hivemind-goals

Create, track and update team goals + KPIs via the Deeplake virtual filesystem at memory/goal/ and memory/kpi/. Use whenever the user mentions a goal, objective, KPI, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.

Quality

96%

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

Quality

Content

100%

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

Tight, concrete, and well-structured: it assumes Claude's competence, gives fully executable tool calls and a resumable-context template, and organizes everything into clear sections without unnecessary external references. No meaningful weaknesses to address.

Dimension	Reasoning	Score
Conciseness	The body is lean and action-dense with no re-explanation of concepts Claude knows; the few parenthetical asides (provenance flag, no status-move tools) earn their place by preventing wrong actions rather than padding.	3 / 3
Actionability	Gives exact tool signatures with parameters and return values (e.g. hivemind_goal_add({ text }) returns goal_id), concrete path templates, and a copy-paste-ready "Start here / Files / Branch / Run / Why" example block.	3 / 3
Workflow Clarity	Two clearly numbered, sequenced workflows (goal creation, task resume) with a confirm step and a "What NOT to do" guardrail; the operations are non-destructive so missing validation loops does not cap the score.	3 / 3
Progressive Disclosure	A short, single-file skill well-organized into clear sections (Tools, Workflow, Capture, Resume, What NOT to do) with no need for external references; per the simple-skill note this earns a 3.	3 / 3
	Total	12 / 12 Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states concrete capabilities and provides rich, explicit trigger terms covering both goals and tasks. Its main weakness is conflict risk: the broad extension into generic actionable terms ("task", "todo", "fix X") could overlap with other skills.

Suggestions

Tighten the trigger surface for tasks so it only fires for task capture within the Hivemind/goals context (e.g. "remind me to track/fix X as a goal") rather than bare "task"/"todo"/"fix X", reducing overlap with general task-management and coding skills.

Lead with the distinct Hivemind + openclaw framing so the niche is anchored before the generic task triggers, making it less likely to bind on a plain coding request.

Consider dropping or scoping "fix X" — it is the most generic term and the most likely to collide with code-fixing skills.

Dimension	Reasoning	Score
Specificity	"Create, track, and read team goals + KPIs" lists multiple concrete actions, matching the score-3 anchor of enumerating several specific capabilities.	3 / 3
Completeness	Explicitly answers both what ("Create, track, and read team goals + KPIs via Hivemind") and when ("Use whenever the user mentions…"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Broad natural-term coverage — "goal, objective, KPI, target, milestone" plus "task, todo, work item, remind me to, fix X" — terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The Hivemind-goals niche is distinct, but the "ALSO use when the user says task, todo, fix X, or any actionable work item" expansion into generic action terms overlaps with task/todo/coding skills, so it could trigger for the wrong skill.	2 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: activeloopai/hivemind
Path: harnesses/claude-code/skills/hivemind-goals/SKILL.md
Commit: a587b30

Reviewed: about 10 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.