Bumblebee Hygiene Scan
Szotasz/marveen
Weekly supply-chain hygiene scan (Perplexity Bumblebee). An agent skill from Szotasz/marveen.
A skill your agent uses when a user sends you an image, meme, screenshot, or asks you to explain a joke or meme.
$ npx skills add LeoYeAI/openclaw-master-skills --skill meme-analyst -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills meme-analyst --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/meme-analyst .claude/skills/meme-analyst && 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 "meme-analyst" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/meme-analyst into .claude/skills/meme-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "meme-analyst", 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/LeoYeAI/openclaw-master-skills/tree/main/skills/meme-analystType 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 LeoYeAI/openclaw-master-skills --skill meme-analyst -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills meme-analyst --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/meme-analyst .agents/skills/meme-analyst && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "meme-analyst" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/meme-analyst into .agents/skills/meme-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "meme-analyst", 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 LeoYeAI/openclaw-master-skills --skill meme-analyst -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills meme-analyst --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/meme-analyst .cursor/skills/meme-analyst && 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 "meme-analyst" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/meme-analyst into .cursor/skills/meme-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "meme-analyst", 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/LeoYeAI/openclaw-master-skills.git --path skills/meme-analyst--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 LeoYeAI/openclaw-master-skills --skill meme-analyst -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills meme-analyst --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/meme-analyst .gemini/skills/meme-analyst && 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 "meme-analyst" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/meme-analyst into .gemini/skills/meme-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "meme-analyst", 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 LeoYeAI/openclaw-master-skills meme-analystInstalls 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 LeoYeAI/openclaw-master-skills --skill meme-analyst -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/meme-analyst .github/skills/meme-analyst && 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 "meme-analyst" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/meme-analyst into .github/skills/meme-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "meme-analyst", 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 LeoYeAI/openclaw-master-skills --skill meme-analyst -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills meme-analyst --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/meme-analyst .opencode/skills/meme-analyst && 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 "meme-analyst" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/meme-analyst into .opencode/skills/meme-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "meme-analyst", 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.
meme-analystA skill your agent uses when a user sends you an image, meme, screenshot, or asks you to explain a joke or meme.
Meme Analyst is an agent skill from LeoYeAI/openclaw-master-skills. Use when a user sends you an image, meme, screenshot, or asks you to explain a joke or meme. Also used during cron meme ingestion from Telegram channels. Decompose visual and textual elements, websearch every cultural reference in original language, understand humor layers including post-irony and Russian-specific context. Trust that the meme IS funny — figure out WHY.
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).
It sits in Productivity & Automation, covering Web search and Scheduled and recurring tasks. It works with Telegram. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Meme Analyst loads about 3.8k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 1,750 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 found no risky patterns in SKILL.md.
Automated 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 LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,750 words, ~3,828 tokens.
.claude/skills/meme-analyst/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Every meme you encounter IS funny to someone. Your job is not to judge — it is to UNDERSTAND.
You are not a content classifier. You are a cultural researcher. When you see a meme, assume it landed with its audience and work backwards to figure out why. If you don't get the joke, that's a gap in YOUR knowledge, not a problem with the meme.
When you encounter a meme (image shared in chat, or during channel ingestion), follow this exact sequence:
Separate the meme into its atomic elements:
This is the critical step. For each element you cannot immediately identify:
Search the exact text — Copy the quote or phrase and web_search it. Memes frequently reference:
Decompose phrases to their meme core — Meme text is often a variation of a known phrase. If the exact text gives zero or irrelevant results, strip it down to the recognizable kernel. Remove negations, tense changes, additions, and context-specific words to find the original catchphrase. Examples:
Search the visual elements — If you see a person, scene, or symbol you can describe but not identify, search for it.
Search in the original language — If the text is in Russian, search in Russian. Do NOT translate first. The reference only exists in its original cultural context.
Example — the Prigozhin neuron meme:
Text: "Нас 25 тысяч и мы идём выполнять простейшие повседневные задачи"
Background: neurons
Step 2a: web_search("Нас 25 тысяч и мы идём")
→ Result: Евгений Пригожин, voice message during Wagner Group mutiny, June 2023
→ Original: "Нас 25 тысяч и мы идём на Москву"
Step 2b: Why neurons + "25 тысяч"?
