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-lookup
skills/dld-lookup/SKILL.md
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description with strong trigger guidance and clear distinctiveness. The explicit 'IMPORTANT — use this proactively' clause with the specific '@decision annotations' trigger is excellent for automatic skill selection. The main weakness is that the capabilities could be slightly more specific about what the skill returns or does with the looked-up decisions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (decisions) and lists some actions (look up by ID, tag, code path, keyword), but doesn't describe what happens after lookup or what decisions contain. | 2 / 3 |
Completeness | Clearly answers both what (look up decisions by various criteria) and when (explicitly states 'use this proactively whenever you encounter @decision annotations in code'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'decisions', 'ID', 'tag', 'code path', 'keyword', and critically '@decision annotations' which is a specific trigger term for automatic use. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche - '@decision annotations' is a highly specific trigger that wouldn't conflict with other skills. The combination of decision lookup + code annotation context creates a clear, unique use case. | 3 / 3 |
Total | 11 / 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 well-crafted skill with excellent actionability and workflow clarity. It provides concrete examples, clear query patterns, and explicit decision trees for different scenarios. The proactive usage section is particularly strong with its explicit conflict handling workflow. Minor improvement could come from slightly better progressive disclosure for the query mode details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding unnecessary explanations. It assumes Claude understands concepts like YAML frontmatter, file scanning, and code annotations without over-explaining. | 3 / 3 |
Actionability | Provides concrete query patterns (DL-047, tag:payment-gateway, path:src/billing/vat.ts), specific file paths to check, exact output format with table example, and clear step-by-step behavior for each query mode. | 3 / 3 |
Workflow Clarity | Clear prerequisite check with explicit stop condition, well-defined query modes with distinct patterns, and explicit 4-step process for proactive usage including conflict handling and when to stop vs proceed. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in a single file. For a skill of this length (~80 lines), some content like the detailed query mode examples could potentially be split out, though the current structure is functional. | 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.