verified-answer
Use this skill whenever the user asks a technical question where a wrong answer could cause real harm — broken infrastructure, failed deployments, production…
Skill by davidnbr
Chalk Labs
Need help deploying verified-answer?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/davidnbr-verified-answer
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: backend, devops, cloud, security
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/verified-answer
What's inside
- Skill name
verified-answer- Description
- Use this skill whenever the user asks a technical question where a wrong answer could cause real harm — broken infrastructure, failed deployments, production bugs, security gaps, or wasted time. Triggers on any question involving tool syntax, API signatures, CLI flags, configuration keys, resource or argument names, version-specific behavior, default values, quotas or limits, error-message root causes, "does X support Y", "how do I do Z in some tool", or any factual claim that can be verified against documentation. Use this even when the user does not explicitly ask for sources — they always want verified answers over plausible-sounding guesses. Especially important for Terraform, AWS (ECS, ELB, SES, WAF, VPN, IAM, S3, Lambda), Python and its libraries (boto3, pydantic, requests), NixOS and Nix and Home Manager, GitHub Actions, CircleCI, Go, Docker, Kubernetes, Ruby on Rails, PostgreSQL, Redis, Azure, and any cloud or CI or infra topic where a hallucinated flag or function signature will break things.
- License
- unknown
- Instructions
- 227 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from davidnbr/.claude
- 0.547score
local-worker
davidnbr
Delegate edit/implementation work to a local LLM (Ollama-backed) running as a separate claude or opencode CLI process, while this session stays the…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-verified-tackle
davidnbr
End-to-end verified delivery for BMAD projects: runs the bmad-tackle-story dev→review→resolve loop on the given story id/range, then the code-enforced…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
complete-pr-review
davidnbr
Run a grounded, senior-engineer PR review on a branch — verify EVERY claim against real source (no assumptions), trace the changed logic like a state-machine…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-tackle-story
davidnbr
Tackle an existing BMAD story (or story range like aks-1-3..aks-1-5) end-to-end by orchestrating a dev→review→resolve loop: a coder subagent runs…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-resolve-review
davidnbr
Verify, address, and reply to PR/code-review findings from a senior-engineer perspective.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
verified-tackle
davidnbr
End-to-end verified delivery for non-BMAD projects (openspec/ or no spec tooling): plan-verify, implement, then the code-enforced Workflow verification loop…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
teach-mode
davidnbr
Learning-mentor mode with three sub-modes — Code Mentor (Socratic pair-programming, student writes all code), Explain Mode (deep verified concept explanation…
SkillBFreshness: B★ 1Claude Code +9 - 0.497score
pr-reviewer
davidnbr
Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go.
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
recall
davidnbr
Spaced repetition learning system for developers using multiple AI tools.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 27, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/davidnbr/.claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from davidnbr
- 0.547score
local-worker
davidnbr
Delegate edit/implementation work to a local LLM (Ollama-backed) running as a separate claude or opencode CLI process, while this session stays the…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-verified-tackle
davidnbr
End-to-end verified delivery for BMAD projects: runs the bmad-tackle-story dev→review→resolve loop on the given story id/range, then the code-enforced…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
complete-pr-review
davidnbr
Run a grounded, senior-engineer PR review on a branch — verify EVERY claim against real source (no assumptions), trace the changed logic like a state-machine…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-tackle-story
davidnbr
Tackle an existing BMAD story (or story range like aks-1-3..aks-1-5) end-to-end by orchestrating a dev→review→resolve loop: a coder subagent runs…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
bmad-resolve-review
davidnbr
Verify, address, and reply to PR/code-review findings from a senior-engineer perspective.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
verified-tackle
davidnbr
End-to-end verified delivery for non-BMAD projects (openspec/ or no spec tooling): plan-verify, implement, then the code-enforced Workflow verification loop…
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get verified-answer running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
verified-answer skill. Agent Mart. https://agentmart.dev/skills/davidnbr-verified-answer (last updated 2026-10-24)