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

56%

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

Quality

Content

63%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, genuinely instructional process guide with concrete artifacts, update triggers, and validation checkpoints — its actionability and workflow clarity are solid. Its weaknesses are token efficiency (several promotional/boilerplate sections that teach Claude nothing new) and the absence of any progressive disclosure: a 400-line monolith whose per-artifact references and checklists should live in separate files.

Suggestions

Cut the 'Benefits', 'Core Philosophy', and 'Instructions' sections (or compress them to 2-3 lines each) — they explain concepts Claude already infers and add ~80 lines of non-instructional padding.

Move the per-artifact deep-dives (product.md through tracks.md contents/update triggers) and the Context Validation Checklist into reference files (e.g., references/artifacts.md, references/validation-checklist.md) linked from a concise overview, keeping SKILL.md under ~150 lines.

Add verification steps to the synchronization and session-end flows (e.g., how to confirm tech-stack.md matches actual dependencies after a merge), matching the explicit validation already present in the pre-track workflow.

Dimension	Reasoning	Score
Conciseness	The artifact relationships, maintenance principles, and checklists are tight and instructional, but several sections pad the token budget: the promotional 'Benefits' section, the conceptual 'Core Philosophy', generic 'Instructions' boilerplate ('Apply relevant best practices and validate outcomes'), and redundant 'Do not use this skill when'/'Limitations' disclaimers. This matches 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	As an instruction-only skill it gives concrete guidance: a full inventory of the five artifacts with per-artifact update triggers, numbered greenfield/brownfield procedures anchored to the /conductor:setup command, and explicit session start/end/interruption sequences. It is not 5 because most steps are directives without commands or examples (e.g., 'Flag any outdated information' has no how).	4 / 5
Workflow Clarity	The Context → Spec & Plan → Implement workflow is clearly sequenced, and validation is explicit ('Verify Context Before Implementation', a four-part validation checklist, and interruption-recovery steps). It falls short of 5 because the four phase definitions are single lines with no error-recovery loops, and synchronization tasks ('Keep Artifacts Synchronized') describe updates without any verification step.	4 / 5
Progressive Disclosure	No bundle files exist, and the ~400-line body inlines everything: the per-artifact deep-dives, the validation checklists, and the directory-structure reference are exactly the material that belongs in one-level-deep reference files. Section headers are well-organized, so it is above anchor 2's 'minimal structure', but the monolithic single-file layout matches 'content that should be separate is inline'.	3 / 5
	Total	14 / 20 Passed

Description

50%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 communicates a coherent concept but stays at an abstract marketing register: it states a clear 'what' with no 'when', omits the Conductor tool name that makes the skill distinct, and uses no natural user trigger phrases. All dimensions land at the midpoint because nothing is wrong in kind, yet nothing is concrete enough to rise above anchor 3.

Suggestions

Add an explicit 'Use when...' clause with concrete triggers, e.g. 'Use when setting up or maintaining a Conductor project, updating context artifacts like product.md or tech-stack.md, or onboarding teammates to an AI-assisted codebase.'

Replace abstract phrasing ('managed artifact', 'team alignment') with the skill's concrete deliverables: the five context artifacts (product.md, product-guidelines.md, tech-stack.md, workflow.md, tracks.md) and the /conductor:setup command.

Include natural synonyms users would say — 'context files', 'project context', 'Conductor setup' — to improve trigger-term coverage and reduce overlap with generic documentation skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("context as a managed artifact alongside code") and two actions ("implementing and maintaining"), but these remain abstract; it lists only two generic actions rather than the several specific actions of anchor 4.	3 / 5
Completeness	It clearly answers 'what' (a guide for implementing and maintaining context artifacts) but contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines; it is not 2 because the 'what' is stated clearly rather than vaguely.	3 / 5
Trigger Term Quality	Terms like "context", "AI interactions", and "structured project documentation" are relevant, but common natural variations users would actually say — "Conductor", "context files", "project onboarding", "product.md" — are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Context-Driven Development" with "structured project documentation" is somewhat specific but overlaps with documentation, project-init, and onboarding skills; the tool that defines this niche (Conductor) is never named, so it cannot reach anchor 4's 'mostly distinct'.	3 / 5
	Total	12 / 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: sickn33/agentic-awesome-skills
Path: skills/context-driven-development/SKILL.md
Commit: 7b534bc

Reviewed: 5 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.