CtrlK
BlogDocsLog inGet started
Tessl Logo

context-driven-development

Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a `conductor/` directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves. Use when setting up a project, creating or updating product docs, managing a tech stack file, defining development workflows, tracking work units, onboarding to an existing codebase, or running project scaffolding.

70

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is concise and well-structured with a single clearly signaled reference file, but it relies on abstract best-practice directives rather than concrete, executable steps and lacks an explicit workflow with validation checkpoints.

Suggestions

Add a concrete scaffold/extract/sync workflow with explicit commands or file-creation steps and a validation checkpoint (e.g., a consistency-checklist invocation) to lift workflow_clarity to 3.

Replace abstract directives with executable specifics — show the directory layout and a minimal product.md/tech-stack.md template inline or via the existing artifact-templates.md reference.

Include a brief validation/feedback loop (validate artifacts -> fix inconsistencies -> proceed) before major implementation work to satisfy the destructive/batch-operation guidance.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and avoids explaining what context artifacts are; every section earns its place with no padded background.

3 / 3

Actionability

Guidance is mostly directional ('Always read relevant artifacts before starting work', 'Make incremental context changes') rather than executable commands or concrete templates, leaving key specifics to the referenced files.

2 / 3

Workflow Clarity

'When to Use' and 'Best Practices' give sequence signals but there is no explicit multi-step workflow with validation checkpoints for the scaffold/extract/sync operations described in the description.

2 / 3

Progressive Disclosure

A concise overview with a clearly signaled one-level-deep reference to references/details.md (and artifact-templates.md exists in the bundle), keeping the main file navigable.

3 / 3

Total

10

/

12

Passed

Description

100%

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 is specific, third-person, and answers both 'what' and 'when' with an explicit Use-when clause and natural trigger terms. It is concise yet comprehensive and distinguishes itself via the conductor/ artifact vocabulary.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as 'Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves'.

3 / 3

Completeness

Explicitly states what the skill does (creates/maintains context artifacts, scaffolds, extracts, validates, synchronizes) and when via an explicit 'Use when' clause enumerating trigger scenarios.

3 / 3

Trigger Term Quality

Covers natural user phrasings including 'setting up a project, creating or updating product docs, managing a tech stack file, defining development workflows, tracking work units, onboarding to an existing codebase'.

3 / 3

Distinctiveness Conflict Risk

The conductor/ directory and named artifacts (product.md, tech-stack.md, workflow.md, tracks.md) carve a clear niche unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
wshobson/agents
Reviewed

Table of Contents

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.