CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hivemind-goals

Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, 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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

A well-executed operational skill: copy-paste commands for every core operation, path conventions treated as the source of truth, and honest edge-case handling (soft-close semantics, goal_id rename rejection). The main gaps are the under-specified edit operation, the absence of any post-write verification step, and some repetition around the path-encoding rule.

Suggestions

Add a concrete example to "Edit a goal description" (e.g. a Read/Edit sequence on an actual goal path) so every operation has the same level of executable detail.

Add a verification step after create/capture (e.g. re-run `hivemind goal list --mine` or `ls` on the status folder to confirm the row landed) to close the validation gap in the workflows.

State the path-encoding rule once (in Path conventions or Constraints) and reference it elsewhere instead of repeating it three times, and consider moving the parked-task capture/resume procedures (sections 1a/1b) into a reference file to slim the main body.

DimensionReasoningScore

Conciseness

The body is dominated by commands, path templates, and tight examples rather than concept explanations, matching the anchor for efficient content with minor trims available. It is not 5 because the path-is-source-of-truth rule is stated three times, the `mv` command is repeated nearly verbatim, and emphasis caps ("LEARN THESE", "DO NOT") pad a few sections.

4 / 5

Actionability

Nearly every operation ships a copy-paste command (`ls`, `mv`, `rm`, `hivemind goal add/get/list`, `uuidgen`) plus a fully worked capture example, but section 3 ("Edit a goal description") contains only a comment block with no concrete command or example. This matches the anchor for mostly executable guidance with minor gaps; not 5 because editing a goal is a common case left without a worked example.

4 / 5

Workflow Clarity

Create and resume flows are numbered with dependencies resolved up front (`hivemind whoami` → uuidgen → write) and include an ambiguity checkpoint ("If ambiguous, show the candidates and ask"); `rm` is explicitly defused as a soft-close so the destructive-op cap does not apply. Matches the anchor for clear sequence with minor validation gaps — no post-write verification step (e.g. re-list to confirm the row landed); not 3 because sequences and some checkpoints are explicitly present.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is self-contained, with clean sections (When to use / Path conventions / File body format / Operations / Constraints / Team visibility) and no buried or nested references. Matches the anchor for good structure with minor organization gaps; not 5 because at ~136 lines it exceeds the simple-skill case and inlines two related but separable procedures (goals vs. parked-task capture/resume) that could live in a reference file.

4 / 5

Total

16

/

20

Passed

Description

87%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.

A strong description: concrete capabilities, explicit and natural trigger guidance covering both goals and tasks, and a clearly named mechanism. The main weakness is trigger breadth — claiming "any actionable work item" and "fix X" makes it likely to fire on generic coding or reminder requests that belong to other skills.

Suggestions

Narrow the task-side triggers or add a boundary qualifier (e.g. "use when the user wants to persist/track a work item in the team goal system") to reduce conflict with ordinary coding and reminder requests.

Mention one or two more capabilities in the 'what' clause (e.g. close, reassign, resume parked tasks with stored context) so the description matches the skill's actual operation set.

Trim the legacy-CLI explanation ("replaced the legacy hivemind tasks CLI and now covers both") to a shorter clause — it is context, not capability, and adds tokens without adding trigger value.

DimensionReasoningScore

Specificity

"Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/" names the domain, mechanism, and several concrete actions, matching the anchor for several specific actions with minor gaps. It is not 5 because it omits operations the skill actually supports (close, reassign, resume parked tasks); not 3 because it gives more than 1-2 actions and a concrete path-based mechanism.

4 / 5

Completeness

Explicitly answers both: what ("Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/") and when ("Use whenever the user mentions a goal... ALSO use when the user says 'task', 'todo'...") with concrete trigger phrases. Matches the anchor for clearly answering both; nothing significant is missing.

5 / 5

Trigger Term Quality

Covers "goal, objective, target, milestone" plus "task", "todo", "work item", "remind me to", "fix X", and "track progress" — comprehensive natural-language synonyms users would actually say. This matches the anchor for comprehensive coverage including synonyms; only trivially below would be a few missing variants, which do not apply here.

5 / 5

Distinctiveness Conflict Risk

The niche is distinct (Deeplake goal table, explicitly replaces the legacy `hivemind tasks` CLI), but the trigger sweep claims "any actionable work item", "remind me to", and "fix X" — language that overlaps ordinary coding, todo-list, and reminder skills. This matches the anchor for somewhat-specific-but-still-overlapping; not 4 because the deliberate breadth creates more than minor overlap risk, not 2 because the target system is clearly named.

3 / 5

Total

17

/

20

Passed

Validation

100%

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/hivemind-goals/SKILL.md

Reviewed

Table of Contents

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.