinctiveness. It is held back by abstract action verbs and jargon-heavy trigger terms rather than concrete operations and natural user phrasing.

Suggestions

Replace abstract verbs ('working with', 'managing', 'understanding') with concrete actions the skill performs (e.g. 'create, update, and validate product.md, tech-stack.md, and workflow.md context artifacts').

Add natural-language trigger variations users would actually say (e.g. 'set up project context', 'keep context docs in sync', 'onboard to a Conductor project') alongside the methodology term.

Tighten the artifact list to the most decisive triggers so the description reads as a clear capability statement rather than a scope enumeration.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete artifacts ('product.md, tech-stack.md, and workflow.md files') and actions ('managing project context artifacts', 'understanding the relationship'), but the verbs are abstract rather than a comprehensive list of concrete operations, matching the 'names domain and some actions' anchor rather than the multiple-specific-actions anchor at 3.	2 / 3
Completeness	It answers both what ('managing project context artifacts', 'understanding the relationship between...files') and when via an explicit 'Use this skill when...' trigger clause, matching the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	It surfaces relevant terms ('context-driven development', 'context artifacts', named .md files) a Conductor user might say, but the language is methodology-internal jargon with limited natural variation, fitting the 'some relevant keywords but missing common variations' anchor rather than broad natural-term coverage at 3.	2 / 3
Distinctiveness Conflict Risk	The trigger is tied to a specific named methodology and product ('Conductor's context-driven development') plus named artifacts, giving it a clear niche unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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
Commit: abece4a

Reviewed: 4 days 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.