flows-app-brief
Certification coach for Flows apps. Captures the app name, value case, persona, problem, and design intent through a structured conversation and writes App-Brief.md at the repo root. This is the FIRST step of the Flows app certification flow — run it immediately after `npx @cognite/cli apps create`, before building. Use when the user asks to start an app brief, run the certification coach, fill out the app brief, or run flows-app-brief.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly communicates what the skill does (structured conversation to capture app details and write App-Brief.md), when to use it (explicit trigger terms and workflow context), and how it fits into a larger process. It uses third-person voice consistently and provides enough specificity to be easily distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: captures app name, value case, persona, problem, and design intent through structured conversation, writes App-Brief.md at repo root. Also specifies its position in a workflow (first step after `npx @cognite/cli apps create`). | 3 / 3 |
Completeness | Clearly answers both 'what' (captures app details through structured conversation and writes App-Brief.md) and 'when' (explicit 'Use when...' clause listing four trigger scenarios, plus contextual timing guidance about running it after app creation). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'app brief', 'certification coach', 'fill out the app brief', 'flows-app-brief', 'Flows apps'. These cover the likely phrasings a user would employ when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Flows app certification coaching, App-Brief.md generation, specific CLI tool reference. Very unlikely to conflict with other skills due to the domain-specific terminology and precise workflow positioning. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted conversational workflow skill that provides excellent actionability through specific coaching prompts, challenge phrases, good-example answers, and a complete output template. The workflow sequencing is strong with clear validation gates at each coached field and before file writing. The main weakness is moderate verbosity — while most content is justified, some redundancy exists between operating rules and step-level instructions, and the skill could benefit from splitting the output template or mapping tables into separate reference files.
Suggestions
Consider extracting the App-Brief.md template and the spec-kit mapping table into separate reference files to reduce the main skill's length and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~250 lines) but most content earns its place — the coaching rubrics, spec-kit mapping table, and challenge prompts are all novel domain knowledge Claude wouldn't have. However, there's some redundancy: operating rules repeat 'confirm before saving' logic that's also stated in Step 0 rules, and some phrasing could be tightened (e.g., the preflight section's retry flow is verbose for what it does). | 2 / 3 |
Actionability | The skill provides highly concrete guidance: exact AskQuestion prompts to use when challenging vague answers, specific good-example answers for each coached field, a complete YAML+markdown template for the output file, exact CLI commands for the preflight step, and a clear spec-kit mapping table. Everything is copy-paste ready and leaves no ambiguity about what to produce. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Preflight → Step 0 → Step 1 → Step 2 → Step 3 → Step 4 → Step 5) with explicit validation checkpoints: Step 4 explicitly states 'If any required field is still empty, do not write the file — return to coaching that field.' The preflight includes a retry/skip/stop feedback loop. Each coached field has a clear save-when/challenge-when rubric that acts as a validation gate. | 3 / 3 |
Progressive Disclosure | The skill is a single monolithic file with no references to supporting documents, which is acceptable given no bundle files exist. However, at ~250 lines it's on the edge of what should be a single file — the spec-kit mapping table and the full App-Brief.md template could reasonably be split out. The internal structure with clear headers and tables is good, but the content density is high for a single read. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- cognitedata/builder-skills
- Commit
d6af887
- Reviewed
Table of Contents
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.