planning

ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration across tasks, or the user explicitly asked to review a plan first. Load create-tasks via load_tool before calling it (search "create tasks" if not visible). Do NOT use for new one-off workflows, single-workflow edits, verification-only requests, or standalone data-table ops — use workflow-builder or data-table-manager instead.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

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

A well-structured, highly actionable planning skill with a clear sequenced method. Its main weaknesses are mild internal repetition that could be tightened and a monolithic single-file layout where the detailed spec/assumptions rules could live in separate reference files.

Suggestions

De-duplicate the checkpoint guidance: state the 'no routine verification checkpoints' rule once and have the Checkpoints section reference it rather than re-deriving it three times across Method, intro, and close.

Consolidate 'When NOT to use this skill' and 'When to use this skill' so the routing criteria appear once; the current two-section split restates the same coordination-vs-single-workflow distinction.

Consider moving the detailed Task Graph Rules spec-label definitions and the Assumptions rules into a reference file (e.g. references/task-spec.md) and signaling it from the body, so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Dense and free of concept-explanation fluff, but there is real repetition: the 'When NOT to use' and 'When to use' sections overlap, and the 'no routine checkpoints' rule is restated three times (Method step 6, Checkpoints intro, and its closing line).	2 / 3
Actionability	Highly executable for an instruction-only skill: exact task kinds, the ordered spec label list, exact planningContext fields, and concrete tool calls like nodes(action="suggested") and credentials(action="list").	3 / 3
Workflow Clarity	The Method is a clear 8-step sequence with a revisions/rejection feedback loop; no validation loop is required since planning is non-destructive, so the sequence is unambiguous.	3 / 3
Progressive Disclosure	No skill bundle files exist and the body is a single ~170-line file; the dense Task Graph Rules and Assumptions sections are reference-like material kept inline rather than split into signaled reference files.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 high-quality description: it states concrete capabilities, gives explicit positive and negative triggers, and actively disambiguates from sibling skills. The only mild weakness is that some operational mechanics ('Load create-tasks via load_tool') bleed into what is otherwise a capability/trigger statement.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities — 'coordinated multi-artifact work', 'multiple workflows with dependencies', 'shared data-table schema/migration across tasks', 'review a plan first' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('coordinated multi-artifact work...') and when ('ONLY for...', 'Do NOT use for...') with explicit positive and negative triggers.	3 / 3
Trigger Term Quality	Includes natural trigger phrases a user would say ('review a plan first', 'multiple workflows with dependencies') alongside the negative-trigger list, giving good coverage of when this applies.	3 / 3
Distinctiveness Conflict Risk	The explicit 'Do NOT use for ... use workflow-builder or data-table-manager instead' clause carves out a clear niche and steers away from sibling skills, making misrouting unlikely.	3 / 3
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: n8n-io/n8n
Path: packages/@n8n/instance-ai/skills/planning/SKILL.md
Commit: bcbea0a

Reviewed: 7 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.