CtrlK
BlogDocsLog inGet started
Tessl Logo

hivemind

Orchestrate free opencode workers from Claude Code to cut token costs. Use when delegating grunt work to a single worker or a parallel swarm (scout/coder/tester) with worktree isolation, benchmarking against opencode, or when the user says "spawn a worker", "swarm", "delegate to opencode", or "/oc".

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

The canonical home for this skill is hivemind in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 exemplary orchestration skill: concise, fully actionable, with sequenced workflows and validation checkpoints, and a well-structured overview that delegates detail to real one-level-deep bundle files. No dimension falls short of the top anchor.

DimensionReasoningScore

Conciseness

Lean and dense throughout: prerequisites, invocation contract, and flows are stated as executable facts with no concept lectures or padding, and every section (Prerequisites, Windows notes, Known limits) earns its tokens.

5 / 5

Actionability

Fully executable guidance — the exact invocation contract, returned JSON shape, failure stages, server-management behavior, and concrete CLI commands ("npm i -g opencode-ai", "git worktree add ../<repo>-wt-N -b swarm/N") are copy-paste ready and cover common cases.

5 / 5

Workflow Clarity

The swarm flow is a numbered sequence with explicit validation checkpoints ("Review every diff yourself", "YOU are the only merger") and a feedback-loop fallback ladder (retry once -> inline with [orchestrator-sourced] -> abandon), satisfying the batch/destructive validation requirement.

5 / 5

Progressive Disclosure

Clear overview with a Components table pointing to one-level-deep real bundle files (oc-worker.mjs, oc-status.mjs, assets/commands/, assets/agents/), all verified to exist, with well-signaled navigation and no nested references.

5 / 5

Total

20

/

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.

The description is concrete, third-person, and explicitly pairs what-it-does with natural-language triggers, hitting all the completeness and distinctiveness anchors. It sits just below top on specificity and trigger breadth due to a few missing action/synonym details.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Orchestrate free opencode workers", "parallel swarm (scout/coder/tester) with worktree isolation", "benchmarking against opencode" — with only minor gaps in coverage (e.g., merge/review is implied rather than stated).

4 / 5

Completeness

Clearly answers both what (orchestrate free opencode workers to cut token costs) and when via an explicit "Use when delegating... or when the user says..." clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say ("spawn a worker", "swarm", "delegate to opencode", "/oc") alongside "grunt work" and "swarm"; a few common synonyms are missing, keeping it just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (opencode worker orchestration) with distinct triggers ("/oc", "swarm", "delegate to opencode") that are unlikely to fire for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-skills
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.