memory-management

Persist SEO/GEO campaign context across Claude sessions with automatic hot-list, active work, and archive tiers. 项目记忆/跨会话

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/memory-management/SKILL.md

Quality

Content

71%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 content is a well-structured, actionable overview with excellent progressive disclosure to real reference files and solid validation/confirmation gates, with the main weakness being Quick Start prompt padding and deferred core workflows.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's domain competence, but the Quick Start section enumerates 12+ near-identical prompt variants and several long validation checklists that could be tightened without losing meaning.	3 / 5
Actionability	It gives concrete, executable guidance — specific file paths, numeric thresholds (80 lines max, 90+ days, 3+ refs), a 5-step lookup flow with a markdown example, and explicit hygiene checks — though the detailed promotion/demotion and update procedures are deferred to references.	4 / 5
Workflow Clarity	The Context Lookup Flow and Memory Hygiene Checks are clearly sequenced, and the Validation Checklists plus user-confirmation gates on destructive archival/wiki compilation provide most checkpoints; the core promotion/demotion workflows live in referenced files rather than being sequenced inline, leaving minor gaps.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references to real bundle files (hot-cache-template.md, glossary-template.md, promotion-demotion-rules.md, update-triggers-integration.md, examples.md), with content appropriately split and easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

58%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 and distinguishes a clear SEO/GEO campaign-memory niche, but it omits explicit 'when to use' trigger guidance and the natural conversational phrases a user would actually say, both of which live elsewhere in the frontmatter.

Suggestions

Append an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when the user says remember this, save SEO data, or asks for project status') so the description self-contains the when-to-use signal.

Add one or two conversational trigger phrases ('remember this', 'what did we decide') to the description text itself rather than relying solely on the separate triggers metadata.

Replace the abstract 'active work' phrasing with a concrete capability verb (e.g., 'surfaces active work') to remove the last vague term.

Dimension	Reasoning	Score
Specificity	The description names the SEO/GEO domain and several concrete capabilities — 'Persist... campaign context across Claude sessions', 'automatic hot-list', 'active work', and 'archive tiers' — listing multiple specific actions with only minor abstractness in 'active work'.	4 / 5
Completeness	It clearly answers 'what' (persist campaign context across sessions with tiered storage) but provides no 'Use when...' clause or equivalent explicit trigger guidance within the description itself, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	It contains relevant domain keywords ('SEO/GEO campaign context', 'Claude sessions', 'hot-list', 'archive') but is missing the natural conversational phrases users actually say ('remember this', 'project status'); the natural-language triggers live in a separate frontmatter field rather than the description.	3 / 5
Distinctiveness Conflict Risk	The 'SEO/GEO campaign context' qualifier and the three-tier (hot-list/active/archive) framing carve a clear niche distinct from generic memory skills, with only minor overlap risk against closely related project-memory skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: MODSetter/SurfSense
Path: .cursor/skills/memory-management/SKILL.md
Commit: d96e29d

Reviewed: 8 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.