verification-gate
Verify implementation claims with relevant tests, validation, diffs, and concrete evidence before completion.
Skill by Anders-planck
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/anders-planck-verification-gate
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/verification-gate
What's inside
- Skill name
verification-gate- Description
- Verify implementation claims with relevant tests, validation, diffs, and concrete evidence before completion. Use when finishing code, configuration, documentation, releases, migrations, or any task whose result must be proven rather than assumed.
- License
- MIT
- Instructions
- 18 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Verification Gate ## Workflow 1. Restate the requested outcome as observable conditions. 2. Inspect the final diff and exclude unrelated changes. 3. Run the narrowest relevant tests, then repository-wide validation when risk warrants it. 4. Check generated artifacts in their consumed format, not only their source. 5. Report exact commands, pass/fail state, and any unverified boundary. ## Guardrails - Do not treat compilation alone as behavioral verification. - Do not hide skipped, flaky, unavailable, or partially passing checks. - Do not declare completion while a relevant failure remains. - Avoid destructive cleanup merely to obtain a clean test result.
From Anders-planck/orditra, MIT.
More from Anders-planck/orditra
- 0.529score
workflow-router
orditra
Routes engineering work to the smallest suitable skill flow and checks prerequisites.
SkillBFreshness: BClaude Code +9 - 0.526score
serena-symbolic-code
orditra
Uses Serena MCP for symbol discovery, references, dependency understanding, and precise symbol-level edits.
SkillBFreshness: BClaude Code +9 - 0.526score
structural-code-search
orditra
Uses ast-grep for AST-aware code search, lint rules, and controlled rewrites while keeping text search and semantic navigation separate.
SkillBFreshness: BClaude Code +9 - 0.521score
project-bootstrap
orditra
Initializes a repository for portable agent workflows without overwriting existing conventions.
SkillBFreshness: BClaude Code +9 - 0.519score
evidence-report
Anders-planck
Convert engineering findings into concise terminal, JSON, Markdown, SARIF, HTML, and Mermaid-backed reports.
SkillBFreshness: BClaude Code +9 - 0.519score
agent-supply-chain
Anders-planck
Audit agent skills, MCP servers, plugins, hooks, prompts, permissions, pins, licenses, and content digests before activation.
SkillBFreshness: BClaude Code +9 - 0.519score
performance-report
Anders-planck
Capture browser performance traces and turn Core Web Vitals, network, console, and rendering evidence into actionable reports.
SkillBFreshness: BClaude Code +9 - 0.519score
large-codebase-map
Anders-planck
Build token-budgeted repository maps and route large-code discovery between Serena, Repomix, and Probe.
SkillBFreshness: BClaude Code +9 - 0.519score
browser-qa
Anders-planck
Run token-efficient browser quality assurance with Playwright CLI and escalate to MCP only for persistent exploratory loops.
SkillBFreshness: BClaude Code +9 - 0.519score
current-docs
Anders-planck
Retrieve current version-specific library and API documentation from Context7 or primary official sources.
SkillBFreshness: BClaude Code +9 - 0.519score
dependency-architecture
Anders-planck
Map module dependencies and enforce architectural boundaries with dependency-cruiser or a language-specific provider.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 12, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Anders-planck/orditra
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Anders-planck
- 0.519score
agent-supply-chain
Anders-planck
Audit agent skills, MCP servers, plugins, hooks, prompts, permissions, pins, licenses, and content digests before activation.
SkillBFreshness: BClaude Code +9 - 0.519score
browser-qa
Anders-planck
Run token-efficient browser quality assurance with Playwright CLI and escalate to MCP only for persistent exploratory loops.
SkillBFreshness: BClaude Code +9 - 0.519score
current-docs
Anders-planck
Retrieve current version-specific library and API documentation from Context7 or primary official sources.
SkillBFreshness: BClaude Code +9 - 0.519score
dependency-architecture
Anders-planck
Map module dependencies and enforce architectural boundaries with dependency-cruiser or a language-specific provider.
SkillBFreshness: BClaude Code +9 - 0.519score
evidence-report
Anders-planck
Convert engineering findings into concise terminal, JSON, Markdown, SARIF, HTML, and Mermaid-backed reports.
SkillBFreshness: BClaude Code +9 - 0.519score
large-codebase-map
Anders-planck
Build token-budgeted repository maps and route large-code discovery between Serena, Repomix, and Probe.
SkillBFreshness: BClaude Code +9
Cite this page
verification-gate skill. Agent Mart. https://agentmart.dev/skills/anders-planck-verification-gate (last updated 2026-10-24)