oblique
This skill should be used when the user asks to "/oblique", "oblique strategy", "give me an oblique strategy", "give me a creative prompt", or wants lateral thinking inspiration for their coding session.
What this skill does
# Oblique Strategies
Inspired by Brian Eno and Peter Schmidt's Oblique Strategies deck - a set of cards offering creative prompts to break through creative blocks and introduce unexpected directions.
## Workflow
### Step 1: Get Random Strategies
Run the script to get 4 random strategies:
```bash
./scripts/pick-strategies.sh -n 4
```
### Step 2: Present Strategies to User
Use `AskUserQuestion` to present the 4 strategies as options. Each strategy becomes a selectable option.
**Format:**
- header: "Strategy"
- question: "Which oblique strategy would you like to apply to this session?"
- options: The 4 strategies from the script output
- multiSelect: false
### Step 3: Ask How to Apply
After the user selects a strategy, use another `AskUserQuestion` to ask how they'd like to apply it.
**Format:**
- header: "Application"
- question: "How would you like to apply '[selected strategy]'?"
- options:
- "Apply to current task" - Focus this strategy on whatever I'm working on right now
- "Use as session mindset" - Let this strategy color the entire session's approach
- "Help me interpret it" - Explain what this strategy might mean in a coding context
- multiSelect: false
### Step 4: Acknowledge and Incorporate
Based on the user's choice:
- **Apply to current task**: Reframe the current work through the lens of the strategy. Offer specific suggestions for how the strategy might change the approach.
- **Use as session mindset**: Acknowledge the strategy and naturally reference it throughout the session when relevant. Let it influence suggestions and perspectives.
- **Help me interpret it**: Explain the strategy's origin and meaning, then offer interpretations for how it might apply to software development, debugging, architecture, or creative coding challenges.
## Example Interaction
```
User: /oblique
Claude: [Runs ./scripts/pick-strategies.sh -n 4]
Output:
- Honor thy error as a hidden intention
- Emphasise the flaws
- Do nothing for as long as possible
- Use an old idea
Claude: [AskUserQuestion #1]
"Which oblique strategy would you like to apply to this session?"
Options presented to user...
User: Selects "Honor thy error as a hidden intention"
Claude: [AskUserQuestion #2]
"How would you like to apply 'Honor thy error as a hidden intention'?"
Options presented to user...
User: Selects "Apply to current task"
Claude: Interesting choice! "Honor thy error as a hidden intention" suggests that
mistakes aren't accidents - they might be revealing something your
conscious mind missed.
For your current work, this could mean:
- That bug you found might actually be a feature in disguise
- The "wrong" approach might lead somewhere interesting
- Instead of fixing, explore what the error is trying to tell you
What are you working on? Let's see what hidden intentions might be lurking.
```
## Notes
- The script uses POSIX tools (`awk`, `sort`, `head`, `cut`) for cross-platform compatibility
- All 113 original Oblique Strategies are embedded in the script
- Each invocation is independent - no state is tracked between uses
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.