gauntlet-loop
Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small…
Skill by jonnyasmith
Chalk Labs
Need help deploying gauntlet-loop?
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/jonnyasmith-gauntlet-loop
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: design, writing, research, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
gauntlet-loop- Description
- Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop until it wins. Works for builds, writing, code, research, or design. Triggers on "/gauntlet-loop", "gauntlet loop", "gauntlet this", "make a gauntlet prompt", "loop until it beats X".
- License
- unknown
- Instructions
- 130 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from jonnyasmith/skills
- 0.559score
gauntlet-workflow
jonnyasmith
Runs a gauntlet loop as a Workflow script instead of a pasted prompt - a deterministic outer loop that builds each piece, grades it with a fresh harsh critic…
SkillAFreshness: AClaude Code +9 - 0.559score
feature-ticket-delegator
jonnyasmith
Resolve and deterministically plan the descendants of a supplied root issue, feature, or local Markdown item, then delegate each ready work item to a fresh…
SkillAFreshness: AClaude Code +9 - 0.559score
architecture
jonnyasmith
Creates or updates root ARCHITECTURE.md from verified implementation.
SkillAFreshness: AClaude Code +9 - 0.559score
goal-prompt
jonnyasmith
Turn a task with a runnable verifier into a paste-ready Claude Code /goal prompt that runs a verification loop — the session orchestrates, fans out to an…
SkillAFreshness: AClaude Code +9 - 0.556score
gauntlet-kit
jonnyasmith
Turn a goal plus whatever reference material the user supplies into a bar that builders and critics grade against, and hand back the prompt that runs the loop…
SkillAFreshness: AClaude Code +9 - 0.556score
build-change
jonnyasmith
Build a change from its plan.html as an orchestrator only: a Workflow runs each plan step through fresh implementer, adversarial critic and fixer agents until…
SkillAFreshness: AClaude Code +9 - 0.556score
dev-wiki
jonnyasmith
Query the user's dev-wiki when they explicitly ask to use their dev-wiki or personal developer wiki, including by supplying its path.
SkillAFreshness: AClaude Code +9 - 0.556score
discovery
jonnyasmith
Build a visual, evidence-backed architecture discovery report for a feature or app area, then interactively resolve the highest-impact gaps.
SkillAFreshness: AClaude Code +9 - 0.554score
discussion
jonnyasmith
Enter discussion mode - talk through a problem, design, or codebase without changing anything.
SkillAFreshness: AClaude Code +9 - 0.552score
build-change
jonnyasmith
Build a change from its plan.html as an orchestrator only: an eval-cell workflow runs each plan step through fresh implementer, adversarial critic and fixer…
SkillAFreshness: AClaude Code +9 - 0.534score
code-review
jonnyasmith
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillAFreshness: AClaude Code +9 - 0.519score
gauntlet-workflow
jonnyasmith
Runs a gauntlet loop as a workflowz eval cell instead of a pasted prompt - a deterministic outer loop that builds each piece, grades it with a fresh harsh…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 3, 2026 (28 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/jonnyasmith/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from jonnyasmith
- 0.559score
goal-prompt
jonnyasmith
Turn a task with a runnable verifier into a paste-ready Claude Code /goal prompt that runs a verification loop — the session orchestrates, fans out to an…
SkillAFreshness: AClaude Code +9 - 0.559score
architecture
jonnyasmith
Creates or updates root ARCHITECTURE.md from verified implementation.
SkillAFreshness: AClaude Code +9 - 0.559score
feature-ticket-delegator
jonnyasmith
Resolve and deterministically plan the descendants of a supplied root issue, feature, or local Markdown item, then delegate each ready work item to a fresh…
SkillAFreshness: AClaude Code +9 - 0.559score
gauntlet-workflow
jonnyasmith
Runs a gauntlet loop as a Workflow script instead of a pasted prompt - a deterministic outer loop that builds each piece, grades it with a fresh harsh critic…
SkillAFreshness: AClaude Code +9 - 0.556score
discovery
jonnyasmith
Build a visual, evidence-backed architecture discovery report for a feature or app area, then interactively resolve the highest-impact gaps.
SkillAFreshness: AClaude Code +9 - 0.556score
dev-wiki
jonnyasmith
Query the user's dev-wiki when they explicitly ask to use their dev-wiki or personal developer wiki, including by supplying its path.
SkillAFreshness: AClaude 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 gauntlet-loop 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
gauntlet-loop skill. Agent Mart. https://agentmart.dev/skills/jonnyasmith-gauntlet-loop (last updated 2026-10-24)