flows-external-app-submit

Final gate of the Flows app certification flow for external submission. Verifies that flows-app-brief, flows-code-review, and flows-design-review have all been run and are in a passing state (App-Brief.md complete, 0 Must Fix in latest code review, design average ≥ 3.8), then runs `npx @cognite/cli apps submit` to zip the repo and pre-populate the submission form. Use when the user asks to submit a Flows app for certification, run flows-external-app-submit, or finalize an app for external review.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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

A dense, highly actionable verification gate with exemplary workflow sequencing and validation checkpoints. The only weakness is mild verbosity from a repeated git-archive caveat and a few justificatory asides.

Suggestions

State the `git archive HEAD` exclusion once (in Preconditions #4) and have Steps 4–5 reference it, instead of re-explaining it in the Step 4 intro and block message.

Tighten justificatory asides to their operational core — e.g., 'App-Brief.md is non-negotiable — it captures the value case the certification reviewer reads first' can become 'App-Brief.md is required (non-negotiable).'

Shorten the 'Round 0 is intentional...' paragraph to the essential rule: stubs use round 0 so `sort -V | tail -1` supersedes them once a real round (>=1) is added.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of basic-concept padding, but the `git archive HEAD` caveat is restated in precondition #4, the Step 4 intro, and the Step 4 message, and a few justificatory asides could be tightened — matching 'could be tightened' rather than 'every token earns its place'.	2 / 3
Actionability	Packed with executable, copy-paste-ready bash (`git ls-files ... \| sort -V \| tail -1`, `npx @cognite/cli@latest apps submit`), exact regexes (`^- Must Fix open: (\d+)$`), and exact stub templates — fully actionable.	3 / 3
Workflow Clarity	Steps 0–8 are clearly sequenced with per-step validation, a PASS/FAIL/SKIPPED table checklist (Step 6), an explicit 'stop, do not run the CLI' gate, and feedback loops that name the exact next-step skill to re-run.	3 / 3
Progressive Disclosure	Well-organized into Preconditions, Step 0–8, and Stub templates with clear headers and no nested references; the self-contained workflow has no need for external files, and the inline stub templates are tightly coupled to their single consumer (Step 0).	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and distinctive, with concrete actions and natural trigger phrases covering both what the skill does and when to use it. Third-person voice is used throughout and nothing is over-claimed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Verifies that flows-app-brief, flows-code-review, and flows-design-review have all been run and are in a passing state' and 'runs `npx @cognite/cli apps submit` to zip the repo and pre-populate the submission form' — matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly states what (verifies three prior reviews' passing state, then runs the submit CLI) and when ('Use when the user asks to submit a Flows app for certification...'), with explicit triggers — satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Explicit triggers 'submit a Flows app for certification', 'run flows-external-app-submit', and 'finalize an app for external review' are natural phrases a user would actually say, giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (final gate of the Flows app certification flow) with distinct triggers unlikely to fire for any other skill.	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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: cognitedata/builder-skills
Commit: ab7b5f8

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.