benchmark-checklist
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
Skill by daryl-tg
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/daryl-tg-benchmark-checklist
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: documents
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/benchmark-checklist
What's inside
- Skill name
benchmark-checklist- Description
- Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
- License
- unknown
- Instructions
- 35 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 daryl-tg/deez-skills
- 0.565score
create-verification-skill
daryl-tg
Generate a project-owned verification skill, feature map, and control wrapper in the deez-skills hub so an agent can drive the real app and prove behavior.
SkillAFreshness: AClaude Code +9 - 0.557score
clanker-mode
daryl-tg
Daryl's agent style: routed playbooks, cited principles, proof on the real surface, and delivery by rebase-PR-squash.
SkillAFreshness: AClaude Code +9 - 0.556score
design
daryl-tg
Settle the shape before writing code: ground, sketch competing designs from the caller's usage, get approval, implement against the sketch, and scrap it when…
SkillAFreshness: AClaude Code +9 - 0.556score
create-formal-verification-skill
daryl-tg
Generate a project-owned skill in the deez-skills hub that formally verifies the code where a bug costs most and tests reach least, with whichever tool fits.
SkillAFreshness: AClaude Code +9 - 0.556score
automate-me
daryl-tg
Draft or refresh the operator's personal mode skill from real transcript history rather than from description.
SkillAFreshness: AClaude Code +9 - 0.555score
verify-om
daryl-tg
Use when a change to the `om` daemon or CLI (the openmarket-internal monorepo — packages/cli, packages/sdk, the runner, the action registry, the ops…
SkillAFreshness: AClaude Code +9 - 0.555score
verify-openfloor
daryl-tg
Use when a change to the OpenFloor mobile app (openmarket-chat-app, the Expo/React Native OpenMarket client) needs to be driven and proven on a real iOS…
SkillAFreshness: AClaude Code +9 - 0.555score
verify-kiyotaka
daryl-tg
Use when a change to the OpenMarket chart frontend (kiyotaka-frontend) needs to be driven and proven in the running app — starting a dev-server lane…
SkillAFreshness: AClaude Code +9 - 0.555score
verify-om-chat
daryl-tg
Use when a change to the OM Chat GUI (the openmarket-chat workspace — /rooms, /chat/, or the shared packages/chat-ui) needs to be driven and proven in the…
SkillAFreshness: AClaude Code +9 - 0.531score
correct
daryl-tg
Find the mistakes agents keep repeating in a repo and make each one impossible: architecture first, then types, a lint whose error names the fix, a test, and…
SkillAFreshness: AClaude Code +9 - 0.521score
adhd
daryl-tg
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time…
SkillBFreshness: BClaude Code +9 - 0.519score
authoring-orange-shared-packages
daryl-tg
Use when creating or changing a package in the orange-shared workspace (/Users/dboon/Gitlab/orange-shared, @orangecharts npm scope) — adding a shared…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/daryl-tg/deez-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from daryl-tg
- 0.565score
create-verification-skill
daryl-tg
Generate a project-owned verification skill, feature map, and control wrapper in the deez-skills hub so an agent can drive the real app and prove behavior.
SkillAFreshness: AClaude Code +9 - 0.557score
clanker-mode
daryl-tg
Daryl's agent style: routed playbooks, cited principles, proof on the real surface, and delivery by rebase-PR-squash.
SkillAFreshness: AClaude Code +9 - 0.556score
automate-me
daryl-tg
Draft or refresh the operator's personal mode skill from real transcript history rather than from description.
SkillAFreshness: AClaude Code +9 - 0.556score
create-formal-verification-skill
daryl-tg
Generate a project-owned skill in the deez-skills hub that formally verifies the code where a bug costs most and tests reach least, with whichever tool fits.
SkillAFreshness: AClaude Code +9 - 0.556score
design
daryl-tg
Settle the shape before writing code: ground, sketch competing designs from the caller's usage, get approval, implement against the sketch, and scrap it when…
SkillAFreshness: AClaude Code +9 - 0.555score
verify-om-chat
daryl-tg
Use when a change to the OM Chat GUI (the openmarket-chat workspace — /rooms, /chat/, or the shared packages/chat-ui) needs to be driven and proven in the…
SkillAFreshness: AClaude Code +9
Cite this page
benchmark-checklist skill. Agent Mart. https://agentmart.dev/skills/daryl-tg-benchmark-checklist (last updated 2026-10-24)