arena
Generate independent candidates for one task, score them against a private rubric, select a base, and synthesize the strongest coherent result.
Skill by kyeshmz
Chalk Labs
Need help deploying arena?
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/kyeshmz-arena
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/arena
What's inside
- Skill name
arena- Description
- Generate independent candidates for one task, score them against a private rubric, select a base, and synthesize the strongest coherent result. Use for @arena, arena this, throw it in the arena, or competing attempts at a nontrivial artifact.
- License
- MIT
- Metadata
- opencode/autoinvoke: false
- Instructions
- 48 lines in SKILL.md · view on GitHub
Files (3)
- LICENSE
- SKILL.md
- shared-rules.md · references/
SKILL.md (first lines)
# Arena Produce one verified artifact from competing attempts. Keep Frame, Fan out, Cross-judge, Pick, Graft, and Verify in a task list or checklist. Read `references/shared-rules.md`. Resolve resources from the loaded skill base. Run project commands in the target repository or assigned worktree. Load `swarm` for isolation, handoff records, and reconciliation. This skill adds candidate comparison and synthesis, not a scheduler or another entry mode. ## Frame 1. State the artifact, requested scope, and observable done predicate. Use the same task and grounding for every candidate. 2. Define three to six concrete, gradeable success criteria before dispatch. Keep the selection rubric out of candidate prompts. The rubric is for the parent and judge, not a target candidates can game. 3. Use two candidates by default. Add seats only for distinct directions or justified generation coverage. Inherit the current model by omitting `model`. Use different models only when the user authorizes them and the host confirms exact IDs. No role file, family fallback, or guessed model is required. Same-model replicas are not cross-model review. 4. Give each writer a separate worktree or disjoint artifact directory. Include generated output, Git state, ports, and mutable fixtures in the ownership check. Serialize code writes if isolation is unavailable. A read-only request permits no repository edits or external writes. Candidates return text when artifact writes are not authorized. ## Fan out Use the host's native `subagent` tool with an advertised `chef` or suitable `general` agent, a short `description`, a self-contained `prompt`, and `background: true` for independent work. Do not pass Cursor-only arguments. Launch candidates together up to the resource cap and wait for completion notifications without polling. Every brief includes the original task, accumulated constraints, absolute working directory, grounding pointers, owned paths, allowed writes, artifact contract, verification commands, and a short rationale naming alternatives rejected. Forbid nested fanout and shared coordination writes. Omit `model` unless Frame authorized it. Account for every launched child before finishing. If a candidate returns no usable output, record the dropout and compare the remaining candidates. If the caller requires two shapes and fewer survive, obtain another bounded attempt or report the comparison incomplete. When delegation is unavailable, compare local drafts only if useful and label the loss of independence. ## Cross-judge After all candidate writers stop, give one fresh read-only judge the rubric and path-labeled candidates. Explicitly forbid edits, commits, and external writes. Ask for criterion-level scores, a recommended base, and reasons. Use a different model family only when authorized and available. Report a same-model or unavailable judge honestly. Run judging alongside the parent's own reading. Do not expose candidate self-rankings as evidence or ask the judge to inspect unfinished output. ## Pick Read every candidate end to end. Score each criterion, then compare the judge's reasoning. A disagreement requires examining both rationales and the rubric, not averaging scores blindly. Pick the base a maintainer can extend without breaking invariants. Break a close tie in favor of clearer ownership or the smaller useful API. ## Graft Revisit every losing candidate for worthwhile parts. Usually one or two ideas deserve adapting. Integrate them under the base's mental model rather than pasting incompatible pieces together. Use `principle-redesign-from-first-principles` when the combination changes the shape. If candidates converge, record consensus and skip unnecessary grafting. If they diverge because the task was underspecified, reframe before rerunning. Do not average incompatible interpretations into an artifact nobody designed. ## Verify Verify the synthesized artifact itself against the done predicate through the project's existing harness or public surface. Candidate checks do not prove a combined result. If a missed failure came from the task contract, reframe. If a candidate already caught it, revisit the graft. Do not hide the failure with an unrelated patch. Do not delete worktrees, commit, push, open a PR, install globally, or make external writes without authorization. Preserve discarded candidates until any requested cleanup has an approved exact scope. ## Report Return the synthesized artifact and a short synthesis note. Include the rubric, chosen base and why, judge verdict and limitations, each graft with its source, rejected ideas and reasons, convergence or divergence, dropouts, parent verification, and remaining gaps.
