swarm-planner

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

Quality

52%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/swarm-planner/SKILL.md

Quality

Discovery

40%

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 carves out a clear and distinctive niche around multi-agent parallel planning, which is its strongest aspect. However, it lacks a 'Use when...' clause entirely, and the capability description is a single high-level action rather than a list of concrete sub-actions. The trigger terms lean technical and miss natural user language variations.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user explicitly requests a parallelized implementation plan, task decomposition for multiple agents, or dependency-ordered work breakdown.'

List more concrete actions, e.g., 'Analyzes task dependencies, generates directed acyclic task graphs, identifies parallelizable work streams, and produces ordered implementation plans for multi-agent execution.'

Include natural language trigger terms users might say, such as 'break down tasks', 'plan the work', 'task decomposition', 'parallelize implementation', or 'work distribution'.

Dimension	Reasoning	Score
Specificity	Names the domain (implementation planning) and mentions key qualifiers (dependency-aware, parallel multi-agent execution), but doesn't list multiple concrete actions—it's a single high-level action 'creates plans' without detailing sub-steps like analyzing dependencies, generating task graphs, or assigning agent roles.	2 / 3
Completeness	The 'what' is partially addressed (creates dependency-aware implementation plans), but there is no 'when' clause at all—no 'Use when...' or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also somewhat vague, this scores a 1. The '[EXPLICIT INVOCATION ONLY]' tag implies invocation context but doesn't explain when to use it.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'implementation plans', 'parallel', 'multi-agent', and 'dependency-aware', but these are somewhat technical. Missing natural user phrases like 'break down tasks', 'plan work', 'parallelize', 'task decomposition', or 'work distribution'. The '[EXPLICIT INVOCATION ONLY]' tag helps but isn't a natural trigger term.	2 / 3
Distinctiveness Conflict Risk	The combination of 'dependency-aware', 'implementation plans', and 'parallel multi-agent execution' creates a very specific niche that is unlikely to conflict with other skills. The '[EXPLICIT INVOCATION ONLY]' tag further reduces accidental triggering.	3 / 3
	Total	8 / 12 Passed

Implementation

64%

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

This is a solid, actionable skill for creating dependency-aware implementation plans. Its main strengths are the concrete task dependency format, complete plan template, and the subagent review feedback loop. Weaknesses include some redundancy across steps (clarification questions mentioned in three places), a numbering error (two step 4s), and the lengthy inline template that could benefit from being extracted to a separate file.

Suggestions

Fix the duplicate step numbering (two steps labeled '4') and consolidate the repeated clarification/question guidance from Core Principles, Step 1a, and Step 3 into a single clear instruction.

Extract the Plan Template into a separate file (e.g., PLAN_TEMPLATE.md) and reference it from the main skill to improve progressive disclosure and reduce inline bulk.

Add an explicit validation checkpoint between the Research/Documentation phase and the Plan Creation phase to ensure sufficient context has been gathered before planning begins.

Dimension	Reasoning	Score
Conciseness	The skill has some redundancy - step 3 (STOP and Request User Input) largely repeats the 'Ask Questions' core principle and step 1a. The plan template is quite verbose with placeholder fields like 'log' and 'files edited/created' that pad the token count. However, most content is purposeful and not explaining things Claude already knows.	2 / 3
Actionability	The skill provides a concrete task dependency format with a clear example, a complete plan template with markdown structure, specific subagent review prompt text, and explicit file naming conventions. The guidance is specific and copy-paste ready.	3 / 3
Workflow Clarity	The multi-step process is clearly sequenced (Research → Documentation → Clarification → Plan → Save → Review), and includes a feedback loop via subagent review. However, there are two steps labeled '4' (Create Plan and Save Plan), and the validation checkpoints between steps are implicit rather than explicit - there's no clear gate between research and planning phases.	2 / 3
Progressive Disclosure	The content is reasonably structured with clear sections, but the full plan template is inlined rather than referenced as a separate file, making the skill quite long. The template could be in a separate PLAN_TEMPLATE.md file with a reference. No external file references are used despite the skill being over 100 lines.	2 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: am-will/codex-skills
Commit: ca2c3b3

Reviewed: 10 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.