planned-task-runtime

Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.

Quality

85%

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

85%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 densely prescriptive, highly actionable runtime skill body with strong workflow sequencing and verification feedback loops. The main weakness is cross-section redundancy in the silence/no-poll/load-trigger admonitions that could be consolidated.

Suggestions

Consolidate the recurring 'do not poll / end your turn' and 'do not write a user-facing message' rules into one section and reference it, instead of restating them in Synthesize, Build-workflow, and Checkpoint.

Trim the opening load-trigger paragraph so it does not repeat the full tag list already present in the description; keep a single concise 'load when…' cue.

Dimension	Reasoning	Score
Conciseness	Mostly lean and imperative with no concept over-explanation, but the 'do not poll / end your turn' and 'do not write a user-facing message' admonitions recur across the Synthesize, Build-workflow, and Checkpoint sections, and the opening load-trigger paragraph repeats the description's trigger list.	2 / 3
Actionability	Gives concrete, executable tool calls with exact parameters (workflows(action="setup"), complete-checkpoint(taskId, status, result), create-tasks with planningContext.source: "replan") plus specific field names and status values.	3 / 3
Workflow Clarity	Each follow-up type has a clear sequenced procedure, and the Checkpoint section includes explicit verification checkpoints, a patch-and-re-verify feedback loop, and a two-round escalation bound ('if the issue cannot be narrowed within two rounds, call complete-checkpoint(status="failed")').	3 / 3
Progressive Disclosure	Single cohesive SKILL.md with no bundle files and no nested references; content is organized under clearly labeled per-follow-up-type headers, which is appropriate for a self-contained runtime skill.	3 / 3
	Total	11 / 12 Passed

Description

85%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 precise, well-scoped runtime skill description that clearly states both capability and load conditions. Its only weakness is that the trigger terms are system tag names rather than natural user language, leaving little room for common phrasing variations.

Suggestions

Add one or two natural-language trigger phrasings alongside the system tags (e.g., 'after spawning background tasks' or 'when a planned task finishes') so the skill also matches how users describe these situations.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions ('synthesize, replan, build-workflow, checkpoint') and specific tag surfaces (background-task-completed, running-tasks, create-tasks silence rules) rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Handles system follow-up turns: ...') and when ('Load whenever any of these tags appear or after calling create-tasks'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Lists the precise system tags that trigger loading, but these are technical XML tag names, not natural phrasings a user would say; only 'after calling create-tasks' approaches natural language and common variations are absent.	2 / 3
Distinctiveness Conflict Risk	Tied to highly specific system tags (planned-task-follow-up, background-task-completed, running-tasks) that form a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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/planned-task-runtime/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.