ntm-orchestrator

Spawn and orchestrate an ntm multi-agent session from within Claude Code. Plans work distribution, sends targeted prompts, monitors progress via polling, handles coordination through Agent Mail, collects results, and synthesizes a summary. Knows when to ask for human direction. Keywords: spawn agents, ntm session, orchestrate, multi-agent, fan out work.

Quality

80%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./SKILL.md

Quality

Content

77%

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

This is a highly actionable and well-structured orchestration skill with excellent workflow clarity and concrete executable guidance. The multi-phase approach with explicit validation checkpoints and escalation triggers demonstrates sophisticated design. The main weakness is length - while the complexity may justify it, some sections (token budget, anti-patterns repetition) could be trimmed or externalized to improve token efficiency.

Suggestions

Consider moving the Token Budget table and Anti-Patterns table to a reference file (e.g., references/orchestrator-reference.md) to reduce main skill length

The escalation matrix 'NEVER Escalate' section partially duplicates guidance from earlier sections - consider consolidating

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but includes some redundancy (e.g., anti-patterns table repeats information from earlier sections, token budget table may be unnecessary detail). However, most content is necessary for a complex orchestration skill and assumes Claude's competence with the underlying tools.	2 / 3
Actionability	Excellent actionability with executable bash commands, specific JSON schemas, complete command tables with exact flags, and concrete code examples throughout. Every phase has copy-paste ready commands and clear instructions.	3 / 3
Workflow Clarity	Outstanding workflow clarity with 7 clearly numbered phases, explicit validation checkpoints (preflight validation, quality gates, health checks), feedback loops for error recovery, and detailed escalation matrix. The monitoring loop includes specific cadence tables and intervention patterns.	3 / 3
Progressive Disclosure	References external files appropriately (templates/, patterns/, references/) but the main document is quite long (~500+ lines). Some content like the full escalation matrix and token budget could potentially be moved to reference files. The structure is good but the skill itself is monolithic.	2 / 3
	Total	10 / 12 Passed

Description

82%

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

This is a well-crafted description with strong specificity and distinctive terminology. It clearly explains the capabilities and includes helpful keywords. The main weakness is the absence of an explicit 'Use when...' clause that would help Claude know exactly when to select this skill over others.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to distribute work across multiple agents, requests parallel task execution, or mentions ntm/multi-agent workflows.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Plans work distribution, sends targeted prompts, monitors progress via polling, handles coordination through Agent Mail, collects results, and synthesizes a summary.' These are clear, actionable capabilities.	3 / 3
Completeness	Clearly answers 'what does this do' with detailed capabilities, but lacks an explicit 'Use when...' clause. The keywords help but don't constitute explicit trigger guidance for when Claude should select this skill.	2 / 3
Trigger Term Quality	Includes explicit keywords section with natural terms users would say: 'spawn agents, ntm session, orchestrate, multi-agent, fan out work.' These cover common variations of how users might request this functionality.	3 / 3
Distinctiveness Conflict Risk	Very specific niche around 'ntm multi-agent session' and 'Agent Mail' coordination. The domain-specific terminology (ntm, Agent Mail) and clear focus on multi-agent orchestration makes it unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (671 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: emptyaltoidstin/ntm-orchestrator
Commit: cf5a710

Reviewed: 3 months 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.