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".

Quality

53%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/memory-capture/SKILL.md

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill demonstrates a reasonable architectural design for routing between two memory capture modes, but suffers from significant verbosity — the same routing logic is represented in an ASCII diagram, a routing table, a data flow diagram, and prose, all saying the same thing. The actual execution details are deferred to phase files that aren't provided, making the skill a verbose router description rather than a complete, actionable guide. Error handling is present but lacks validation checkpoints.

Suggestions

Eliminate redundant representations: keep only the auto-route rules table and remove the ASCII architecture diagram and data flow diagram, which repeat the same information.

Since bundle files aren't provided, either inline the essential execution steps from phases/01-compact.md and phases/02-tips.md, or ensure those files exist and contain the detailed instructions.

Add a validation checkpoint after structured text generation and before core_memory import (e.g., verify the text is non-empty and well-formed).

Remove explanatory prose like 'Unified memory capture skill that routes to two execution modes' — Claude can infer this from the structure itself.

Dimension	Reasoning	Score
Conciseness	The skill is excessively verbose with multiple redundant representations of the same routing logic (ASCII diagram, auto-route table, data flow diagram, and prose). The architecture overview diagram, the duplicate phase reference tables, and the data flow section all repeat the same information. Much of this (routing concepts, MCP tool calling patterns) is knowledge Claude already has.	1 / 3
Actionability	The routing rules table and the core_memory call provide some concrete guidance, but the actual execution logic is deferred entirely to phase files (phases/01-compact.md, phases/02-tips.md) which are not provided. The skill tells Claude what to do at a high level but lacks the detailed executable instructions for either mode.	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 validation checkpoints between steps — for example, no verification that the structured text was correctly generated before calling core_memory import, and the retry logic is mentioned but not detailed.	2 / 3
Progressive Disclosure	The skill correctly references phase files (phases/01-compact.md, phases/02-tips.md) for detailed execution, which is good progressive disclosure structure. However, no bundle files are provided, so we cannot verify these references resolve to actual content. Additionally, the SKILL.md itself contains too much redundant inline content (the same routing logic shown 3-4 different ways) that should either be trimmed or moved to a reference file.	2 / 3
	Total	7 / 12 Passed

Description

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 multilingual keywords and occupies a distinct niche, but falls short on explaining what the skill concretely does. The phrase 'unified memory capture with routing' is somewhat abstract and doesn't clearly convey the specific actions performed (e.g., summarizing session history, extracting key learnings, saving to a file). Adding concrete action descriptions would significantly improve clarity.

Suggestions

Expand the 'what' portion with concrete actions, e.g., 'Summarizes and compresses the current session into a memory file, or extracts quick tips and learnings for future reference.'

Add a 'Use when...' clause that describes the situational context, e.g., 'Use when the user wants to save session progress, compress conversation history, or capture reusable tips before ending a session.'

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 partially compensates but the lack of a clear 'Use when...' clause with contextual guidance limits it.	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 specific multilingual triggers creates a clear niche that is unlikely to conflict with other skills. The routing concept and specific terminology make it quite distinctive.	3 / 3
	Total	10 / 12 Passed

Validation

90%

Warnings & errors only

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: 07491b0

Reviewed: 20 days ago

Table of Contents

Discovery Implementation Validation

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.