memory-management

AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.

Quality

67%

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 ./.agents/skills/memory-management/SKILL.md

Quality

Content

51%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 concise, actionable command reference with copy-paste bash examples, but it lacks any sequenced workflow or validation for its destructive/batch operations and its reference tables point to non-existent or mis-pathed files. Fixing the broken paths and adding a short validated workflow would substantially raise quality.

Suggestions

Correct the reference paths: point the Scripts table at 'scripts/memory-backup.sh' and 'scripts/memory-consolidate.sh' (the real locations) and either create 'docs/hnsw.md' and 'docs/memory-schema.md' or remove those reference rows.

Add a short sequenced workflow with a validation checkpoint around destructive/batch operations, e.g. 'list --namespace' to confirm the target key before 'memory delete', and verify an export file exists after 'memory export'.

Remove the duplicated frontmatter restated in the Purpose and When to Trigger/Skip sections to recover tokens, keeping a single concise statement of intent.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with no concept over-explanation, but it restates the frontmatter three times — the Purpose section verbatim repeats the description and the 'When to Trigger'/'When to Skip' sections re-list the same Use/Skip clauses — so several tokens do not earn their place and could be tightened.	3 / 5
Actionability	Each command is a complete, copy-paste-ready bash invocation (e.g. 'npx @claude-flow/cli memory store --key ... --namespace patterns') with worked examples for the common cases (store, search, get, list), but delete/init/stats/export lack example blocks and no prerequisites (e.g. init or install) are stated, leaving minor gaps.	4 / 5
Workflow Clarity	The body is a command catalog rather than a sequenced workflow; the only implicit sequence is the vague Best Practices list ('Check memory for existing patterns before starting', 'Store successful patterns after completion'), with no validation checkpoints for the destructive 'delete' or batch 'export' operations, fitting the anchor for a rough sequence with many gaps and absent validation.	2 / 5
Progressive Disclosure	Structure is well organized with clearly signaled Scripts and References tables, but the referenced paths are broken: 'docs/hnsw.md' and 'docs/memory-schema.md' do not exist, and the scripts are cited at '.agents/scripts/...' while the actual bundle lives at 'scripts/...', so navigation does not actually resolve.	3 / 5
	Total	12 / 20 Passed

Description

83%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 strong: it cleanly answers both what the skill does and when to use it, with a useful skip clause and mostly natural trigger phrases. Its main weakness is a few vague capability phrases and light overlap risk with generic learning/memory skills.

Dimension	Reasoning	Score
Specificity	Names the domain (AgentDB, HNSW vector search) and several concrete capabilities (store successful patterns, semantic search, semantic lookup, sharing knowledge), though entries like 'learning from previous tasks' and 'building knowledge base' remain somewhat abstract, leaving minor gaps rather than full comprehensive coverage.	4 / 5
Completeness	It explicitly states both what it does ('AgentDB memory system with HNSW vector search. Provides... pattern retrieval, persistent storage, and semantic search') and when to use it via a concrete 'Use when:' trigger list plus a 'Skip when:' clause, matching the anchor that requires clear what-and-when with concrete triggers.	5 / 5
Trigger Term Quality	The 'Use when' clause supplies several natural phrases a user might say ('store successful patterns', 'searching for similar solutions', 'learning from previous tasks', 'sharing knowledge between agents'), but mixes in jargon ('semantic lookup of past work', HNSW) and misses common synonyms, so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	The AgentDB/HNSW framing and 'sharing knowledge between agents' carve a recognizable niche, but broader triggers like 'learning from previous tasks' and 'building knowledge base' could overlap with other memory or learning skills, giving minor rather than minimal conflict risk.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/memory-management/SKILL.md
Commit: b14c79e

Reviewed: 3 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.