planner

Create structured plans for multi-task projects that can be used by the task-orchestrator skill. Use when breaking down complex work into parallel and sequential tasks with dependencies.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

A well-organized, actionable planning skill with a concrete template and clear phase sequence. Weaker spots are minor verbosity in the template and the absence of an explicit error-recovery feedback loop in the workflow.

Suggestions

Add an explicit validate-fix-retry loop (e.g., after Phase 3 subagent review, revise and re-review until criteria pass) to strengthen workflow clarity.

Trim the plan template's more obvious placeholder lines to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the plan template and a few explanatory lines could be tightened to earn their tokens more clearly.	2 / 3
Actionability	Provides a concrete plan template with specific fields (Location, Acceptance Criteria, Validation), real-file-path bad/good examples, and copy-paste-ready hand-off commands and invocation prompts.	3 / 3
Workflow Clarity	Phases 0-4 give a clear sequence and the template includes validation fields and a review checkpoint, but the main workflow lacks an explicit validate-fix-retry feedback loop for error recovery.	2 / 3
Progressive Disclosure	Content is well-organized into clear sections with a single clearly-signaled one-level reference (parallel-task), and appropriately split as an overview plus template with no bundle files needed.	3 / 3
	Total	10 / 12 Passed

Description

85%

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

A strong, third-person description that clearly states what the skill does and when to use it, with a distinct niche. Its main weakness is trigger-term coverage, which leans technical rather than capturing the natural phrasings a user would say.

Suggestions

Broaden the 'Use when' clause with more natural user phrasings (e.g., 'plan a project', 'break work into tasks', 'organize a multi-step project') to improve trigger-term coverage.

Consider naming a few more concrete planning artifacts (e.g., sprints, task dependencies, acceptance criteria) to make the capability list even more specific.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'Create structured plans for multi-task projects' and 'breaking down complex work into parallel and sequential tasks with dependencies' — covering multiple specific capabilities rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Create structured plans for multi-task projects...') and when via a clear 'Use when breaking down complex work...' trigger clause.	3 / 3
Trigger Term Quality	Includes relevant keywords like 'breaking down complex work', 'parallel and sequential tasks', and 'dependencies', but the phrasing is somewhat process-technical and misses common natural variations a user would spontaneously say.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — planning for the task-orchestrator skill — with distinct triggers around parallel/sequential task breakdown, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	12 / 16 Passed

Repository: jdrhyne/agent-skills
Commit: 292843f

Reviewed: about 18 hours 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.