hivemind-memory

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

Quality

68%

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/codex/skills/deeplake-memory/SKILL.md

Quality

Content

75%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 command reference with a clear search workflow and dry-run safeguards on destructive operations, held back slightly by repeated caveats, unresolved path placeholders, and an inline-heavy structure.

Suggestions

Resolve the auth command path concretely (or give a one-line resolution snippet) so org-management commands are copy-paste ready instead of carrying '<path>' placeholders.

Add an explicit validate-then-proceed note for member removal and invite operations (e.g. run with --dry-run or confirm role before executing).

De-duplicate the 'Each argument is separate' caveat and consider moving the lengthy skillify flag catalog to a separate reference file.

Dimension	Reasoning	Score
Conciseness	The body is a lean command reference with little padding, though the 'Each argument is separate — do NOT quote subcommands together' note is repeated in two sections and a few explanatory sentences could be trimmed.	4 / 5
Actionability	Provides many concrete, executable commands, but several org-management commands use unresolved path placeholders ('<path>', '<AUTH_CMD>') that prevent fully copy-paste-ready execution despite the resolve-path guidance.	4 / 5
Workflow Clarity	The 'How to Search' section gives a clear numbered sequence and destructive/batch operations (push, unpull, remove) expose --dry-run validation flags, though there is no explicit validate-then-proceed feedback loop for the member-removal and invite flows.	4 / 5
Progressive Disclosure	Content is well-organized into clear sections with no nested references and no bundle files to navigate; the only gap is that the long skillify and org-management command catalogs remain fully inlined rather than being split into dedicated reference files.	4 / 5
	Total	16 / 20 Passed

Description

62%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 clearly identifies a distinct niche and pairs a 'what' with a 'when' trigger, but the capability list is thin and the natural-language trigger vocabulary is narrow.

Suggestions

Add a concrete 'Use when...' trigger clause listing natural phrases users say, e.g. 'Use when recalling past sessions, what a team discussed, or prior project decisions.'

Broaden trigger-term coverage with synonyms like 'remember', 'recall', 'prior conversations', and 'session history'.

Name one or two more concrete capabilities (e.g. searching, summarizing, or sharing memory) to lift specificity above a single recall-check action.

Dimension	Reasoning	Score
Specificity	Names the domain ('Global team and org memory powered by Activeloop') and one concrete action ('check BOTH built-in memory AND Hivemind memory when recalling information'), but coverage is limited to a single recall-check action rather than a comprehensive set of capabilities.	3 / 5
Completeness	States what it is ('Global team and org memory') and provides an explicit when-trigger ('when recalling information'); the trigger is present but could be more specific about the situations that call for it.	4 / 5
Trigger Term Quality	Includes relevant keywords ('memory', 'recalling information', 'team and org memory') but misses common natural variations and synonyms a user would actually say ('remember', 'what did we discuss', 'recall').	3 / 5
Distinctiveness Conflict Risk	The 'Hivemind memory' / 'Activeloop' niche is clearly distinct from generic skills, with only minor overlap risk against built-in memory tooling (which it explicitly addresses by saying check both).	4 / 5
	Total	14 / 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: activeloopai/hivemind
Path: harnesses/codex/skills/deeplake-memory/SKILL.md
Commit: 551d366

Reviewed: 4 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.