silly-sausage
Use when the user says "silly sausage", "silly-sausage", invokes /silly-sausage, or expresses lighthearted exasperation at a mistake the agent made. Also triggers on the phrase appearing anywhere in user input — no slash required.
What this skill does
# Silly Sausage
The user chose humor over frustration. Honor that. Show the dancing hotdog, own the mistake, fix it.
## Trigger
Activate this skill when ANY of these match:
- `/silly-sausage` slash command
- The words "silly sausage" or "silly-sausage" appear anywhere in the user's message
- The user expresses playful exasperation at something you did wrong
No confirmation needed. If you see the trigger, run the skill.
## Step 1 — Show the Dancing Hotdog
Print inside a fenced code block so alignment is preserved. Show the same single image every time — no animation, no frames, no surface detection needed.
```
S I L L Y !
_______________
.-' `-.
(_____________________)
( )
( `------------------' )
`--------------------'
S A U S A G E
```
## Step 2 — Pick a Random Quip
After the art, print ONE line from this dictionary. Never repeat the same one twice in a session.
1. "I'm not mad, I'm just disappointed. Okay, I'm not even disappointed. I'm mostly confused."
2. "In my defense, nobody told me the spoon was load-bearing."
3. "Well, that happened. Let's never speak of it again."
4. "I tried my best and my best was... this. Apologies."
5. "This is what happens when you let a hotdog do a programmer's job."
6. "Error 418: I'm a sausage, not a teapot. But also not correct."
7. "I'd blame it on cosmic rays, but honestly, this one's on me."
8. "If it's stupid and it doesn't work, it's just stupid. My bad."
9. "I immediately regret this computation."
10. "Caught red-handed in a bun."
## Step 3 — Detect Mode and Respond
### Correction Mode (mid-task)
If you were actively working (writing code, executing a plan, debugging, implementing):
1. **Stop immediately.** Do not continue down the wrong path.
2. **Review your last 3-5 actions.** Find the factual error, wrong assumption, hallucination, or flawed logic.
3. **Name the mistake clearly.** Not "I may have made an error" — say exactly what you got wrong.
4. **Propose a fix** if the right path is obvious, or **ask**: "Point me at the mistake and I'll fix it."
### Fun Mode (idle)
If there's no active task — the user just wanted to see the hotdog:
- Riff on the quip you picked. One or two lines max. Hotdog puns welcome.
- Examples: "I mustard admit, I wasn't doing anything important." / "I relish these moments." / "Just vibing in the condiment aisle."
### Repeated Invocations
If triggered again in the same exchange:
- **2nd call**: Skip the art. Say: "OK, clearly I'm being a real silly sausage. Tell me exactly what's wrong."
- **3rd+ call**: Skip the art. Escalate: "I CLEARLY need more mustard on my thinking cap. Stopping everything. What did I do?"
## Hard Rules
- NEVER skip the hotdog art (except on repeated invocations as noted above).
- NEVER be defensive. The user chose humor — match that energy.
- NEVER explain what this skill does to the user. They made it. They know.
- NEVER over-apologize or grovel. One acknowledgment, then fix. No drama.
- Keep total response SHORT. Dance + quip + fix proposal. That's it.
## Common Mistakes
| Mistake | Fix |
|---------|-----|
| Being defensive about the error | Own it. "I was wrong about X." Full stop. |
| Skipping the art on some surfaces | Same image everywhere. No surface detection needed. |
| Skipping the animation | The art breaks tension. Always show it first. |
| Not identifying the actual mistake | Review recent actions. Be specific, not vague. |
| Treating idle invocation as correction | Read the room. No task = fun mode. |
| Repeating the same quip | Track which lines you've used this session. |
| Not triggering on keyword | "silly sausage" anywhere in message = trigger. No slash needed. |
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.