memory-capture
Unified memory capture with routing - session compact or quick tips. Triggers on "memory capture", "compact session", "save session", "quick tip", "memory tips", "记录", "压缩会话".
71
64%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/memory-capture/SKILL.mdQuality
Discovery
72%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 good trigger term coverage including bilingual terms and is distinctive enough to avoid conflicts with other skills. However, it lacks specificity about what the skill concretely does—'unified memory capture with routing' is somewhat abstract, and the actual actions (compacting sessions, saving tips) are not explained in enough detail for Claude to confidently select this skill over alternatives.
Suggestions
Expand the 'what' portion to describe concrete actions, e.g., 'Captures and compresses session context into persistent memory notes, or saves quick reusable tips from conversations.'
Add a 'Use when...' clause that explains the scenarios beyond just listing trigger words, e.g., 'Use when the user wants to save key learnings from a session, compress conversation history for future reference, or store quick tips for later retrieval.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('memory capture with routing') and mentions two specific actions ('session compact' and 'quick tips'), but doesn't elaborate on what these actions concretely entail—e.g., what is being compacted, what format tips are saved in, etc. | 2 / 3 |
Completeness | The 'what' is partially addressed (memory capture with routing to session compact or quick tips), and the 'when' is addressed via explicit trigger terms. However, the 'what' is weak—it doesn't clearly explain what the skill actually does beyond naming categories. The trigger list substitutes for a proper 'Use when...' clause but doesn't explain the use cases. | 2 / 3 |
Trigger Term Quality | Provides a solid list of natural trigger terms including both English and Chinese variations: 'memory capture', 'compact session', 'save session', 'quick tip', 'memory tips', '记录', '压缩会话'. These are terms users would naturally say when wanting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'memory capture', 'compact session', and 'quick tips' with routing logic creates a fairly distinct niche. The specific trigger terms and bilingual keywords make it unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has strong structural organization and progressive disclosure, with a clear routing mechanism and well-signaled references to phase documents. Its main weaknesses are moderate verbosity (redundant diagrams conveying the same information) and the lack of validation checkpoints in the workflow. The actionability is decent at the routing level but relies heavily on external phase files for actual execution detail.
Suggestions
Remove one of the redundant diagrams (Architecture Overview ASCII art or Data Flow) since they convey essentially the same routing logic, saving significant tokens.
Add a validation checkpoint after structured text generation and before core_memory import, e.g., 'Verify the generated text contains required sections before importing.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ASCII architecture diagram and data flow diagram are somewhat redundant with each other and with the textual explanation. The skill over-explains the routing concept that could be conveyed more tersely. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The routing rules table and input examples are concrete and useful. However, the actual execution logic is deferred entirely to phase files (01-compact.md, 02-tips.md), so the skill itself provides incomplete guidance. The core_memory call is a good concrete example, but most operational detail is absent from this file. | 2 / 3 |
Workflow Clarity | The three-step workflow (parse/route → execute phase → save) is clearly sequenced, and error handling is documented in a table. However, there are no explicit validation checkpoints—e.g., no step to verify the structured text was generated correctly before importing, and no feedback loop for the core_memory import beyond 'retry once.' | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure: the SKILL.md serves as a clear router/overview with well-signaled one-level-deep references to phases/01-compact.md and phases/02-tips.md. Content is appropriately split between overview and detailed phase documents, with clear navigation via linked tables. | 3 / 3 |
Total | 9 / 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
0f8e801
- 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.