{
  "markdown": "# Flows Skills\n\nAgent-agnostic AI skills for [Flows](https://cognite-dune-docs.mintlify.app/cdf/flows) apps. Works with Claude Code, Cursor, Copilot, and any agent that supports the [skills format](https://agentskills.io/specification).\n\n## Install\n\nPull all skills into your Flows app:\n\n```bash\nnpx @cognite/cli@latest apps skills pull\n```\n\nPull a specific skill:\n\n```bash\nnpx @cognite/cli@latest apps skills pull --skill integrate-fusion-agent\n```\n\n## Certification flow\n\nFour skills drive the Flows app certification flow end to end. Run them in order:\n\n1. **flows-app-brief** — Right after `npx @cognite/cli apps create`. Coaches you through the App Brief and writes `App-Brief.md`.\n2. **flows-code-review** — Technical review. Writes `reviews/code-review/feedback-round-<N>/`. Re-run until 0 Must Fix.\n3. **flows-design-review** — Manual design quality assessment (10 questions). Writes `reviews/design-review/feedback-round-<N>/`. Target average ≥ 3.8.\n4. **flows-external-app-submit** — Verifies the prior three artifacts and runs `npx @cognite/cli apps submit`.\n\n## Available Skills\n\n| Skill | Description |\n|-------|-------------|\n| **flows-app-brief** | Certification coach (step 1) — captures app details, persona, problem, and success criteria, writes `App-Brief.md` |\n| **flows-review-checks** | Shared technical-review bar (hunts, coverage scope, public criteria). Loaded by `flows-code-review` and by external review skills — do not copy |\n| **flows-code-review** | Local technical review runner (step 3) — loads `flows-review-checks`, writes `reviews/code-review/feedback-round-<N>/` |\n| **flows-design-review** | Manual design quality assessment (step 4) — scores the 10 quality-guidelines questions, writes `reviews/design-review/feedback-round-<N>/design-review-report.md` |\n| **flows-external-app-submit** | Submission gate (step 5) — verifies brief + code review (0 Must Fix) + design review (avg ≥ 3.8), then runs `npx @cognite/cli apps submit` |\n| **integrate-fusion-agent** | Default AI path — Atlas / EOS sidebar |\n| **integrate-atlas-chat** | Exception — in-app `useAtlasChat` when the EOS sidebar cannot work |\n| **create-client-tool** | `AtlasTool` for an approved in-app chat (sidebar tools: `integrate-fusion-agent`) |\n| **setup-python-tools** | Pyodide for in-app chat only |\n| **call-cognite-function** | Invokes a deployed CDF Function by ID or external ID — session nonce, call, poll until complete, return typed result |\n| **code-quality** | Reviews Flows apps for code quality, maintainability, and clean code issues |\n| **correctness-and-error-handling** | Reviews for bugs, missing error states, unhandled rejections, and edge cases |\n| **dm-graph-traversal** | CDF Data Modeling graph traversal patterns — query-vs-list decisions, traversal payload guardrails, failure debugging, and payload-shape test requirements |\n| **dm-limits-and-best-practices** | DMS concurrency, pagination, batching; LLM-over-rows cap (5 / max 50) |\n| **integrate-file-viewer** | Integrates CogniteFileViewer to preview CDF files (PDFs, images, text) |\n| **performance** | Optimizes Flows apps for speed, render counts, and bundle size |\n| **pull-changes-resolve-conflicts** | Merge or rebase workflow — list conflicts, analyze ours/theirs, get user approval before resolving |\n| **security** | Reviews for security issues — credentials, user input, external data |\n| **migrate-app-to-flows** | Migrates a legacy Dune POC app to Flows Custom App infrastructure — fixes `app.json`, auth, `manifest.json`, and deploy scripts |\n| **setup-flows-auth** | Migrates React apps to Flows auth or adds DuneAuthProvider |\n| **hide-show-shell** | Hides/reveals the Fusion sidebar + topbar for full-screen app-only mode via `api.setHideShell()`, with best practices for always giving users a way back |\n| **handle-startup-state** | Reads `initialState` from `connectToHostApp()` on mount — deep links, shareable URLs, and host-provided startup arguments — with safe parsing, defaults merging, and optional `syncInternalState` write-back |\n| **design** | Aura UI — components and tokens, layouts, UX copy, forms/async feedback, accessibility (`skills/design/`) |\n\n## Contributing\n\nAdd a new skill by creating a `skills/<name>/SKILL.md` file with proper frontmatter:\n\n```yaml\n---\nname: my-skill\ndescription: \"When to use this skill...\"\nallowed-tools: Read, Glob, Grep, Edit, Write\n---\n```\n\nConsolidated Aura guidance uses the **`design`** skill (`skills/design/SKILL.md`). Older per-topic `design-*` skills were merged into that folder.\n\n**Authoring style**: Use `## Section` markdown headings for structural sections like Role, When to use, and Setup. XML tags (e.g., `<rubric>`, `<example>`) are acceptable where they serve a machine-parsing purpose.\n",
  "bytes": 4754,
  "sha": "226d48dc12087b173e6b44371a797a8f74ed99eaa5d2de181e3a92424ca6bf5a",
  "repo_slug": "cognitedata/builder-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_cognitedata_builder_skills_reveal_3d_74316a66/readme"
}