swarm-planner

[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

The content is highly actionable, with concrete formats, a worked example, a complete template, and a ready-to-use review prompt. Its weaknesses are a broken step-numbering scheme that muddies the workflow, repetition of the clarification-question guidance, and a monolithic structure with no progressive disclosure despite its length.

Suggestions

Fix the process heading numbering (the two '### 4.' sections should be 4 and 5, with Subagent Review renumbered to 6) to remove sequencing ambiguity.

Consolidate the repeated 'ask clarifying questions' guidance into a single authoritative section to tighten conciseness.

Extract the large plan template into a referenced file (e.g., references/plan-template.md) and link to it from a concise overview section to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient process guidance with no padding about concepts Claude already knows, but it repeats the 'ask clarifying questions' guidance across three separate sections (Principle 3, Step 1a, Step 3) and repeats full template task blocks for T1/T2/T3 that could be expressed once, so it could be tightened past level 2 toward level 3.	2 / 3
Actionability	It provides a concrete task dependency format with a worked T1–T7 example, a fully specified plan template, and a copy-paste-ready subagent review prompt — concrete, specific, and directly usable guidance rather than vague direction, matching the level-3 anchor (adapted for an instruction skill).	3 / 3
Workflow Clarity	The process is sequenced and includes an explicit review-then-revise checkpoint, but the heading numbering is broken (two consecutive '### 4.' sections for Create Plan and Save Plan, with Subagent Review mislabeled as 5), which introduces real sequencing ambiguity and keeps it below level 3.	2 / 3
Progressive Disclosure	Sections are well-organized with headers, but the skill is a monolithic single file with no bundle references and a large inline plan template that could be split out; with no one-level-deep references it does not reach the level-3 anchor, and at ~170 lines it exceeds the under-50-line simple-skill exception.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 clearly states what the skill does but omits any explicit 'when to use it' trigger guidance and leans on a single action statement with modifiers rather than enumerating concrete capabilities. Trigger terms are present but incomplete and the niche overlaps with general planning/Plan Mode skills.

Suggestions

Add an explicit 'Use when…' clause naming the natural trigger situations (e.g., 'Use when the user asks to plan a multi-step implementation for parallel agents or wants dependency-aware task scheduling').

List concrete capabilities the skill produces beyond a single action (e.g., 'generates dependency graphs, parallel execution waves, and acceptance criteria for each task') to lift specificity.

Replace the meta tag '[EXPLICIT INVOCATION ONLY]' inside the description with user-facing trigger keywords to improve trigger term quality.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('Creates dependency-aware implementation plans optimized for parallel multi-agent execution') and its domain, but describes a single action with modifiers rather than listing multiple specific concrete actions, so it stops short of the level-3 anchor.	2 / 3
Completeness	The 'what' is clearly stated, but there is no 'Use when…' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains some natural terms a user might say ('implementation plans', 'parallel multi-agent execution'), but lacks common variations and an explicit trigger clause; the '[EXPLICIT INVOCATION ONLY]' tag is an invocation mechanism rather than a user-facing trigger term, placing it at level 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	The parallel multi-agent planning niche is somewhat specific, but 'implementation plans' is generic and the skill itself notes it can run inside Plan Mode, indicating real overlap with general planning skills; it is not clearly distinct enough for level 3.	2 / 3
	Total	8 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: am-will/codex-skills
Commit: e343715

Reviewed: 14 days 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.