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

76%

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

85%

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

The skill body is well-structured, highly actionable, with strong validation feedback loops and sound progressive disclosure to real local reference files; its main weakness is length with some duplication between the Quick Start and Instructions sections.

Suggestions

Consolidate the duplicated material between 'Quick Start', 'What This Skill Does', and 'Instructions' to reduce verbosity while keeping the actionable specifics.

Clarify which links are local bundle references versus broader-repo paths (e.g. skill-contract.md, state-model.md, CONNECTORS.md) so navigation depth is unambiguous.

Dimension	Reasoning	Score
Conciseness	Per-section content is dense and free of generic concept explanations Claude already knows, but the ~275-line body has notable duplication (Quick Start prompts overlap with the Instructions section; the 11-item 'What This Skill Does' recapitulates later 'Instructions') that could be tightened.	2 / 3
Actionability	Concrete file paths, specific thresholds (80 lines, 25KB, 90 days, 3+ refs), executable commands (/seo:wiki-lint [--fix], 'Refresh wiki index'), and a copy-paste-ready save-results filename format give fully actionable guidance.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced (Context Lookup Flow Steps 1-5, Memory Hygiene Checks 1-4) with a dedicated Validation Checkpoints section and feedback loops (count -> flag -> recommend archival) for destructive/batch operations.	3 / 3
Progressive Disclosure	The body is an overview that signals one-level-deep local references (promotion-demotion-rules.md, update-triggers-integration.md, examples.md, templates) with clear 'See ... for ...' cues; these files exist in ./references/ and content is appropriately split.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 distinct, clearly conveying the tiered campaign-memory concept, but it omits an explicit 'Use when...' trigger clause and relies partly on internal jargon over natural user phrasing.

Suggestions

Append an explicit trigger clause, e.g. 'Use when reviewing or archiving campaign memory, or when the user asks to save findings, remember this, or check project status.'

Replace internal taxonomy ('hot-list, active work, and archive tiers') with more natural user-facing terms or pair them with common phrasings like 'project memory' and 'remember this'.

Dimension	Reasoning	Score
Specificity	Names the SEO/GEO campaign-memory domain and concrete structures ('automatic hot-list, active work, and archive tiers', 'across Claude sessions'), listing multiple specific capabilities rather than vague abstractions.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 2.	2 / 3
Trigger Term Quality	Contains relevant terms ('SEO/GEO campaign context', '项目记忆') but leans on internal taxonomy ('hot-list', 'archive tiers') that users would not naturally say, and omits common natural phrasings like 'remember this' or 'project memory' within the description itself.	2 / 3
Distinctiveness Conflict Risk	The SEO/GEO + cross-session tiered-memory scoping carves a clear niche with distinct triggers, unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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: 3b319ce

Reviewed: about 13 hours 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.