Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
YOLO mode. An agent skill from davepoon/buildwithclaude.
$ npx skills add davepoon/buildwithclaude --skill ops-yolo -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install davepoon/buildwithclaude ops-yolo --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/claude-ops/skills/ops-yolo .claude/skills/ops-yolo && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ops-yolo" agent skill from https://github.com/davepoon/buildwithclaude/tree/main/plugins/claude-ops/skills/ops-yolo into .claude/skills/ops-yolo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-yolo", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/davepoon/buildwithclaude/tree/main/plugins/claude-ops/skills/ops-yoloType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add davepoon/buildwithclaude --skill ops-yolo -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install davepoon/buildwithclaude ops-yolo --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/claude-ops/skills/ops-yolo .agents/skills/ops-yolo && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ops-yolo" agent skill from https://github.com/davepoon/buildwithclaude/tree/main/plugins/claude-ops/skills/ops-yolo into .agents/skills/ops-yolo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-yolo", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add davepoon/buildwithclaude --skill ops-yolo -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install davepoon/buildwithclaude ops-yolo --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/claude-ops/skills/ops-yolo .cursor/skills/ops-yolo && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ops-yolo" agent skill from https://github.com/davepoon/buildwithclaude/tree/main/plugins/claude-ops/skills/ops-yolo into .cursor/skills/ops-yolo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-yolo", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/davepoon/buildwithclaude.git --path plugins/claude-ops/skills/ops-yolo--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add davepoon/buildwithclaude --skill ops-yolo -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install davepoon/buildwithclaude ops-yolo --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/claude-ops/skills/ops-yolo .gemini/skills/ops-yolo && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ops-yolo" agent skill from https://github.com/davepoon/buildwithclaude/tree/main/plugins/claude-ops/skills/ops-yolo into .gemini/skills/ops-yolo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-yolo", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install davepoon/buildwithclaude ops-yoloInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add davepoon/buildwithclaude --skill ops-yolo -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/claude-ops/skills/ops-yolo .github/skills/ops-yolo && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ops-yolo" agent skill from https://github.com/davepoon/buildwithclaude/tree/main/plugins/claude-ops/skills/ops-yolo into .github/skills/ops-yolo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-yolo", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add davepoon/buildwithclaude --skill ops-yolo -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install davepoon/buildwithclaude ops-yolo --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/claude-ops/skills/ops-yolo .opencode/skills/ops-yolo && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ops-yolo" agent skill from https://github.com/davepoon/buildwithclaude/tree/main/plugins/claude-ops/skills/ops-yolo into .opencode/skills/ops-yolo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops-yolo", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ops-yoloYOLO mode. An agent skill from davepoon/buildwithclaude.
Ops Yolo is an agent skill from davepoon/buildwithclaude. YOLO mode. Spawns 4 parallel C-suite agents (CEO, CTO, CFO, COO). Each analyzes the business from their perspective using ALL available data. Produces unfiltered Hard Truths report. After user types YOLO, autonomously runs the business for a day using /loop.
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Computer vision. It works with Amazon Web Services. The repository describes itself as: A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 10bfc43. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
BashReadGrepGlobSkillAgentAskUserQuestionTeamCreateSendMessageTaskCreate…and 14 more on the same allowed-tools line.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
ghawsjqFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use gh and aws, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
GITHUB_TOKENSENTRY_AUTH_TOKENLINEAR_API_KEYAWS_ACCESS_KEY_IDFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ops Yolo loads about 2.9k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 980 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Bash, Read, Grep, Glob, Skill, Agent, AskUserQuestion, TeamCreate, SendMessage, TaskCreate, TaskUpdaAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from davepoon/buildwithclaude at commit 10bfc43, republished under its MIT licence (© davepoon). 980 words, ~2,893 tokens.
