swarm-planner

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

Quality

61%

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

57%

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 identifies a clear and distinctive niche—creating dependency-aware plans for parallel multi-agent execution—which minimizes conflict risk. However, it lacks a proper 'Use when...' clause with natural trigger terms, and the specific capabilities could be enumerated more concretely (e.g., task decomposition, dependency graph generation, parallelization strategy).

Suggestions

Add an explicit 'Use when...' clause describing trigger scenarios, e.g., 'Use when the user asks to break down a project into parallelizable tasks, plan multi-agent work, or create a dependency-aware execution strategy.'

List more concrete sub-actions such as 'analyzes task dependencies, generates execution graphs, identifies parallelizable work streams, and assigns tasks to agents'.

Include natural user-facing trigger terms like 'break down tasks', 'plan implementation', 'task decomposition', 'parallelize work' to improve discoverability.

Dimension	Reasoning	Score
Specificity	It names the domain (implementation plans, multi-agent execution) and a key action (creates dependency-aware implementation plans), but doesn't list multiple concrete sub-actions like analyzing dependencies, generating task graphs, assigning agent roles, etc.	2 / 3
Completeness	The 'what' is reasonably clear (creates dependency-aware implementation plans for parallel multi-agent execution), but the 'when' is only partially addressed via '[EXPLICIT INVOCATION ONLY]' which indicates invocation mode rather than providing explicit trigger scenarios or a 'Use when...' clause.	2 / 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'.	2 / 3
Distinctiveness Conflict Risk	The combination of 'dependency-aware implementation plans' and 'parallel multi-agent execution' is a very specific niche that is unlikely to conflict with other skills. The '[EXPLICIT INVOCATION ONLY]' tag further reduces conflict risk.	3 / 3
	Total	9 / 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 reasonably well-constructed planning skill with strong actionability - the task dependency format, example, and plan template are concrete and usable. Its main weaknesses are redundancy (clarification questions appear in multiple places, core principles duplicate process steps), a numbering error (two step 4s), and the inlined plan template that makes the skill longer than necessary. The workflow would benefit from tighter organization and deduplication.

Suggestions

Fix the duplicate step numbering (two steps labeled '4') and consolidate the clarification/question-asking guidance into a single location rather than repeating it in Core Principles, Step 1a, and Step 3.

Move the plan template to a separate file (e.g., `PLAN_TEMPLATE.md`) and reference it from the skill to improve progressive disclosure and reduce inline bulk.

Add an explicit validation checkpoint after the subagent review step - e.g., 'If subagent identifies critical dependency gaps, re-run step 4 before saving final plan.'

Dimension	Reasoning	Score
Conciseness	The skill has some redundancy - step 1a and step 3 both cover asking clarification questions with similar guidance, and the core principles repeat what's detailed in the process steps. The plan template is quite verbose with placeholder fields like 'log' and 'files edited/created' that pad the content. However, it's not egregiously verbose and most content serves a purpose.	2 / 3
Actionability	The skill provides a concrete task dependency format with a clear example, a complete plan template with markdown structure ready to use, specific subagent review instructions, and explicit file naming conventions. The guidance is specific and directly executable.	3 / 3
Workflow Clarity	The process has numbered steps with a clear sequence, and includes a subagent review step as validation. However, there are two steps both numbered '4' (Create Plan and Save Plan), step 1a's conditional logic is somewhat confusing, and the feedback loop after subagent review is mentioned but not structured with explicit re-validation. The overlap between steps 1a and 3 (both about asking questions) creates ambiguity about when to actually stop.	2 / 3
Progressive Disclosure	The content is well-structured with clear sections, but the full plan template is inlined rather than referenced as a separate file, making the skill quite long. For a skill of this complexity, the template could be in a separate file with a reference. The structure within the file is good with headers and logical grouping, but it's borderline monolithic.	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: 633b7e0

Reviewed: 5 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.