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.

Quality

63%

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

60%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-structured with clear workflow phases, maintenance principles, and a validation checklist, but it leans verbose and conceptual rather than executable. Tightening explanatory prose and adding concrete commands/templates would raise actionability and conciseness.

Suggestions

Trim concept-restating prose (e.g. the 'Benefits' section and the explanatory 'Purpose/Contents' lines that describe what each file self-evidently holds) to improve token efficiency.

Add at least one concrete executable artifact or template (e.g. a sample product.md skeleton or a validation command) so guidance is copy-paste ready rather than descriptive.

Move the detailed per-artifact 'Contents' lists into a reference file and keep SKILL.md as an overview to strengthen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is long and restates widely-understood concepts (e.g. explaining that product.md captures vision/goals, or that tech-stack.md documents dependencies) that Claude already knows; sections like 'Benefits' and 'Best Practices' add bulk beyond the actionable core, though it is not severely padded.	3 / 5
Actionability	It lists concrete artifact names and update triggers, but guidance stays at a descriptive level ('Document the rationale', 'Read all context artifacts') with no executable commands or copy-paste examples beyond the directory tree; the steps are high-level hints rather than directly executable instructions.	3 / 5
Workflow Clarity	The Context -> Spec & Plan -> Implement workflow, the validation checklist, and the session continuity sequences are clearly ordered with explicit checkpoints (e.g. 'Flag any outdated information', 'Propose updates before proceeding'); minor gaps in feedback-loop detail keep it just below 5.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with a single inline directory-structure overview and no bundle files referenced; structure is good but the document is monolithic (everything in SKILL.md with no offloading to reference files), which is acceptable for this skill yet not maximal.	4 / 5
	Total	14 / 20 Passed

Description

67%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 answers both what the skill does and when to use it, anchored to a specific methodology and concrete file artifacts. Trigger term coverage and the reliance on a proper-noun product name prevent a top score.

Suggestions

Broaden trigger terms with natural synonyms a user would say (e.g. 'project documentation', 'context files', 'onboarding to a Conductor project') rather than leaning on the 'Conductor' proper noun.

Add an explicit creation/update action (e.g. 'creating and updating context artifacts') to round out the capability list.

Dimension	Reasoning	Score
Specificity	Names the domain ('context-driven development methodology') and several concrete actions ('managing project context artifacts', 'understanding the relationship between product.md, tech-stack.md, and workflow.md'), with minor coverage gaps (no mention of creating/updating artifacts explicitly).	4 / 5
Completeness	Has both a clear 'what' (context-driven methodology and artifact management) and an explicit 'when' via the 'Use this skill when...' clause with multiple triggers; the 'when' could be more specific but is adequately explicit.	4 / 5
Trigger Term Quality	Includes some relevant natural terms ('context-driven development', 'project context artifacts') and concrete file names, but misses common synonyms a user might naturally say and relies on a proper-noun product name 'Conductor' that many users may not vocalize.	3 / 5
Distinctiveness Conflict Risk	The specificity of named artifacts (product.md, tech-stack.md, workflow.md) and the Conductor methodology niche make it mostly distinct from other skills, with only minor overlap risk against general documentation skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/context-driven-development/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.