From kyeshmz/jiro, MIT.
More from kyeshmz/jiro
- 0.570score
create-formal-verification-skill
kyeshmz
Generate and prove a project-local formal verification skill for a high-risk invariant, race, parser, retry, or unsafe operation.
SkillAFreshness: AClaude Code +9 - 0.570score
jiro
kyeshmz
Jiro's verified engineering workflow for OpenCode.
SkillAFreshness: AClaude Code +9 - 0.567score
how
kyeshmz
Use for how does X work, code walkthroughs before changing something, and placement, ownership, or layering questions such as where should this live or which…
SkillAFreshness: AClaude Code +9 - 0.567score
interrogate
kyeshmz
Challenge code or a design with independent adversarial reviewers and synthesize a pragmatic verdict without applying fixes.
SkillAFreshness: AClaude Code +9 - 0.567score
architect
kyeshmz
Sketch caller usage, types, signatures, ownership, and module boundaries before implementation.
SkillAFreshness: AClaude Code +9 - 0.567score
automate-me
kyeshmz
Turn the user's working preferences into a personal style skill or update one from explicit feedback and scoped conversation evidence.
SkillAFreshness: AClaude Code +9 - 0.567score
benchmark-checklist
kyeshmz
Vet a performance claim against its limiter, production tuning, physical limits, errors, repeatability, relevance, and proof that timed work happened.
SkillAFreshness: AClaude Code +9 - 0.567score
blast-radius
kyeshmz
Trace what a change can break beyond its diff and prove the load-bearing safety fact against real code.
SkillAFreshness: AClaude Code +9 - 0.567score
create-subagent
kyeshmz
Create or update a reusable OpenCode subagent with a clear role, required skills, permissions, and reporting contract.
SkillAFreshness: AClaude Code +9 - 0.567score
delegate
kyeshmz
Scope work into bounded child-agent tasks, write self-contained briefs, and verify their results.
SkillAFreshness: AClaude Code +9 - 0.567score
figure-it-out
kyeshmz
Design and execute an auditable workflow when no narrower recipe fits a large migration, multi-part change, or unattended task.
SkillAFreshness: AClaude Code +9 - 0.567score
ketchup
kyeshmz
Catch the user up on changes in this chat since their previous message and list every decision waiting on them with enough context to decide.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kyeshmz/jiro
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kyeshmz
- 0.570score
jiro
kyeshmz
Jiro's verified engineering workflow for OpenCode.
SkillAFreshness: AClaude Code +9 - 0.570score
create-formal-verification-skill
kyeshmz
Generate and prove a project-local formal verification skill for a high-risk invariant, race, parser, retry, or unsafe operation.
SkillAFreshness: AClaude Code +9 - 0.567score
how
kyeshmz
Use for how does X work, code walkthroughs before changing something, and placement, ownership, or layering questions such as where should this live or which…
SkillAFreshness: AClaude Code +9 - 0.567score
architect
kyeshmz
Sketch caller usage, types, signatures, ownership, and module boundaries before implementation.
SkillAFreshness: AClaude Code +9 - 0.567score
automate-me
kyeshmz
Turn the user's working preferences into a personal style skill or update one from explicit feedback and scoped conversation evidence.
SkillAFreshness: AClaude Code +9 - 0.567score
interrogate
kyeshmz
Challenge code or a design with independent adversarial reviewers and synthesize a pragmatic verdict without applying fixes.
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 arena 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
arena skill. Agent Mart. https://agentmart.dev/skills/kyeshmz-arena (last updated 2026-10-24)