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-snapshot
skills/dld-snapshot/SKILL.md
Discovery
50%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 excels at specificity and distinctiveness by naming exact output files and their purposes. However, it critically lacks explicit trigger guidance ('Use when...'), which caps its usefulness for skill selection. Adding natural user-facing trigger terms would significantly improve discoverability.
Suggestions
Add a 'Use when...' clause specifying triggers like 'when the user asks to summarize decisions', 'generate decision documentation', or 'create decision snapshots'
Include natural language variations users might say: 'decision summary', 'ADR overview', 'document architecture decisions', 'decision history'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate SNAPSHOT.md', 'detailed decision reference', 'OVERVIEW.md', 'narrative synthesis with diagrams', and specifies the source 'from the decision log'. | 3 / 3 |
Completeness | Clearly describes WHAT it 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 | Includes some relevant terms like 'SNAPSHOT.md', 'OVERVIEW.md', 'decision log', and 'diagrams', but missing common variations users might say like 'summarize decisions', 'decision summary', 'document decisions', or 'ADR'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche with distinct file names (SNAPSHOT.md, OVERVIEW.md) and clear domain (decision log processing); unlikely to conflict with other documentation or generation skills. | 3 / 3 |
Total | 9 / 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 skill with excellent actionability and workflow clarity. The templates are comprehensive and the step sequence is logical with proper prerequisite checks. The main weakness is verbosity in the guidelines sections, which could be more concise or split into reference files for better progressive disclosure.
Suggestions
Consider moving the detailed 'Narrative guidelines' and 'Diagram guidelines' sections to a separate GUIDELINES.md reference file to reduce the main skill's length
Tighten explanatory prose like 'This is fundamentally different from SNAPSHOT.md' - Claude can infer the difference from the templates themselves
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant explanations (e.g., explaining what OVERVIEW.md is 'fundamentally different' and describing it as 'the document you'd give a new team member'). The templates and guidelines are thorough but could be tightened in places. | 2 / 3 |
Actionability | Provides fully executable bash commands, complete markdown templates with exact formatting, and specific rules for content organization. The templates are copy-paste ready with clear placeholders and the guidelines are concrete and specific. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit prerequisites check, validation of decision states before proceeding, and logical progression from data collection through generation to state update. Each step has clear success criteria. | 3 / 3 |
Progressive Disclosure | The skill is self-contained with good section organization, but the lengthy templates and guidelines create a wall of text. The narrative and diagram guidelines could potentially be split into separate reference files for cleaner main skill flow. | 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.