post-build-flow

Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.

Quality

81%

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

81%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.

An instruction-dense, highly actionable skill body: exact tool invocations, a complete JSON example, explicit validation checkpoints, and feedback loops around destructive operations. Its weaknesses are cross-section rule duplication that inflates token cost and an inlined credential-recipe section that would fit better as a reference file.

Suggestions

Deduplicate the publish-readiness and mocked-verification live-test rules by stating each once in its own section and cross-linking from the numbered steps, which would meaningfully cut token cost.

Move the credential-recipe field-by-field spec (the placeholders/docsUrl/testUrl bullet list plus the fal.ai example) into a references/ file, keeping only the decision rule (when to use Simplified Custom Auth and the load-credential-recipe-research instruction) inline.

The setup-panel and setup-card instructions overlap between the "Setup panel" section and steps 3-5 of "After build-workflow succeeds"; consolidate into one authoritative location.

Dimension	Reasoning	Score
Conciseness	Nearly every sentence encodes non-obvious routing rules Claude cannot infer, with no padding or explanation of known concepts — but the same rules repeat across sections: publish-readiness appears in "Publishing and testing" and again at steps 9-10, and the mocked-verification live-test instructions appear three times. This duplication goes beyond the minor trimming of a 4, but there is no verbosity of the padded, known-concept kind of a 2.	3 / 5
Actionability	Guidance is fully executable: exact tool calls with parameters (workflows(action="setup", reopenSkipped: ["slackApi"]), executions(action="get-resolved-node-parameters")), precise field names and statuses throughout, and a complete copy-paste-ready credentialHints JSON example (fal.ai) covering the common custom-auth case.	5 / 5
Workflow Clarity	The 10-step post-build sequence has explicit validation checkpoints (inspect the persisted workflow against the request, re-verify after patches, read resolvedParameterWarnings and skippedParameterChecks), feedback loops (failed run → executions(action="debug") → repair → retest; publish refusal → verificationDisclosure → user decision), and destructive operations (test-data cleanup, publishing) gated behind approval and claim levels.	5 / 5
Progressive Disclosure	references/trigger-input-data-shapes.md is a real, clearly signaled, one-level-deep reference with a workspace fallback, and sections are well-organized with anchored cross-links. It stays at 4 because heavy detail (the ~90-line credential-recipe section) is inlined in SKILL.md where a reference file could carry it.	4 / 5
	Total	17 / 20 Passed

Description

76%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 tightly scoped, third-person description with an explicit what and multiple concrete when clauses anchored to distinct system markers. Its main weakness is trigger-term naturalness — the keywords are system jargon rather than user phrasing, and boundary cases with closely related build-flow skills are left unstated.

Suggestions

Add one or two natural user-language trigger phrases (e.g. "verify the workflow after building it", "set up credentials after a build") alongside the system markers so the description also matches how users actually phrase the need.

State the key boundary in the description itself (e.g. one-off builds route to a different skill) to reduce overlap risk with closely related build/verify skills.

Dimension	Reasoning	Score
Specificity	"Handles workflow verification and setup after build-workflow succeeds" names the domain and concrete actions, and cites exact trigger fields like verificationReadiness and workflow-verification-follow-up. It stays at 4 rather than 5 because only two capability verbs (verification, setup) are given rather than comprehensive action coverage.	4 / 5
Completeness	It clearly answers what ("Handles workflow verification and setup after build-workflow succeeds") and explicitly answers when with concrete trigger phrases ("or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds...").	5 / 5
Trigger Term Quality	Keywords are mostly system-injected markers ("workflow-verification-follow-up", "workflow-setup-required", "verificationReadiness") plus domain terms ("build-workflow", "verify/setup follow-up") — relevant and on-domain but missing the natural phrases a user would say, like "test the workflow" or "verify my workflow".	3 / 5
Distinctiveness Conflict Risk	The distinct system trigger tags carve a clear post-build niche with minimal misfire risk, but the build/verify/setup territory overlaps closely related skills (workflow-builder, one-off-operations) and the description does not state the one-off-build exclusion, so it sits at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (709 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: n8n-io/n8n
Path: packages/@n8n/instance-ai/skills/post-build-flow/SKILL.md
Commit: 439e8ba

Reviewed: 1 day 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.