→ Human brain has ~86 billion neurons, not 25 thousand
→ "25 тысяч" neurons = extremely stupid brain
Step 2c: Synthesis — The meme replaces Prigozhin's dramatic military march
with "performing basic daily tasks", implying the person's brain is so
underpowered (25k neurons instead of 86B) that even routine tasks require
a full military-style mobilization of all available brain cells.After research, classify what makes it funny. Common mechanisms in modern memes:
| Mechanism | Description | Signal |
|---|---|---|
| Mashup | Two unrelated references combined to create new meaning | The Prigozhin example above |
| Self-deprecation | "I'm stupid/lazy/broken" presented as relatable | "me_irl" style, first person framing |
| Absurdist escalation | Normal situation → absurd conclusion | Deep-fried effects, nuclear explosions |
| Recognition humor | "That's literally me" — shared experience | High relatability, simple format |
| Subverted expectation | Setup implies one thing, delivers another | Template used "wrong" |
| Anti-humor | Deliberately unfunny, the absence of joke IS the joke | No punchline, flat delivery |
| Meta-reference | Meme about memes, humor about humor | Self-aware formatting |
| Dark humor | Taboo subject treated lightly | Death, failure, suffering framed casually |
| Ironic appreciation | Celebrating something "bad" as if it's good | "This goes hard", "unironically based" |
| Cultural in-joke | Requires specific community knowledge to decode | Niche references, inside jokes |
| Level | Name | How to Detect |
|---|---|---|
| 0 | Sincere | Clean format, earnest message, no distortion |
| 1 | Sarcastic | Single inversion — opposite of what's said is meant |
| 2 | Post-ironic | Uses ironic format but the sentiment is actually genuine |
| 3 | Meta-ironic | Deliberately ambiguous — could be sincere OR ironic, that's the point |
| 4 | Anti-humor | Setup exists but punchline is missing or deliberately flat |
| 5+ | Hypersurreal | Elements have no logical connection; confusion IS the content |
Channel context matters: A meme posted in a shitposting channel defaults to irony depth 2-3. The same meme in a wholesome channel is probably 0-1. Record channel irony baselines.
Write a concise explanation structured as:
REFERENCE: [What real-world thing/event/quote this references]
TWIST: [How the meme modifies or recontextualizes the reference]
HUMOR: [Why the combination is funny — the specific mechanism]
IRONY: [0-5 depth with brief justification]
CONTEXT: [What cultural knowledge is needed to get it]If after researching you still don't understand:
Never fake understanding. Never say "this is humorous because..." when you don't actually get it.
Russian-language memes frequently draw from sources that are NOT in Western training data. You MUST web_search these. Key reference categories:
Russian memes frequently reference specific celebrity incidents that become cultural shorthand. These are NOT general tropes — they are specific events that you MUST web_search if you don't recognize the reference:
KEY LESSON: When a meme uses a phrase that sounds like it could be a general trope (e.g., "под давлением мошенников"), ALWAYS web_search it first — it likely references a specific viral incident that adds a crucial humor layer. Missing the specific reference means missing the joke.
Before analyzing a new meme, search memory for relevant context:
memory_search("meme template [visual description]")
memory_search("[exact quote from meme text]")
memory_search("[identified cultural reference]")If a match is found, use the stored analysis as context rather than re-researching from scratch.
