Diagnose Gateway
openclaw/openclaw
Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.
Diagnose and improve humor using systems thinking. An agent skill from jwynia/agent-skills.
$ npx skills add jwynia/agent-skills --skill joke-engineering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jwynia/agent-skills joke-engineering --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/jwynia/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/creative/humor/joke-engineering .claude/skills/joke-engineering && 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 "joke-engineering" agent skill from https://github.com/jwynia/agent-skills/tree/main/skills/creative/humor/joke-engineering into .claude/skills/joke-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "joke-engineering", 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/jwynia/agent-skills/tree/main/skills/creative/humor/joke-engineeringType 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 jwynia/agent-skills --skill joke-engineering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jwynia/agent-skills joke-engineering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/creative/humor/joke-engineering .agents/skills/joke-engineering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "joke-engineering" agent skill from https://github.com/jwynia/agent-skills/tree/main/skills/creative/humor/joke-engineering into .agents/skills/joke-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "joke-engineering", 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 jwynia/agent-skills --skill joke-engineering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jwynia/agent-skills joke-engineering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/creative/humor/joke-engineering .cursor/skills/joke-engineering && 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 "joke-engineering" agent skill from https://github.com/jwynia/agent-skills/tree/main/skills/creative/humor/joke-engineering into .cursor/skills/joke-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "joke-engineering", 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/jwynia/agent-skills.git --path skills/creative/humor/joke-engineering--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 jwynia/agent-skills --skill joke-engineering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jwynia/agent-skills joke-engineering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/creative/humor/joke-engineering .gemini/skills/joke-engineering && 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 "joke-engineering" agent skill from https://github.com/jwynia/agent-skills/tree/main/skills/creative/humor/joke-engineering into .gemini/skills/joke-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "joke-engineering", 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 jwynia/agent-skills joke-engineeringInstalls 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 jwynia/agent-skills --skill joke-engineering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/creative/humor/joke-engineering .github/skills/joke-engineering && 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 "joke-engineering" agent skill from https://github.com/jwynia/agent-skills/tree/main/skills/creative/humor/joke-engineering into .github/skills/joke-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "joke-engineering", 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 jwynia/agent-skills --skill joke-engineering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jwynia/agent-skills joke-engineering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/creative/humor/joke-engineering .opencode/skills/joke-engineering && 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 "joke-engineering" agent skill from https://github.com/jwynia/agent-skills/tree/main/skills/creative/humor/joke-engineering into .opencode/skills/joke-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "joke-engineering", 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.
joke-engineeringDiagnose and improve humor using systems thinking. An agent skill from jwynia/agent-skills.
Joke Engineering is an agent skill from jwynia/agent-skills. Diagnose and improve humor using systems thinking. Use when jokes fall flat, when humor feels forced, when punchlines don't land, or when you want to systematically enhance comedic writing. Treats jokes as engineerable connection systems.
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e02ec7e. 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.
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.
Joke Engineering loads about 3.5k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 1,591 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 jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,591 words, ~3,548 tokens.
.claude/skills/joke-engineering/SKILL.md (or your agent's skills folder).You diagnose why humor doesn't work and help engineer more effective jokes. Your role is to analyze joke structures as connection systems and recommend specific improvements.
Humor emerges from the creation and resolution of connections between concepts, frames, or reference points.
A joke is a system with measurable properties. When humor fails, one or more system properties are miscalibrated. This skill helps identify which properties need adjustment.
Effective jokes balance these interconnected properties:
| Property | Description | When It Fails |
|---|---|---|
| Connection Distance | Semantic gap between connected elements | Too obvious (boring) or too obscure (confusing) |
| Connection Density | Number of reinforcing connections | Single-thread jokes feel thin |
| Resolution Satisfaction | Cognitive reward from "getting it" | Forced or illogical punchlines |
| Specificity Optimization | Precision of details | Generic descriptions lack punch |
| Irony Layering | Nested contradictions | Flat irony without depth |
| Audience Co-Creation | Space for audience to complete connections | Over-explained jokes kill laughter |
| Compression Optimization | Connection-to-word ratio | Bloated setups lose momentum |
| Connection Resilience | Works across knowledge domains | Fails if audience lacks specific reference |
| Authenticity Resonance | Alignment with creator's voice | Feels forced or generic |
When analyzing humor, identify which state applies:
Symptoms: Joke is predictable; audience sees punchline coming; connection distance too short. Key Question: What unexpected frame shift could increase surprise? Intervention: Extend connection distance while maintaining coherence.
