CtrlK
BlogDocsLog inGet started
Tessl Logo

memory-navigation

记忆系统三入口路由(search_evidence / graph_resolve / list_recent)决策树 + 噪音控制 + 加载时机。F188 Phase F (AC-F6) 配套 skill。 Use when: 没先验、压缩后回顾、"我记得最近讨论过 X"、search_evidence 反复 low-hit。 Not for: 已有精确 anchor 直接 Read;代码符号查 Grep/LSP。 Output: 选定入口 + 噪音控制参数 + 进入对应 MCP 工具。

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

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

The body is an efficient, actionable routing guide — a copy-ready decision tree with concrete MCP parameters and a nudge-driven feedback loop. Structure is clean with well-signaled one-level references; only minor conciseness and navigation polish keep it from full marks.

Suggestions

Trim the 'When to load' list since the same triggers already appear in frontmatter, or keep only the novel hook-trigger ('compact' event) not already covered.

Consider moving the single-source-of-truth pointer (../.cat-cafe-shared-refs/memory-routing-partial.md) into a dedicated 'References' section near the bottom instead of the opening blockquote for clearer navigation.

The 7-tool family catalog is useful for cross-reference but could be collapsed to just the three entry points plus a one-line pointer to where the full family is documented.

DimensionReasoningScore

Conciseness

Lean and free of over-explanation of known concepts, but the 'When to load' section echoes frontmatter triggers and the 7-tool catalog adds minor redundancy that could be trimmed.

4 / 5

Actionability

Concrete, copy-paste-ready MCP calls with parameters (graph_resolve(anchor, depth=1), list_recent(scope="all", since="7d"), relations=["wikilink","doc_link"]) covering the common routing cases.

5 / 5

Workflow Clarity

The decision tree is a clearly sequenced routing flow with an explicit feedback loop (🧭 Memory navigation nudge → switch to graph/recent); operation is read-only so the destructive-validation cap does not apply.

5 / 5

Progressive Disclosure

Well-organized sections with one-level-deep, clearly signaled references (partial.md as single source of truth, CLAUDE.md, spec doc); no bundle files exist to verify, and the single-source pointer sits in a top blockquote rather than a dedicated navigation section.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 is specific, trigger-rich, complete, and well-bounded — it names concrete MCP entry points, lists natural trigger phrases, and distinguishes itself from Read/Grep/LSP. Uses acceptable imperative 'Use when' phrasing rather than penalized first/second person.

DimensionReasoningScore

Specificity

Names three concrete entry points (search_evidence / graph_resolve / list_recent) plus decision tree, noise control, and load-timing actions — multiple specific concrete actions with comprehensive coverage.

5 / 5

Completeness

Explicitly answers what (三入口路由决策树 + 噪音控制 + 加载时机) and when (Use when triggers), plus Not for and Output clauses.

5 / 5

Trigger Term Quality

Natural phrases a user would say ('我记得最近讨论过 X', 'cold start', '扫一眼最近', '找不到 anchor') with synonyms and variations covering the memory-navigation need.

5 / 5

Distinctiveness Conflict Risk

Clear niche (memory entry-point routing) with explicit Not for boundaries (direct Read, Grep/LSP) minimizing conflict with adjacent skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
zts212653/clowder-ai
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.