.claude/skills/ops-yolo/SKILL.md (or your agent's skills folder).Before YOLO analysis, load:
cat ${CLAUDE_PLUGIN_DATA_DIR:-$HOME/.claude/plugins/data/ops-ops-marketplace}/preferences.json — read owner, timezone, yolo_enabled, all channel configscat ${CLAUDE_PLUGIN_DATA_DIR}/daemon-health.json — all services must be healthy for comprehensive analysis${CLAUDE_PLUGIN_DATA_DIR}/memories/ — contact profiles, preferences, topics, donts. YOLO agents need maximum context.| Command | Usage | Output |
|---|---|---|
aws ce get-cost-and-usage --time-period Start=<YYYY-MM-DD>,End=<YYYY-MM-DD> --granularity MONTHLY --metrics "UnblendedCost" --output json | Current month spend | Cost JSON |
| Command | Usage | Output |
|---|---|---|
gh pr list --repo <owner/repo> --json number,title,statusCheckRollup,reviewDecision,mergeable,isDraft | Open PRs with status | JSON array |
gh pr merge <n> --repo <repo> --squash --admin | Squash merge PR | Merge result |
gh run list --limit 20 --json status,conclusion,name,headBranch,createdAt | Recent CI runs | JSON array |
If CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set, use Agent Teams instead of fire-and-forget subagents for the C-suite analysis (Phase 2). This enables:
Team setup (only when flag is enabled):
TeamCreate("yolo-csuite")
Agent(team_name="yolo-csuite", name="ceo", subagent_type="ops:yolo-ceo", ...)
Agent(team_name="yolo-csuite", name="cto", subagent_type="ops:yolo-cto", ...)
Agent(team_name="yolo-csuite", name="cfo", subagent_type="ops:yolo-cfo", ...)
Agent(team_name="yolo-csuite", name="coo", subagent_type="ops:yolo-coo", ...)After initial analysis, use SendMessage(to="cto", content="CFO flagged $400/mo in waste — does this change your tech-debt ranking?") or similar to cross-pollinate findings between peer agents. The main /ops:yolo orchestrator (this skill) then reads all four analysis files (ceo-analysis.md, cto-analysis.md, cfo-analysis.md, coo-analysis.md) and synthesizes them into the Hard Truths report. yolo-ceo is a parallel peer, not the synthesizer.
If the flag is NOT set, fall back to standard parallel subagents (fire-and-forget, no mid-task steering).
Run all of these simultaneously:
${CLAUDE_PLUGIN_ROOT}/bin/ops-infra 2>/dev/null || echo '{}'${CLAUDE_PLUGIN_ROOT}/bin/ops-git 2>/dev/null || echo '[]'${CLAUDE_PLUGIN_ROOT}/bin/ops-prs 2>/dev/null || echo '[]'${CLAUDE_PLUGIN_ROOT}/bin/ops-ci 2>/dev/null || echo '[]'${CLAUDE_PLUGIN_ROOT}/bin/ops-unread 2>/dev/null || echo '{}'aws ce get-cost-and-usage --time-period "Start=$(date +%Y-%m-01),End=$(date +%Y-%m-%d)" --granularity MONTHLY --metrics "UnblendedCost" --output json 2>/dev/null || echo '{}'cat "${CLAUDE_PLUGIN_ROOT}/scripts/registry.json" 2>/dev/null || echo '{}'${CLAUDE_PLUGIN_ROOT}/bin/ops-external 2>/dev/null || echo '[]'for d in $(jq -r '.projects[] | select(.gsd == true) | .paths[]' "${CLAUDE_PLUGIN_ROOT}/scripts/registry.json" 2>/dev/null); do
expanded="${d/#\~/$HOME}"
[ -f "$expanded/.planning/STATE.md" ] && echo "=== $(basename $expanded) ===" && cat "$expanded/.planning/STATE.md" && echo "---"
doneSpawn these 4 agents simultaneously using all pre-gathered data as context. Each writes their analysis to a file in /tmp/yolo-[session]/:
Uses agents/yolo-ceo.md. Writes /tmp/yolo-[session]/ceo-analysis.md.
Uses agents/yolo-cto.md. Writes /tmp/yolo-[session]/cto-analysis.md.
Uses agents/yolo-cfo.md. Writes /tmp/yolo-[session]/cfo-analysis.md.
Uses agents/yolo-coo.md. Writes /tmp/yolo-[session]/coo-analysis.md.
