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".
66
79%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/memory-manage/SKILL.mdQuality
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 provides explicit trigger terms (including multilingual ones) and covers both what and when, which are strong points. However, the actual capabilities are described at a high level ('unified memory management', 'documentation generation') without specifying concrete actions, and the phrase 'interactive routing' is vague jargon. The description would benefit from more specific action verbs describing what the skill actually does.
Suggestions
Replace vague phrases 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 analysis.'
Clarify what 'documentation generation' means specifically—what kind of docs, from what inputs, in what format—to reduce overlap risk with other doc-generation skills.
| 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? What kind of docs are generated? | 2 / 3 |
Completeness | Answers both 'what' (CLAUDE.md updates, documentation generation, interactive routing) and 'when' (explicit trigger phrases listed with 'Triggers on'). The trigger clause serves as a clear 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Explicitly lists multiple natural trigger terms including 'memory manage', 'update claude', 'update memory', 'generate docs', and even Chinese equivalents '更新记忆', '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 term 'unified' suggests it consolidates multiple functions, which could increase overlap risk. | 2 / 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 router skill with strong actionability and clear workflow sequencing. The routing logic, interactive question flows, and configuration tables are concrete and executable. The main weakness is verbosity — the ASCII diagram, full AskUserQuestion JSON blocks, and bilingual descriptions inflate the token cost, and the lack of verifiable bundle files makes it hard to fully credit progressive disclosure.
Suggestions
Trim the ASCII architecture diagram to a simple bullet list of routes; the routing table already conveys the same information more precisely.
Consider summarizing the AskUserQuestion payloads more concisely (e.g., as a table of question→options→route) rather than showing full JSON structures inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ASCII architecture diagram and the interactive Q&A blocks with full AskUserQuestion JSON payloads add significant bulk. The routing table and auto-route rules are useful but the bilingual labels and repeated option descriptions could be tightened. Some content (e.g., explaining what CLAUDE.md is in option descriptions) is unnecessary for Claude. | 2 / 3 |
Actionability | The skill provides concrete routing rules with priority order, specific AskUserQuestion payloads with exact parameter structures, direct dispatch examples with input→output mappings, and precise configuration tables for tool fallback, parameters, and batching thresholds. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 3-step flow (Parse → Interactive Assessment → Execute) is clearly sequenced with explicit decision points and branching logic. Error handling is tabulated with resolutions. Each routing path has clear validation (ambiguous input falls to interactive, missing path triggers Q3). The skill correctly delegates execution validation to phase docs. | 3 / 3 |
Progressive Disclosure | The skill references 5 phase documents with clear links and purpose descriptions, which is good progressive disclosure design. However, no bundle files were provided, so we cannot verify these references exist. The SKILL.md itself is quite long (~180 lines) with the full interactive flow inline rather than summarized, and the architecture diagram could be omitted or simplified. | 2 / 3 |
Total | 10 / 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
5ff5e86
- 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.