atlan-fact-verification-gate
Verify Atlan app behavior against SDK docs/code and CLI docs/code before behavior-changing decisions; use lightweight checks by default and deep checks when risk is high.
Best use case
atlan-fact-verification-gate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Verify Atlan app behavior against SDK docs/code and CLI docs/code before behavior-changing decisions; use lightweight checks by default and deep checks when risk is high.
Teams using atlan-fact-verification-gate should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/atlan-fact-verification-gate/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How atlan-fact-verification-gate Compares
| Feature / Agent | atlan-fact-verification-gate | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Verify Atlan app behavior against SDK docs/code and CLI docs/code before behavior-changing decisions; use lightweight checks by default and deep checks when risk is high.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Atlan Fact Verification Gate Create a lightweight verification checkpoint before behavior-changing decisions. ## Workflow 1. Classify task as `build`, `modify`, `test`, `review`, or `release`. 2. Read source guide: `../_shared/references/verification-sources.md`. 3. Verify only what is required for the current decision: - SDK behavior for runtime/data-path decisions. - CLI behavior for scaffold/run/test/release commands. 4. Resolve SDK evidence using portable fallback order: - local checkout (if present) - installed package source - remote source/docs 5. For build tasks, classify app quality tier (`quickstart-utility` or `connector-standard`) using `../_shared/references/app-quality-bar.md`. 6. Create `verification_manifest.json` using `../_shared/assets/verification_manifest.json` as template. 7. Validate manifest: `python ../_shared/scripts/validate_verification_manifest.py verification_manifest.json` 8. Continue if status is `ready`; otherwise resolve unknowns or ask user. 9. If CLI mismatch is found, append proposal entry to `../_shared/references/cli-change-proposals.md`. ## Output Contract - Produce `verification_manifest.json` for non-trivial behavior changes. - Record what was inspected, including exact command/flag facts when command behavior matters. - Never edit SDK or CLI repositories. ## References - Checklist: `references/checklist.md` - Artifact schema: `../_shared/references/artifact-templates.md` - Quality bar: `../_shared/references/app-quality-bar.md` - Multi-agent compatibility: `../_shared/references/agent-surface-compatibility.md`
Related Skills
atlan-workflow-args-secrets-state
Implement workflow argument retrieval, credential_guid usage, and state store updates using Atlan SDK patterns. Use when workflows or activities handle credentials, runtime args, or persisted workflow state.
atlan-sql-connector-patterns
Select and apply the correct SQL connector implementation pattern (SDK-default minimal or source-specific custom). Use when building or extending SQL metadata/query extraction connectors.
atlan-sdk-objectstore-io-defaults
Enforce object store and IO defaults from the Atlan SDK for output paths, prefixes, and file writes. Use when implementing or reviewing raw/transformed output handling.
atlan-review-doc-sync
Run findings-first review for Atlan app changes and synchronize app documentation with implemented behavior. Use when completing a change set, preparing handoff, or auditing regressions.
atlan-e2e-contract-validator
Generate and validate e2e test contracts for Atlan workflows, including API responses, output paths, and schema assertions. Use when adding or updating workflow e2e coverage.
atlan-cli-run-test-loop
Run Atlan app execution loops using CLI-first commands with automatic CLI availability checks and safe fallbacks.
atlan-cli-install-configure
Install Atlan CLI with OS-aware binaries (or Homebrew on macOS) only when missing, then configure baseline tenant auth/log settings.
atlan-app-scaffold-standard
Scaffold new Atlan apps from CLI templates as the default behavior when users ask for a new app, then align files to sample-app standards.
docs-validating-factual-accuracy
Universal methodology for verifying factual correctness in documentation using WebSearch and WebFetch tools. Covers command syntax verification, version checking, code example validation, API correctness, confidence classification system ([Verified], [Error], [Outdated], [Unverified]), source prioritization, and update frequency rules. Essential for maintaining factual accuracy in technical documentation and educational content
phone-verification
Verify phone numbers using SMS one-time codes via the Didit API. Use when you need to confirm a user owns a phone number, implement SMS-based 2FA, or validate phone during signup/onboarding flows.
Superstition Verification Skill
Use this skill to systematically verify superstitions in
code-refactor
Proactively detect and execute code refactoring to maintain DDD architecture and code quality. Triggers: RF, refactor, 重構, 拆分, split, 模組化, modularize, 太長, cleanup.