catalan-adobe/memory-triage
Review Claude Code auto memory accumulated during a task and promote valuable findings to shared project config (CLAUDE.md, .claude/rules/, or global CLAUDE.md). Use this skill when finishing a branch, completing a task, wrapping up work, or anytime you want to review what Claude learned and decide what the team should know. Also use when the Stop hook reminds you about pending memory entries. Triggers on "triage memory", "review memory", "promote memory", "memory triage", "what did we learn", "clean up memory", "share learnings", "anything worth keeping", or when the user asks about knowledge accumulated during a session.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 strong skill description that clearly defines its purpose (reviewing and promoting Claude Code auto memory), provides explicit trigger conditions and natural language keywords, and occupies a distinct niche. It effectively communicates both what the skill does and when it should be selected, with comprehensive trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: review auto memory, promote findings to shared project config (CLAUDE.md, .claude/rules/, or global CLAUDE.md). Also specifies the concrete destinations and the workflow context (finishing a branch, completing a task). | 3 / 3 |
Completeness | Clearly answers both 'what' (review auto memory and promote valuable findings to shared config files) and 'when' (finishing a branch, completing a task, wrapping up work, Stop hook reminder, plus explicit trigger phrases). Has an explicit 'Use this skill when...' clause. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'triage memory', 'review memory', 'promote memory', 'what did we learn', 'clean up memory', 'share learnings', 'anything worth keeping', plus contextual triggers like finishing a branch or completing a task. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on Claude Code's auto memory triage and promotion workflow. The specific terminology around memory entries, CLAUDE.md, .claude/rules/, and the memory triage concept make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 an excellent skill that demonstrates strong content quality across all dimensions. The workflow is well-structured with clear steps, validation points, and safety constraints (read-only on memory files, secret redaction, no automatic commits). The progressive disclosure is well-executed with appropriate delegation to reference files for detailed examples and output formats.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a clear purpose, there's no explanation of concepts Claude already knows, and the instructions are direct without padding or unnecessary context. | 3 / 3 |
Actionability | Provides concrete, executable steps: specific shell commands for path resolution, exact encoding rules, specific file paths, clear decision criteria, and explicit tool usage (Edit tool, Write tool). The guidance is specific enough to act on immediately. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit checkpoints: early termination if no memory exists, secret redaction before presenting, user confirmation before writing, and a final summary report. The feedback loop for 'show filtered' and batch decisions adds robustness. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview workflow in the main file while appropriately delegating detailed examples to reference files (references/CLASSIFICATION.md, references/OUTPUT-FORMATS.md). References are one level deep and clearly signaled with descriptive link text. | 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.
Reviewed
Table of Contents