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-plan
skills/dld-plan/SKILL.md
Discovery
32%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 provides a reasonable overview of the skill's purpose but suffers from missing explicit trigger guidance, which is critical for skill selection. It names the core functionality but lacks the 'Use when...' clause that would help Claude know when to choose this skill over others.
Suggestions
Add a 'Use when...' clause with trigger terms like 'break down feature', 'decision records', 'ADR', 'architecture decisions', or 'feature planning'
Include more specific actions involved in the interactive process (e.g., 'prompts for context, identifies decision points, documents rationale')
Add natural language variations users might say such as 'decompose', 'plan feature', 'document decisions', or 'architecture decision records'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (feature breakdown, decision records) and describes some actions (break down, creates, grouped by tag), but lacks comprehensive detail about what specific actions are involved in the interactive process. | 2 / 3 |
Completeness | Describes what it does (breaks down features into decisions, creates grouped records) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'feature', 'decisions', 'decision records', and 'tag', but missing common variations users might say like 'ADR', 'architecture decisions', 'decompose', or 'planning'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'decision records' and 'shared tag' provides some distinctiveness, but 'break down a feature' is fairly generic and could overlap with planning, task decomposition, or project management skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%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 that efficiently guides Claude through an interactive multi-decision planning workflow. It provides concrete commands, clear sequencing with validation steps, and appropriate user interaction patterns. The skill respects Claude's intelligence while providing all necessary project-specific details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only necessary information without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable bash commands with complete argument syntax, specific example outputs for user prompts, and copy-paste ready script invocations. The printf piping pattern is explicitly documented. | 3 / 3 |
Workflow Clarity | Clear 8-step sequence with explicit checkpoints: prerequisite validation, context gathering, iterative breakdown with user confirmation, and proper sequencing of script calls (next-id before each creation, update-status for superseded, regenerate-index at end). | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections, references to related skills (/dld-init, /dld-implement, /dld-lookup) at appropriate points, and script paths clearly listed upfront. Content is appropriately scoped for a single skill file. | 3 / 3 |
Total | 12 / 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.