memory-manage
Unified memory management - CLAUDE.md updates and documentation generation with interactive routing. Triggers on "memory manage", "update claude", "update memory", "generate docs", "更新记忆", "生成文档".
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%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 has strong trigger term coverage including bilingual terms and an explicit 'Triggers on' clause, which is a notable strength. However, the 'what' portion is somewhat vague—'unified memory management' and 'interactive routing' are abstract concepts that don't clearly convey specific concrete actions. The description would benefit from more specific action verbs describing what the skill actually does.
Suggestions
Replace abstract terms like 'unified memory management' and 'interactive routing' with concrete actions (e.g., 'Adds, updates, and removes entries in CLAUDE.md; generates project documentation from codebase')
Clarify what 'interactive routing' means in practice—does it prompt the user to choose between options? Describe the actual behavior.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (memory management, CLAUDE.md updates, documentation generation) and mentions 'interactive routing', but doesn't list specific concrete actions beyond general categories. What does 'unified memory management' actually do in practice? | 2 / 3 |
Completeness | Answers both 'what' (unified memory management, CLAUDE.md updates, documentation generation with interactive routing) and 'when' (explicitly lists trigger phrases with 'Triggers on...'). The trigger guidance is explicit and clear. | 3 / 3 |
Trigger Term Quality | Explicitly lists multiple natural trigger phrases including 'memory manage', 'update claude', 'update memory', 'generate docs', and even Chinese equivalents '更新记忆' and '生成文档'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The CLAUDE.md focus and specific trigger terms help distinguish it, but 'documentation generation' and 'memory management' are broad enough to potentially overlap with other documentation or memory-related skills. The 'unified' qualifier is vague. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%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 router skill with strong actionability and clear workflow sequencing. The routing logic is concrete with priority-ordered rules, specific examples, and complete interactive question payloads. The main weakness is moderate verbosity — the AskUserQuestion JSON blocks and ASCII diagram could be tightened — but overall the content is functional and well-organized with appropriate progressive disclosure to phase documents.
Suggestions
Condense the AskUserQuestion blocks into a more compact format (e.g., a table of question → options → route) rather than full JSON payloads, since Claude can construct the actual API calls from concise specifications.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ASCII architecture diagram and interactive flow details are somewhat verbose, but most content is functional. The bilingual (Chinese/English) labels add some overhead but serve the target audience. Some tables (like batching thresholds) earn their place, but the extensive AskUserQuestion blocks with full JSON could be more compact. | 2 / 3 |
Actionability | The skill provides concrete routing rules with priority order, specific input-to-action examples, exact AskUserQuestion payloads with options, clear parameter tables, and explicit phase document references. Claude can execute this routing logic directly from the content. | 3 / 3 |
Workflow Clarity | The 3-step flow (Parse → Interactive Assessment → Execute) is clearly sequenced with explicit routing rules, decision trees for each branch, and error handling table. The skill correctly delegates validation to phase docs and includes a confirmation step rule. For a router skill, this is well-structured with clear checkpoints. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure pattern: the SKILL.md serves as a router/overview that references 5 phase documents for detailed execution logic, with clear one-level-deep references in a well-organized table. The 'read on-demand' rule explicitly prevents loading unnecessary content. However, no bundle files were provided to verify the referenced phase docs exist. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
227244f
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.