benchmark-to-suite
Convert an external benchmark into a skill folder with train/test eval suites for the mutation loop.
Skill by maxlbchung
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/maxlbchung-benchmark-to-suite
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: testing, 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
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/benchmark-to-suite
What's inside
- Skill name
benchmark-to-suite- Description
- Convert an external benchmark into a skill folder with train/test eval suites for the mutation loop. Use when asked to add a new benchmark, task family, or eval suite to this repo.
- License
- unknown
- Instructions
- 147 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (7)
- SKILL.md
- audit-tasks.mjs · scripts/
- match-json.py · scripts/graders/
- run-program.py · scripts/graders/
- smoke.py · scripts/
- suitegen.py · scripts/
- validate.mjs · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from maxlbchung/skill-mutator
- 0.516score
dscodebench
maxlbchung
Implementing data-science functions in Python (numpy/pandas/scipy/sklearn ecosystems) precisely to a written specification.
SkillBFreshness: BClaude Code +9 - 0.516score
multipl-racket
maxlbchung
Implement correct, idiomatic Racket functions from documented specs.
SkillBFreshness: BClaude Code +9 - 0.516score
multipl-lua
maxlbchung
Implement correct, idiomatic Lua 5.4 functions from documented specs.
SkillBFreshness: BClaude Code +9 - 0.511score
spreadsheetbench
maxlbchung
Carry out a user's requested manipulation on an Excel workbook and save the result in place — computed values, types preserved.
SkillBFreshness: BClaude Code +9 - 0.508score
mmtu
maxlbchung
Careful reading, navigation, and cell-exact reasoning over data tables of any size or serialization.
SkillBFreshness: BClaude Code +9 - 0.470score
db-and-artifacts
maxlbchung
Query mutator.db (runs, attempts, evaluations, cells, tests, genomes, excerpts) and navigate on-disk artifacts (genomes/, evals/, mutator-work/, .briefing.md).
SkillCFreshness: CClaude Code +9 - 0.469score
skill-authoring
maxlbchung
Fixed reference handed to every mutator agent — the core loop (billing model, per-round process, generality, critic rules) embedded in every mutate prompt…
SkillCFreshness: CClaude Code +9 - 0.467score
spider
maxlbchung
Translate a natural-language question about a relational database into a single correct SQL query, grounded in the schema and data you are given.
SkillCFreshness: CClaude Code +9 - 0.466score
babysit
maxlbchung
Supervise a mutation run round-by-round — launch with a single round (or attach to the run already active), judge each completed round, extend one round at a…
SkillCFreshness: CClaude Code +9 - 0.466score
dev-workflow
maxlbchung
Editing, testing, and debugging the skill-mutator codebase - server restart rules, zero-spend verification with fakes, test conventions, env seams, design…
SkillCFreshness: CClaude Code +9 - 0.465score
canitedit
maxlbchung
Apply a requested change to existing code — fix a bug, add a capability, or adjust behavior — delivering the complete edited version with everything not named…
SkillCFreshness: CClaude Code +9 - 0.463score
run-lifecycle
maxlbchung
Launch, monitor, stop, resume, or extend a mutation run; check whether a run is happening right now; interpret run status and cost.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 2, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/maxlbchung/skill-mutator
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from maxlbchung
- 0.516score
multipl-racket
maxlbchung
Implement correct, idiomatic Racket functions from documented specs.
SkillBFreshness: BClaude Code +9 - 0.516score
dscodebench
maxlbchung
Implementing data-science functions in Python (numpy/pandas/scipy/sklearn ecosystems) precisely to a written specification.
SkillBFreshness: BClaude Code +9 - 0.516score
multipl-lua
maxlbchung
Implement correct, idiomatic Lua 5.4 functions from documented specs.
SkillBFreshness: BClaude Code +9 - 0.511score
spreadsheetbench
maxlbchung
Carry out a user's requested manipulation on an Excel workbook and save the result in place — computed values, types preserved.
SkillBFreshness: BClaude Code +9 - 0.508score
mmtu
maxlbchung
Careful reading, navigation, and cell-exact reasoning over data tables of any size or serialization.
SkillBFreshness: BClaude Code +9 - 0.470score
db-and-artifacts
maxlbchung
Query mutator.db (runs, attempts, evaluations, cells, tests, genomes, excerpts) and navigate on-disk artifacts (genomes/, evals/, mutator-work/, .briefing.md).
SkillCFreshness: CClaude Code +9
Cite this page
benchmark-to-suite skill. Agent Mart. https://agentmart.dev/skills/maxlbchung-benchmark-to-suite (last updated 2026-10-24)