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. If create-tasks is not visible, load it via load_tool (search "create tasks"). 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

82%

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

75%Weight 40%Scale 1-5

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 prescriptive instruction-only skill: exact tool parameters, an ordered executor-briefing format, explicit revision feedback loops, and clear boundary guidance against sibling skills. It is efficient and actionable, with the main improvement levers being a worked example spec and a graph self-check before submission.

Suggestions

Include one worked example of a build-workflow task spec with the ordered labels (Outcome through Done when) filled in, so executors have a copy-paste-ready pattern instead of assembling from prose.

Add a pre-submission validation step in the Method, e.g. re-check dependency edges (producers before consumers, no cycles) before calling create-tasks, to close the workflow-clarity gap.

Consolidate the repeated load_tool instruction into one place and merge the duplicated single-workflow exclusions between the 'When NOT to use' and 'When to use' sections to trim tokens.

Dimension	Reasoning	Score
Conciseness	The body is rule-dense with no padding or explanation of concepts Claude already knows — every line is a specific operational rule (exact parameters, ordered labels, credential branching rules). Minor redundancy holds it below anchor 5: the load_tool instruction appears three times (intro, Method step 7, Revisions) and the single-workflow exclusions are repeated across the 'When NOT to use' and 'When to use' sections.	4 / 5
Actionability	Highly concrete executable guidance: exact tool invocations with parameters ('create-tasks with planningContext.source: "planning-skill"', 'nodes(action="suggested")', 'credentials(action="list")') and an ordered spec label checklist. It falls short of anchor 5 only because there is no worked example of a filled-in task spec — a builder must assemble the labels from prose rather than copy-paste a pattern.	4 / 5
Workflow Clarity	The 8-step Method is clearly sequenced, and the Revisions section provides an explicit feedback loop (reject → revise surgically → resubmit; deny → stop), with checkpoint/verification philosophy spelled out. It misses anchor 5 because there is no pre-submission self-check of the graph itself (producers-before-consumers is stated as a rule but not as a verification step before calling create-tasks).	4 / 5
Progressive Disclosure	No bundle files exist; the body is well-sectioned with clearly signaled external knowledge-base navigation (index.json paths, rg/find under templates/, 'never load templates/index.json wholesale'). Minor gaps: the full spec-label semantics and assumptions rules are long inline sections that could live in a one-level-deep reference file if the skill ever ships a bundle.	4 / 5
	Total	16 / 20 Passed

Description

82%Weight 40%Scale 1-5

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 description with excellent trigger clarity, explicit scope boundaries, and explicit redirects to sibling skills. Its only weakness is that the primary capability (designing a dependency-aware task graph and submitting it with create-tasks) is implied via tool names rather than stated as an action, leaving specificity slightly under the top anchors.

Suggestions

State the core action explicitly in the description, e.g. 'Designs a dependency-aware task graph and submits it with create-tasks', so the what reads as concrete actions rather than being inferred from tool names.

Add one or two natural user phrasings such as 'coordinate', 'orchestrate', or 'multi-step build' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration") and 1-2 concrete actions ("load it via load_tool", redirect to workflow-builder/data-table-manager), but the core deliverable action — designing and submitting a task graph via create-tasks — is only implied by the tool name. It does not list the several explicit actions needed for anchor 4, and it is far above the pure-vagueness of anchors 1-2.	3 / 5
Completeness	Both what (coordinated multi-artifact planning across workflows and shared data tables) and when are explicitly and concretely answered: "ONLY for coordinated multi-artifact work... or the user explicitly asked to review a plan first" plus a full explicit exclusion list. This matches anchor 5's clear-and-explicit what-and-when with concrete trigger phrases; anchor 4's 'when could be more explicit' does not apply.	5 / 5
Trigger Term Quality	Good natural keyword coverage: "review a plan first", "multiple workflows", "dependencies", "data-table schema/migration", plus explicit anti-triggers ("new one-off workflows", "single-workflow edits", "verification-only requests"). A few natural user phrasings (e.g., "coordinate these builds", "orchestrate") are missing, so it falls short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers and an explicit "Do NOT use for..." list that names the alternative skills to use instead (workflow-builder, data-table-manager). Conflict risk with neighboring skills is minimal, matching anchor 5.	5 / 5
	Total	17 / 20 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: 0e1c754

Reviewed: 15 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.