dld-kit/dld
Decision-Linked Development (DLD) — a workflow for recording, linking, and maintaining development decisions alongside code. Skills for planning, recording, implementing, auditing, and documenting decisions via @decision annotations.
68
Quality
68%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
dld-implement
skills/dld-implement/SKILL.md
Discovery
42%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 effectively communicates specific actions (code changes, annotations, status updates) but fails to provide explicit trigger guidance for when Claude should select this skill. The lack of a 'Use when...' clause significantly limits its utility in a multi-skill environment where Claude needs clear selection criteria.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to implement a proposed decision, apply an ADR, or mark a decision as accepted/implemented'
Include natural trigger terms users might say: 'apply decision', 'implement proposal', 'ADR implementation', 'decision tracking'
Clarify the domain context - specify if this relates to Architecture Decision Records (ADRs) or a specific decision-tracking system
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Makes code changes', 'adds @decision annotations', and 'updates decision status'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains some relevant terms like 'decisions', 'implement', 'annotations', but missing common variations users might say like 'apply decision', 'execute proposal', 'mark decision complete', or 'ADR'. | 2 / 3 |
Distinctiveness Conflict Risk | The '@decision annotations' and 'decision status' terms provide some distinctiveness, but 'Makes code changes' is generic and could overlap with many coding skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability and workflow clarity. It provides concrete commands, clear validation steps, and thoughtful guidance on edge cases like refining decisions during implementation. The only minor weakness is that the content is fairly long and could benefit from splitting some detailed sections into referenced files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence. No unnecessary explanations of basic concepts—it jumps straight into actionable steps with clear script paths and structured workflows. | 3 / 3 |
Actionability | Provides fully concrete guidance with specific bash commands, exact annotation syntax in multiple languages, YAML examples for references, and copy-paste ready code snippets throughout. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (7 numbered steps), explicit validation checkpoint (step 5 verify-annotations.sh), and decision points for batch vs. single implementation with clear criteria. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's somewhat monolithic. The annotation guidelines and batch implementation logic could potentially be split into separate reference files for a cleaner overview. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.