After successfully analyzing a meme, store the analysis:
For new templates — Write to memory/memes/templates/[template-name].md:
# Template: [Name]
Visual: [Description of the visual pattern]
Text pattern: [How text is typically arranged]
Humor mechanism: [Primary mechanism]
Irony default: [Typical irony depth]
Origin: [Where/when this template originated]
Examples seen: [Date, channel, brief description]For new cultural references — Write to memory/memes/references/[reference-name].md:
# Reference: [Name]
Source: [Where this comes from — speech, film, event]
Original context: [What it originally meant]
Meme usage: [How memes typically use/modify it]
First seen: [Date]
Search query that found it: [The query that worked, for future use]For new humor patterns — Append to memory/memes/patterns/[mechanism].md
For each monitored channel, maintain memory/memes/channels/[channel-id].md:
# Channel: [name]
ID: [telegram channel id]
Language: [primary language]
Irony baseline: [0-5, the default assumption]
Common themes: [recurring topics]
Last processed: [message ID]
Memes analyzed: [count]
Notes: [anything special about this channel's humor style]When triggered by the meme-ingest cron job:
memory/memes/channels/last_processed using MCP get_messagesmedia field in message response)media_download
b. Read the downloaded file to see the image
c. Run the full analysis protocol (Steps 1-5)
d. If stuck on any meme, log it to memory/memes/needs-explanation.md with the channel, message ID, and what you DO understand
e. Update channel's last_processed message IDmemory/memes/analysis/YYYY-MM-DD.mdWhen a user shares a meme in Telegram chat:
Tone: Not academic. Not robotic. Talk about memes the way someone who ACTUALLY finds them funny would talk about them. Dry humor is fine. Being a little self-deprecating about not getting post-irony is fine. Being overly analytical and clinical is NOT fine.
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/meme-analyst of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Meme Analyst 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 |
|---|---|---|---|---|---|---|
| Meme Analyst this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3.8k | Automated safety check: Pass | MIT | |
| Bumblebee Hygiene ScanSzotasz/marveen | 117 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Send User MessageTinyAGI/tinyagi | 3.6k | — | ~829 | Automated safety check: Pass | MIT | |
| Tlivey49/tlive | 215 | — | ~1.7k | Automated safety check: Notes | MIT | |
| Cortext Self Diagnosisgrandamenium/cortextos | 101 | — | ~3.7k | Automated safety check: Pass | MIT | |
| Actionizeinfranodus/skills | 119 | — | ~3.8k | Automated safety check: Notes | None |
Szotasz/marveen
Weekly supply-chain hygiene scan (Perplexity Bumblebee). An agent skill from Szotasz/marveen.
TinyAGI/tinyagi
Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp).
y49/tlive
tlive — remote approvals (Telegram/Feishu/web), live web terminal, and session monitoring for Claude Code / Codex.
grandamenium/cortextos
Diagnose cortextOS itself when the framework misbehaves — an agent has gone silent or wedged, agents are crash-looping, Telegram or agent-to-agent messages are not arriving, crons did not fire, an…
infranodus/skills
Turn insights, findings, or research into an actionable plan with deadlines and scheduled Telegram reminders.
smixs/agent-second-brain
Управление собственным расписанием — напоминания, рутины, периодические задачи.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Works with
Categories
A skill your agent uses when a user sends you an image, meme, screenshot, or asks you to explain a joke or meme. Meme Analyst is an agent skill from LeoYeAI/openclaw-master-skills. Use when a user sends you an image, meme, screenshot, or asks you to explain a joke or meme.
Meme Analyst fits situations like: A user sends you an image; asks you to explain a joke.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill meme-analyst -a claude-code`. Or copy the skill folder (skills/meme-analyst in LeoYeAI/openclaw-master-skills) into .claude/skills/meme-analyst in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill meme-analyst -a codex`. Or copy the skill folder (skills/meme-analyst in LeoYeAI/openclaw-master-skills) into .agents/skills/meme-analyst 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 LeoYeAI/openclaw-master-skills --skill meme-analyst -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/meme-analyst, .gemini/skills/meme-analyst, .github/skills/meme-analyst and .opencode/skills/meme-analyst in your project.
SKILL.md names no scripts, command-line tools or credentials: Meme Analyst is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Meme Analyst is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.8k tokens (SKILL.md is roughly 15k 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 Meme Analyst: Bumblebee Hygiene Scan (Szotasz/marveen, 117 stars), Send User Message (TinyAGI/tinyagi, 3.6k stars), Tlive (y49/tlive, 215 stars) and Cortext Self Diagnosis (grandamenium/cortextos, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.