context-driven-development

Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structured project documentation.

Quality

41%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/context-driven-development/SKILL.md

The canonical home for this skill is context-driven-development in sickn33/agentic-awesome-skills

Quality

Content

45%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 body is a well-structured but overly long methodology guide with clear workflows and validation checklists, yet it suffers from verbosity, a broken reference, and no real progressive disclosure into bundle files. It reads more like a reference document than a lean skill overview.

Suggestions

Move the per-artifact detail (product.md, tech-stack.md, workflow.md, tracks.md contents and update triggers), the validation checklists, and the anti-patterns into separate reference files, keeping SKILL.md as a concise overview that links to them one level deep.

Fix or remove the dangling reference to resources/implementation-playbook.md (the directory is named 'resources' but no such file or bundle directory exists), and point it at a real file under references/.

Cut conceptual padding — Core Philosophy, Benefits, and the 10-item Best Practices list — to content Claude does not already know, retaining the actionable workflow, directory structure, and checklists.

Dimension	Reasoning	Score
Conciseness	The ~390-line body includes padded conceptual sections (Core Philosophy, Benefits, Common Anti-Patterns, a 10-item Best Practices list) that restate ideas Claude can infer, matching anchor 2 ('Noticeably verbose; several unnecessary explanations or padded sections') rather than the mostly-efficient anchor 3.	2 / 5
Actionability	It offers concrete steps (Run `/conductor:setup`, numbered greenfield/brownfield setup, validation checklists, directory structure) but also abstract items ('Apply relevant best practices and validate outcomes') and a broken reference to resources/implementation-playbook.md, fitting anchor 3 ('Some concrete guidance but incomplete').	3 / 5
Workflow Clarity	The Context → Spec & Plan → Implement workflow is clearly sequenced with an explicit 'Verify Context Before Implementation' step and a Context Validation Checklist, satisfying anchor 4 ('Clear sequence with most checkpoints present'); it stops short of anchor 5's validate→fix→retry feedback loops.	4 / 5
Progressive Disclosure	No bundle files exist, the single reference (resources/implementation-playbook.md) is dangling/broken, and content that belongs in separate files (per-artifact details, checklists) is all inlined, matching anchor 2 ('content that clearly belongs in separate files is inlined; or references are buried').	2 / 5
	Total	11 / 20 Passed

Description

37%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 clearly states the skill's purpose but relies on conceptual, jargon-heavy language with generic actions and no explicit 'when to use' trigger guidance. It is moderately distinct but would benefit from concrete capabilities and natural trigger phrases.

Suggestions

Replace generic verbs ('implementing and maintaining') with concrete actions, e.g. 'Create and update context artifacts (product.md, tech-stack.md, workflow.md) and validate them before each work track.'

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say, e.g. 'Use when setting up or onboarding to a Conductor project, updating context documents, or aligning AI sessions across a team.'

Trim benefit language ('enabling consistent AI interactions and team alignment') to reduce overlap with generic documentation skills and sharpen the niche.

Dimension	Reasoning	Score
Specificity	The description names the domain ('context as a managed artifact') and verbs 'implementing and maintaining', but these are generic actions rather than concrete capabilities, matching anchor 2 ('Names the domain but actions are minimal or generic') rather than the concrete-action bar of anchor 3.	2 / 5
Completeness	It gives a clear 'what' ('Guide for implementing and maintaining context...') but includes no 'Use when...' or equivalent explicit trigger guidance, so per the rubric cap completeness stays at anchor 3 ('Has a clear what but when is missing or only weakly implied').	3 / 5
Trigger Term Quality	Phrases like 'managed artifact', 'structured project documentation' are jargon; 'context' and 'AI interactions' are only weakly natural, and there are no common synonyms or natural user trigger phrases, fitting anchor 2 ('one or two generic keywords; missing the natural phrases users say').	2 / 5
Distinctiveness Conflict Risk	It names a specific niche (managed context for AI-assisted development) but the broad terms 'context', 'AI interactions', 'team alignment', and 'structured project documentation' could overlap with general documentation/onboarding skills, matching anchor 3 ('Somewhat specific but could still overlap with similar skills').	3 / 5
	Total	10 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/context-driven-development/SKILL.md
Commit: 57c135b

Reviewed: 3 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.