This skill (the main orchestrator) is the synthesizer — NOT yolo-ceo. After all 4 parallel agents complete and have written their analysis files to /tmp/yolo-[session]/{ceo,cto,cfo,coo}-analysis.md, read all four files here in the main context and synthesize them into a unified report:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
YOLO ► HARD TRUTHS REPORT — [date]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CEO: [1-2 brutal strategic truths]
CTO: [1-2 brutal technical truths]
CFO: [1-2 brutal financial truths]
COO: [1-2 brutal operational truths]
──────────────────────────────────────────────────────
CONSENSUS: The #1 thing that matters today is:
[single most important action, no sugar-coating]
──────────────────────────────────────────────────────
Full analysis files saved to:
/tmp/yolo-[session]/ceo-analysis.md
/tmp/yolo-[session]/cto-analysis.md
/tmp/yolo-[session]/cfo-analysis.md
/tmp/yolo-[session]/coo-analysis.md
──────────────────────────────────────────────────────
Type YOLO to hand over the controls.
I'll run your business autonomously for the next day.
This means: closing inbox, merging ready PRs,
fixing fires, advancing GSD phases, triaging issues.
Or pick an analysis to read:
──────────────────────────────────────────────────────Use batched AskUserQuestion calls (max 4 options each):
AskUserQuestion call 1:
[Read CEO analysis]
[Read CTO analysis]
[Read CFO analysis]
[More...]AskUserQuestion call 2 (only if "More..."):
[Read COO analysis]
[Execute top recommendation now]
[Type YOLO to go autonomous]If user types YOLO (all caps), enter autonomous mode via /loop.
Before starting, use AskUserQuestion to confirm scope:
YOLO mode will autonomously execute these steps:
1. Inbox — reply to humans, archive automated
2. Fires — fix CRITICAL/HIGH production issues
3. PRs — merge ready PRs (CI green, approved)
4. Triage — auto-resolve confirmed-fixed issues
5. GSD — advance highest-priority phase
6. Linear — sync sprint board
7. Deploy — trigger pending deploys
8. Report — summary
[Run all 8 steps] [Pick which steps to run] [Cancel]If user picks "Pick which steps", show steps as multiSelect via batched AskUserQuestion calls (max 4 options each):
Call 1: [Inbox], [Fires], [PRs], [More steps...]
Call 2 (if "More steps..."): [Triage], [GSD], [Linear], [More steps...]
Call 3 (if "More steps..."): [Deploy], [Report], [Done selecting]
Run the selected steps in sequence, reporting after each step.
Per-step confirmations (use AskUserQuestion before EACH destructive action):
[Send all N replies] / [Review each one] / [Skip inbox] before sending any messages[Dispatch fix agent] / [Skip] before each agent dispatch[Merge all N ready PRs] / [Pick which ones] / [Skip] before merging[Auto-resolve all N confirmed-fixed] / [Review each] / [Skip] before closing[Deploy all] / [Pick which] / [Skip] before triggering[Execute] / [Skip] individually. NEVER batch destructive infra actions.Report-driven execution: When the user approves executing recommendations from the Hard Truths report:
/tmp/yolo-[session]/*.md)⚠️ REQUIRES CONFIRMATIONAskUserQuestion with the exact command that will run, the expected outcome, and the source report (CTO/CFO/COO)After each step, check if new fires have appeared before proceeding. Report final summary when done.
If $ARGUMENTS is analyze or empty, go straight to Phase 1.
If $ARGUMENTS is YOLO, skip to Phase 4.
If $ARGUMENTS is report, skip to Phase 3 (reads existing analysis files if present).
Use TaskCreate at the start of Phase 4 to create a task for each YOLO step. Update with TaskUpdate as each completes. This gives the user a live progress view across the autonomous run.
Before Phase 4 execution, use EnterPlanMode to present the full execution plan. The user reviews what YOLO will do, approves or modifies, then ExitPlanMode to begin execution.
After Phase 4 completes, offer to schedule recurring YOLO via AskUserQuestion:
[Schedule daily YOLO at 9am] [Schedule weekly Monday briefing] [No schedule]Use CronCreate if selected. Use CronList/CronDelete to manage existing schedules.
When YOLO dispatches fix agents or triggers deploys, use Monitor to stream CI output in real-time instead of polling with sleep loops.
Use WebFetch to pull Grafana dashboards, Sentry event details, or AWS status pages when MCPs are unavailable. Use WebSearch to find context on production errors (e.g., known AWS outages).