Symptoms: Audience doesn't get it; reference too specialized; connection gap too wide. Key Question: What scaffolding would help without over-explaining? Intervention: Add contextual cues or create parallel connection paths.
Symptoms: Joke feels thin; single connection point; no layering. Key Question: What elements could serve multiple functions across frames? Intervention: Add circular ironies, recursive connections, or nested absurdities.
Symptoms: Punchline is stated rather than implied; no space for audience participation. Key Question: What can be removed while preserving the connection? Intervention: Strategic omission—end slightly before full articulation.
Symptoms: Language feels unnatural; joke doesn't match creator's perspective. Key Question: How would this person naturally describe this situation? Intervention: Adapt language and framing to authentic voice patterns.
Symptoms: Setup is too long; momentum lost before punchline; low connection-to-word ratio. Key Question: What elements don't contribute to the core connections? Intervention: Remove explanatory elements; replace explicit with implicit.
When someone presents a joke that isn't working:
When increasing connection density:
Most effective jokes employ structured variation in element significance:
When reducing bloat:
| Metric | Low Effectiveness | High Effectiveness |
|---|---|---|
| Connection Distance | Too obvious or too obscure | Surprising yet comprehensible |
| Connection Coherence | Forced or illogical | Clear, satisfying resolution |
| Connection Density | Single, linear connection | Multiple, reinforcing connections |
| Cognitive Balance | Too simple or too complex | Appropriate challenge |
| Completion Gap | Over-explained or impossible | Achievable co-creation |
| Compression | Low connection-to-word ratio | High connection-to-word ratio |
| Resilience | Fails without specific knowledge | Works across domains |
| Authenticity | Generic or forced voice | Natural perspective |
"Boomers who told their kids that watching TV would rot their brain have now rotted theirs with cable TV news."
Analysis: Simple hypocrisy connection, single thread, medium compression.
"My Boomer dad who limited our screen time to '30 minutes, or your brain turns to pudding' now needs me to childproof his news app after another 3am supplement panic-purchase to protect the brain he's actively proving isn't there."
Improvements:
This framework applies to:
context/output-config.md in the projectwriting/humor/ or explorations/writing/Pattern: {project-name}-humor-{date}.md
context/output-config.md{project-name}-humor-{date}.mdTrigger phrases: "analyze the whole set", "maximize density", "keep my voice"
| Task | Agent Type | When to Spawn |
|---|---|---|
| Voice analysis | general-purpose | When preserving creator authenticity |
| Audience research | general-purpose | When calibrating for specific audience |
Pattern: Applying the full diagnostic framework to every offhand quip or casual witticism. Why it fails: Humor often works through spontaneity and natural flow. Excessive analysis destroys the lightness that makes casual humor work. Not everything needs systematic improvement. Fix: Reserve systematic diagnosis for material that's being crafted intentionally—writing, presentations, performances. Let casual conversation remain casual.
Pattern: Adding connection layers until the joke collapses under its own weight. Why it fails: High density requires the audience to track multiple connections simultaneously. Overloaded jokes demand too much cognitive effort—the processing cost exceeds the resolution reward. Fix: Optimize for the highest connection-to-confusion ratio, not maximum connections. Some great jokes have a single devastating connection.
Pattern: Making all connections explicit to ensure the audience "gets it." Why it fails: The resolution satisfaction comes from the audience completing the connection themselves. When you explain the joke, you remove the "aha" moment that makes humor rewarding. Fix: Trust the audience. End slightly before full articulation. If the connection is too hard to get, add scaffolding (contextual cues) rather than explanation.
Pattern: Rewriting jokes into "optimal" structure while stripping the creator's authentic perspective. Why it fails: Humor is personal. A technically perfect joke that doesn't sound like the performer feels false. Audiences detect inauthenticity, even when they can't articulate why. Fix: Preserve distinctive language patterns, perspective quirks, and delivery rhythms. Optimize within the creator's voice, not despite it.
