hivemind-memory

Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.

Quality

66%

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 ./harnesses/claude-code/skills/hivemind-memory/SKILL.md

Quality

Content

65%

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

The body is a dense, actionable CLI reference with clear search workflow guidance and good section organization. Its main weaknesses are a destructive-operation gap in validation checkpoints, repeated warnings, and a monolithic inline structure with no progressive disclosure despite its length.

Suggestions

Add validation/verification steps before destructive commands (e.g., 'skillify push --dry-run first; only --force after confirming the diff') to raise workflow clarity above 2.

De-duplicate the 'do NOT quote subcommands together' warning (state it once) and consider a shared prefix note to tighten conciseness.

Move the large skillify/embeddings command catalogs into reference files linked from SKILL.md to improve progressive disclosure for this 95-line skill.

Dimension	Reasoning	Score
Conciseness	The body is a lean command reference with no concept explanations Claude already knows, but the 'do NOT quote subcommands together' warning is repeated across two sections and command prefixes are restated on every line, so it is 'mostly efficient but could be tightened' (anchor 2) rather than every-token-earns-its-place (anchor 3).	2 / 3
Actionability	It provides concrete, copy-paste-ready commands throughout (e.g., 'hivemind skillify pull', 'grep -r "keyword" ~/.deeplake/memory/'), and the '<path>' placeholder is explicitly justified ('or check the session context for the resolved path'), matching anchor 3 ('Fully executable code/commands; copy-paste ready').	3 / 3
Workflow Clarity	The 'How to Search' section gives a clear index→summary→raw-JSONL sequence with a retry limit, but destructive operations such as 'skillify push --force' (overwrites) and 'skillify unpull' (removes skills) have no validation/verification checkpoints, which per the scoring notes caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized with headers, but the skill is over 50 lines with all content inline and no external references signaled; large command catalogs (skillify, embeddings) that could live in separate files are inline, fitting anchor 2 ('Some structure... content that should be separate is inline') rather than anchor 3's split-with-navigation.	2 / 3
	Total	9 / 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 clearly answers both what the skill is and when to use it via an explicit trigger, and benefits from a named product niche. It is weakened by limited concrete action specificity, missing common trigger-term variations, and overlap risk with built-in memory.

Suggestions

Add concrete capabilities to the description (e.g., 'search past sessions, recall team decisions, browse session summaries') to lift specificity from 2 to 3.

Broaden trigger terms with natural phrasings users actually say, such as 'remember', 'recall past sessions', or 'what did the team decide'.

Sharpen distinctiveness by leading with the Hivemind/Activeloop scope so it is less likely to be confused with built-in memory.

Dimension	Reasoning	Score
Specificity	Names the domain ('Global team and org memory powered by Activeloop') and one action ('check BOTH built-in memory AND Hivemind memory'), but does not list multiple concrete capabilities, matching anchor 2 ('Names domain and some actions, but not comprehensive') rather than anchor 3's multi-action list.	2 / 3
Completeness	It states what ('Global team and org memory powered by Activeloop') and an explicit when trigger ('when recalling information'), satisfying anchor 3 ('Clearly answers both what AND when with explicit triggers'); it is above anchor 2 because the when clause is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes some natural terms a user might say ('team and org memory', 'recalling information'), but misses common variations like 'remember', 'past sessions', or 'what did we discuss', fitting anchor 2 ('Some relevant keywords but missing common variations').	2 / 3
Distinctiveness Conflict Risk	The named product niche (Activeloop/Hivemind) is fairly distinct, but 'memory' and 'recalling information' overlap with built-in memory skills (which the description itself references), matching anchor 2 ('Somewhat specific but could still overlap with similar skills') rather than anchor 3's conflict-free niche.	2 / 3
	Total	9 / 12 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: activeloopai/hivemind
Path: harnesses/claude-code/skills/hivemind-memory/SKILL.md
Commit: a587b30

Reviewed: about 11 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.