© davepoon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugins/claude-ops/skills/ops-yolo of davepoon/buildwithclaude.
Open the folder on GitHubat commit 10bfc43
Ops Yolo next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ops Yolo this skilldavepoon/buildwithclaude | 3.6k | — | ~2.9k | Automated safety check: Notes | MIT | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.3k | Automated safety check: Pass | MIT | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~1.7k | Automated safety check: Pass | MIT | |
| SageMaker Serving Image Selectionhuggingface/skills | 11k | 1 repos | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Yolo Master AgentTencent/YOLO-Master | 742 | — | ~755 | Automated safety check: Pass | AGPL-3.0 | |
| Video Understandjjyaoao/HelloAgents | 3.2k | 1 repos | ~6.2k | Automated safety check: Pass | MIT |
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
huggingface/skills
Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.
Tencent/YOLO-Master
A skill your agent uses when the user wants to run a YOLO-Master task (train/val/predict/track/export/benchmark) or use the Agent Skill dispatcher.
jjyaoao/HelloAgents
Implement specialized video understanding capabilities using the z-ai-web-dev-sdk.
edwardsanchez/MotionEyes
Pixel-based motion and UI change analysis from frame sequences or screenshots using computer vision and visual comparison.
davepoon/buildwithclaude
A skill your agent uses when the user asks to "analyze video", "watch this video", "what happens in this video", "describe this clip", "review this footage", "classify these videos", "compare…
davepoon/buildwithclaude
Activate this agent for any future-oriented question that requires deep quantitative analysis, historical precedents, and structured scenario planning.
davepoon/buildwithclaude
Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data.
davepoon/buildwithclaude
Download YouTube videos with customizable quality and format options.
davepoon/buildwithclaude
Discover Atlas Cloud image and video models, inspect their live schemas, and submit one confirmed media generation request with bounded GET polling.
davepoon/buildwithclaude
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives.
Works with
Categories
YOLO mode. An agent skill from davepoon/buildwithclaude. Ops Yolo is an agent skill from davepoon/buildwithclaude. YOLO mode.
Ops Yolo fits situations like: tasks that involve Computer vision.
Run `npx skills add davepoon/buildwithclaude --skill ops-yolo -a claude-code`. Or copy the skill folder (plugins/claude-ops/skills/ops-yolo in davepoon/buildwithclaude) into .claude/skills/ops-yolo in your project. Claude Code loads it when a task matches its description.
Run `npx skills add davepoon/buildwithclaude --skill ops-yolo -a codex`. Or copy the skill folder (plugins/claude-ops/skills/ops-yolo in davepoon/buildwithclaude) into .agents/skills/ops-yolo in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davepoon/buildwithclaude --skill ops-yolo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ops-yolo, .gemini/skills/ops-yolo, .github/skills/ops-yolo and .opencode/skills/ops-yolo in your project.
Going by SKILL.md and its folder, Ops Yolo needs the command-line tools its instructions call (gh, aws and jq) and credentials named GITHUB_TOKEN, SENTRY_AUTH_TOKEN, LINEAR_API_KEY and AWS_ACCESS_KEY_ID. Our summary lists: A credential in GITHUB_TOKEN; A credential in SENTRY_AUTH_TOKEN. Its frontmatter pre-approves these tools: Bash, Read, Grep, Glob, Skill, Agent, AskUserQuestion, TeamCreate, SendMessage, TaskCreate, TaskUpdate, TaskList, EnterPlanMode, ExitPlanMode, CronCreate, CronList, CronDelete, Monitor, WebFetch, WebSearch, mcp__linear__list_issues, mcp__claude_ai_Vercel__list_deployments, mcp__claude_ai_Slack__slack_search_public_and_private, mcp__claude_ai_Gmail__search_threads.
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Ops Yolo is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ops Yolo: Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars), SageMaker Serving Image Selection (huggingface/skills, 11k stars) and Yolo Master Agent (Tencent/YOLO-Master, 742 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
davepoon (a GitHub user) maintains it in davepoon/buildwithclaude, which has 3,604 GitHub stars. The repository holds 245 skills in this directory. The repository was last updated on October 6, 2026.
Source: davepoon/buildwithclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.