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-init
skills/dld-init/SKILL.md
Discovery
67%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 description excels at specificity and distinctiveness by naming exact artifacts created (dld.config.yaml, decisions/, INDEX.md). However, it lacks an explicit 'Use when...' clause and could benefit from additional trigger terms that users might naturally say when wanting to set up DLD in a project.
Suggestions
Add a 'Use when...' clause with trigger terms like 'setup DLD', 'initialize decision tracking', 'start new DLD project', or 'configure decision-linked development'
Include common synonyms users might say: 'setup', 'initialize', 'init', 'configure', 'start tracking decisions'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Creates dld.config.yaml, the decisions/ directory, and INDEX.md' - these are precise, named artifacts that will be created. | 3 / 3 |
Completeness | Clearly answers 'what' (creates config file, directory, and INDEX.md) but lacks an explicit 'Use when...' clause. The 'Run once per project' hints at when but doesn't provide explicit trigger guidance. | 2 / 3 |
Trigger Term Quality | Includes 'Bootstrap', 'DLD', 'Decision-Linked Development', and 'repository' as keywords, but missing common variations users might say like 'setup', 'initialize', 'init', 'new project', or 'configure'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche - DLD bootstrapping with named files (dld.config.yaml, decisions/, INDEX.md) creates a clear, distinct trigger that's unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%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-structured initialization skill with clear sequential steps and executable commands. The workflow is easy to follow with good conditional handling for different project types. Main weakness is some verbosity in explanations and the large inline CLAUDE.md block that inflates token usage.
Suggestions
Move the CLAUDE.md instruction block to a template file (e.g., templates/claude-md-dld-block.md) and reference it instead of including inline
Trim explanatory text like 'Flat is the default and right for most projects' - Claude can convey this in the question itself
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity, such as explaining what flat vs namespaced means when Claude could infer this, and the lengthy CLAUDE.md block that could be referenced from a template file instead of inline. | 2 / 3 |
Actionability | Provides fully executable bash commands with concrete examples for both flat and namespaced modes. Each step has specific scripts to run with exact syntax, making it copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 7-step sequence with explicit prerequisites check (git repo, no existing config). Each step is numbered with clear dependencies (step 3 reads from step 2's output). Conditional branching for namespaced vs flat is well-defined. | 3 / 3 |
Progressive Disclosure | The skill is reasonably organized with clear sections, but the large CLAUDE.md block inline could be a separate template file. The practices manifest content is appropriately handled inline since it's generated dynamically. | 2 / 3 |
Total | 10 / 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.