CtrlK
BlogDocsLog inGet started
Tessl Logo

team

N coordinated agents on shared task list using tmux-based orchestration

60

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/oh-my-codex/skills/team/SKILL.md

The canonical home for this skill is team in Yeachan-Heo/oh-my-codex

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 a lean, highly operational runbook: sequenced steps with explicit completion criteria, concrete CLI examples for the machine-readable API, and a recovery section keyed to specific failure signals. Its only weaknesses are a few steps that reference other cards or name a verification without giving the command, and slightly over-detailed reasoning-effort precedence rules.

DimensionReasoningScore

Conciseness

The body is dense operational guidance with no padding or explanation of concepts Claude already knows; every section carries runtime-specific facts. Only the agentReasoning precedence rules ('ultra is unsupported and is not an alias for max', explicit-raw-wins hierarchy) could be tightened, keeping it just below anchor 5.

4 / 5

Actionability

Provides copy-paste-ready commands ('omx team api send-message --input ... --json', 'omx team status <name> --json', 'omx team await ... --timeout-ms 30000 --json') and a concrete launch example. Minor gaps: some steps defer to other cards ('The worker card defines ACK, claim, transition...') and verification steps ('Verify shutdown evidence and state cleanup') name the check without the command.

4 / 5

Workflow Clarity

Operational steps 1-8 form a clear sequence with explicit validation checkpoints (run until 'pending=0, in_progress=0, and failed=0', verify shutdown evidence, 'Do not claim completion while workers are still writing'), plus a dedicated recovery section with feedback loops keyed to concrete error signals ('worker_notify_failed', 'ENOENT') and safety guards on destructive pane/state cleanup.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no bundle files, and is organized into six well-labeled sections. Durable detail is explicitly delegated one level deep ('the durable ownership and safety rules remain in templates/AGENTS.md'; 'Read AGENTS.md#durable-runtime-invariants-canonical-ssot') rather than inlined, matching the simple-skill exception for a top score.

5 / 5

Total

18

/

20

Passed

Description

53%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 concise and distinctively identifies a tmux-based multi-agent orchestration capability, but it reads as a mechanism summary rather than a trigger-optimized description. It lacks any 'when to use' guidance and omits the natural phrases (team, parallel agents, workers) a user would actually say.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to run a team of parallel agents, spawn workers, or coordinate multiple agents on a shared task list.'

Enumerate 2-3 concrete actions (e.g. 'launch, dispatch, and monitor N tmux worker sessions') to lift specificity beyond a single mechanism claim.

Include natural synonyms such as 'team', 'multi-agent', and 'worker' alongside 'tmux' so the description matches how users phrase the request.

DimensionReasoningScore

Specificity

The description names a precise domain ('N coordinated agents on shared task list using tmux-based orchestration') with 1-2 concrete capability claims, but does not enumerate the actions performed (launch, dispatch, monitor, shutdown). It is well above anchor 2's generic-domain level but below anchor 4's list of several specific actions.

3 / 5

Completeness

The 'what' is clear (N coordinated agents sharing a task list via tmux orchestration), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps this dimension at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

'tmux', 'agents', and 'shared task list' are relevant keywords, but the phrasing leans technical ('tmux-based orchestration') and common natural variations users would say — 'team', 'parallel workers', 'multi-agent', 'spawn agents' — are missing.

3 / 5

Distinctiveness Conflict Risk

'tmux-based orchestration' and the shared-task-list framing carve a fairly distinct niche with low conflict risk against unrelated skills; only minor overlap with other agent-orchestration skills keeps it below 5.

4 / 5

Total

13

/

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
Yeachan-Heo/oh-my-codex
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.