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

55%

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/skills/context-driven-development/SKILL.md

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

Quality

Content

56%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 content is well-structured and actionable with concrete artifacts, commands, and checklists, but it is noticeably verbose and keeps material inline that would benefit from being split into referenced bundle files, including one broken reference.

Suggestions

Trim padding that Claude already knows: drop or drastically shorten the Benefits section, the 10-item Best Practices list, and the IDE/Git-hooks/CI-CD integration suggestions.

Replace the vague top 'Instructions' block ('Apply relevant best practices and validate outcomes') with concrete first steps, e.g. 'Read conductor/index.md, then run /conductor:setup'.

Move the detailed per-artifact reference into a bundle file under references/ and fix the broken `resources/implementation-playbook.md` reference so progressive disclosure is genuinely one level deep.

Dimension	Reasoning	Score
Conciseness	At ~390 lines the body contains several padded sections that explain things Claude already knows — the Benefits block (team alignment, AI consistency, institutional memory), the 10-item Best Practices list, and generic IDE/Git-hooks/CI-CD integration advice — matching the 'noticeably verbose; several unnecessary explanations or padded sections' anchor.	2 / 5
Actionability	Provides concrete, specific guidance for an instruction-only skill: named artifacts, a `/conductor:setup` command, a real directory tree, numbered greenfield/brownfield and session steps, and validation checklists, with only minor vague patches (the top 'Instructions' block).	4 / 5
Workflow Clarity	Multi-step processes (Context->Spec->Plan->Implement phases, greenfield/brownfield setup, session start/end) are clearly sequenced with a dedicated 'Verify Context Before Implementation' checkpoint and a Context Validation Checklist; no destructive/batch feedback loop is required, so it sits just below the explicit validate->fix->retry anchor at 5.	4 / 5
Progressive Disclosure	The body is well-sectioned but content that belongs in separate files (detailed artifact specs, the playbook) is inlined, and the single reference to `resources/implementation-playbook.md` is clearly signaled yet points to a file that does not exist (no references/scripts/assets bundles present).	3 / 5
	Total	13 / 20 Passed

Description

53%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 is abstract and lacks an explicit 'when to use' trigger clause, which caps completeness. Keywords are present but not the most natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., setting up Conductor, onboarding to an existing Conductor project, deciding when to update context docs).

Replace abstract phrasing like 'managed artifact alongside code' with concrete actions users would say, such as 'manage project context files (product.md, tech-stack.md, tracks.md)'.

Include natural synonyms users actually say, like 'context management', 'AI session continuity', or 'project context'.

Dimension	Reasoning	Score
Specificity	Names the domain ('context as a managed artifact alongside code') and two actions ('implementing and maintaining') but they remain fairly abstract with no concrete file or tool operations, matching the 'domain + 1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Provides a clear 'what' (guide for implementing/maintaining context artifacts) but no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes relevant keywords like 'context', 'AI interactions', and 'project documentation', but 'managed artifact alongside code' is jargon rather than natural user phrasing and common synonyms (context management, AI sessions) are missing.	3 / 5
Distinctiveness Conflict Risk	The framing of context as a managed first-class artifact is a fairly distinct niche with only minor overlap risk against generic documentation or project-management skills.	4 / 5
	Total	13 / 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/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.