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".
62
53%
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 and occupies a distinct niche, but falls short on specificity of what the skill actually does (e.g., what does 'routing' mean here, what does compacting produce?) and lacks an explicit 'Use when...' clause. Adding concrete action descriptions and explicit usage guidance would significantly improve skill selection accuracy.
Suggestions
Add an explicit 'Use when...' clause describing the situations that should trigger this skill, e.g., 'Use when the user wants to save key takeaways from a session or compress conversation history into memory.'
Expand the capability description with concrete actions, e.g., 'Compresses session conversations into structured memory summaries and extracts quick tips for future reference. Routes captured content to appropriate memory storage.'
| 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 - session compact or quick tips') and trigger terms serve as implicit 'when' guidance, but there is no explicit 'Use when...' clause explaining the circumstances under which Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes a solid set of natural trigger terms users would say: 'compact session', 'save session', 'quick tip', 'memory tips', 'memory capture', plus multilingual support with '记录' and '压缩会话'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'memory capture', 'session compact', and 'quick tips' with specific trigger terms creates a clear niche that is unlikely to conflict with other skills. The multilingual triggers further narrow the scope. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
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 good structural intent with clear routing logic and error handling, but suffers from significant verbosity — the same two-mode routing concept is expressed through an ASCII diagram, a routing table, a data flow diagram, and prose, all saying essentially the same thing. The actual execution details are deferred to phase files that aren't provided, making the skill a well-organized but incomplete router description. Trimming redundant representations and ensuring phase files exist would substantially improve quality.
Suggestions
Remove redundant representations: pick ONE of the ASCII diagram, auto-route table, or data flow diagram — not all three. The routing table alone is sufficient.
Add a validation step after structured text generation and before core_memory import (e.g., verify text is non-empty and well-formed) to close the feedback loop gap.
Include the phase files (phases/01-compact.md, phases/02-tips.md) in the bundle, or inline minimal but complete execution logic for each mode so the skill is self-contained enough to be actionable.
Remove the 'Architecture Overview' ASCII diagram entirely — it restates what the routing table and data flow already convey, consuming tokens without adding value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose with multiple redundant representations of the same routing logic (ASCII diagram, auto-route table, data flow diagram, and prose). The architecture overview diagram, execution flow, and data flow sections all convey essentially the same information. Much of this (what routing is, how to parse input) is knowledge Claude already has. | 1 / 3 |
Actionability | The core_memory MCP call is concrete and executable, and the routing rules table is specific. However, the actual execution logic is deferred to phase files (01-compact.md, 02-tips.md) which are not provided, making the skill incomplete on its own. The routing rules are clear but the actual work is elsewhere. | 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 — no verification that the structured text was correctly generated before importing, and the retry logic for core_memory failure is mentioned but not detailed with a feedback loop. | 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. However, no bundle files were provided, so we cannot verify these references exist. The main SKILL.md itself contains too much redundant inline content (multiple diagrams and tables repeating the same routing information) that could be tightened rather than split. | 2 / 3 |
Total | 7 / 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.