instance-awareness

Load when the request depends on what is already on this instance rather than on what the user just typed: a short or ambiguous opener ("fix it", "carry on", "what should I look at"), a reference to earlier work in a new conversation, or any question about what has recently run or broken.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/@n8n/instance-ai/skills/instance-awareness/SKILL.md

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-crafted, instruction-only skill body that provides concrete tool-call guidance inside a clear cheapest-first reading order with strong stop-condition checkpoints. Weakest on actionability completeness (the executions call form is implied but not shown) and progressive disclosure (a dense single file that could split the reference table or rung details).

Suggestions

Show the explicit executions(...) call signature alongside the activity/workflows examples so every surface named in the table has a copy-paste form.

Split the "What each surface can and cannot tell you" table or the per-rung detail into a short reference file to ease scanning and let the body function as a tighter overview.

Trim the editorial aside about "the most common complaint in reviewed conversations" to keep the body purely instructional.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence ("Stop at the first one that answers yours. Do not start at the bottom."), with no padding about what an instance is, though a few editorial passages ("it is the most common complaint in reviewed conversations...") could be trimmed.	4 / 5
Actionability	Gives concrete, parameterized tool calls (activity(action="list"), activity(action="expand", id=N), workflows(action="get", workflowId, full=true)) that are copy-paste ready, but the executions invocation syntax is referenced rather than shown.	4 / 5
Workflow Clarity	A clearly sequenced reading order (rungs 0-2) with an explicit stop-condition checkpoint ("Stop at the first one that answers yours") and prune-handling guidance; being read-only, the destructive/batch validation cap does not apply, though no explicit error-recovery loop is present.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed; the single-file body is well-organized into clear section headers, a Q&A table, and ordered rungs, but is a dense inline block that exceeds the under-50-line simple-skill exception.	4 / 5
	Total	16 / 20 Passed

Description

83%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, well-targeted description that explicitly pairs a clear 'when' trigger with concrete example openers and a distinct instance-state niche. The main gap is capability specificity — it describes when to load more fully than what the skill concretely does.

Dimension	Reasoning	Score
Specificity	Names the domain (instance state) and lists several concrete trigger scenarios ("a short or ambiguous opener", "a reference to earlier work in a new conversation", "any question about what has recently run or broken"), but does not enumerate the underlying capabilities (activity/workflows/executions lookups), so coverage has minor gaps.	4 / 5
Completeness	Explicitly answers both what (depends on what is already on this instance) and when ("Load when the request depends on...") with concrete trigger phrases, satisfying the 'Use when' equivalent requirement.	5 / 5
Trigger Term Quality	Includes genuinely natural openers users would say ("fix it", "carry on", "what should I look at") plus "what has recently run or broken", giving good keyword coverage, though a few synonymous phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	The "what is already on this instance rather than what the user just typed" framing carves a clear niche with minimal conflict risk, but generic openers like "fix it" create minor overlap risk with general context skills.	4 / 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/instance-awareness/SKILL.md
Commit: 3d0c201

Reviewed: 5 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.