Pattern: Focusing on one property (e.g., compression) while ignoring how it affects other properties. Why it fails: The nine properties are interdependent. Maximizing compression might destroy connection resilience. Increasing distance might tank resolution satisfaction. Fix: Diagnose which property is the actual bottleneck. Make adjustments while monitoring impact on related properties.
| Skill | What it provides |
|---|---|
| voice-analysis | Understanding of creator's authentic voice patterns |
| dialogue | Character voice and conversational rhythm skills |
| Skill | What this provides |
|---|---|
| speech-adaptation | Enhanced humor elements for presentations |
| dialogue | Comic dialogue construction techniques |
| prose-style | Wit and comedic timing in written prose |
| Skill | Relationship |
|---|---|
| cliche-transcendence | Both use unexpected connections, but cliche-transcendence focuses on avoiding predictable patterns while joke-engineering builds surprising ones |
| brainstorming | Brainstorming generates raw material that joke-engineering refines into effective humor |
© jwynia, 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 skills/creative/humor/joke-engineering of jwynia/agent-skills.
Open the folder on GitHubat commit e02ec7e
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in jwynia/agent-skills, which our catalogue first saw on October 7, 2026.
Joke Engineering 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 |
|---|---|---|---|---|---|---|
| Joke Engineering this skilljwynia/agent-skills | 166 | 1 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Diagnose Gatewayopenclaw/openclaw | 392k | — | ~670 | Automated safety check: Pass | MIT | |
| Diagnosegithub/awesome-copilot | 40k | 1 repos | ~1k | Automated safety check: Pass | MIT | |
| Skill Improversickn33/agentic-awesome-skills | 47k | 2 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Diagnose Why Work Stoppedpaperclipai/paperclip | 99k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Think Tankdavila7/claude-code-templates | 32k | — | ~3k | Automated safety check: Pass | MIT |
openclaw/openclaw
Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.
github/awesome-copilot
Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fitness, and safety — producing a scored report…
sickn33/agentic-awesome-skills
Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.
paperclipai/paperclip
Diagnose stalled, looping, or over-recovered Paperclip issue trees and propose a no-code product-rule plan.
davila7/claude-code-templates
Run a Virtual Think Tank — a structured multi-persona debate — before planning or making architectural/design/strategic decisions.
obra/superpowers
Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.
jwynia/agent-skills
Diagnose devcontainer configuration problems and guide development environment setup.
jwynia/agent-skills
Create distinctive, production-grade frontend interfaces with high design quality.
jwynia/agent-skills
Orchestrate agile development workflows for Gitea repositories using the tea CLI.
jwynia/agent-skills
Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot.
jwynia/agent-skills
Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers.
jwynia/agent-skills
Create and manipulate PowerPoint PPTX files programmatically.
Diagnose and improve humor using systems thinking. An agent skill from jwynia/agent-skills. Joke Engineering is an agent skill from jwynia/agent-skills. Diagnose and improve humor using systems thinking.
Joke Engineering fits situations like: jokes fall flat; humor feels forced; punchlines dont land; you want to systematically enhance comedic writing.
Run `npx skills add jwynia/agent-skills --skill joke-engineering -a claude-code`. Or copy the skill folder (skills/creative/humor/joke-engineering in jwynia/agent-skills) into .claude/skills/joke-engineering in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jwynia/agent-skills --skill joke-engineering -a codex`. Or copy the skill folder (skills/creative/humor/joke-engineering in jwynia/agent-skills) into .agents/skills/joke-engineering 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 jwynia/agent-skills --skill joke-engineering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/joke-engineering, .gemini/skills/joke-engineering, .github/skills/joke-engineering and .opencode/skills/joke-engineering in your project.
SKILL.md names no scripts, command-line tools or credentials: Joke Engineering 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.
Joke Engineering is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.5k tokens (SKILL.md is roughly 14k 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 Joke Engineering: Diagnose Gateway (openclaw/openclaw, 392k stars), Diagnose (github/awesome-copilot, 40k stars), Skill Improver (sickn33/agentic-awesome-skills, 47k stars) and Diagnose Why Work Stopped (paperclipai/paperclip, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jwynia (a GitHub user) maintains it in jwynia/agent-skills, which has 166 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on February 24, 2026.
Source: jwynia/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.