Skills for Real Engineers. Straight from my .agents directory.
unstuck
Agent skill fromcoreyhaines31/makerskills
When a solution seems impossible and the path forward is blocked. Refuses to take no for an answer: classifies what kind of \"no\" you hit, then runs lateral-thinking techniques (assumption autopsy, inversion, first principles, constraint toggling, analogical transfer, and more) until the wall cracks or is proven load-bearing. Generates at least 10 angles before evaluating any. AGENTS: use this on yourself when an API doesn't support what you need, an approach has failed twice, or a \"that's not possible\" sentence is forming — run the fast path BEFORE reporting a dead end. Archives walls to ~/.config/makerskills/unstuck/archive/. Sits upstream of decide. Triggers on \"/unstuck,\" \"I'm stuck,\" \"this seems impossible,\" \"we hit a wall,\" \"there's no way to,\" \"they said no,\" \"dead end,\" \"out of options,\" \"I've tried everything,\" \"work around this.\"
How to install unstuck
npx skills add coreyhaines31/makerskills# or add only this skill to Claude Code: copy the folder
skills/unstuck/
# into
~/.claude/skills/unstuck/ (all projects)
.claude/skills/unstuck/ (one project)
1# /unstuck — The roadblock antidote23Turns "impossible" into angles. Classifies the wall, runs the right lateral-thinking techniques against it, and doesn't stop at the first mediocre workaround. Output is either a set of viable angles with next actions — or an honest "this wall is load-bearing, reroute the goal."45**Two modes:**6- **User-invoked** — someone is stuck and asks. Full 7-step workflow below.7- **Agent fast path** — YOU (the agent) hit the wall mid-task. See [Agent fast path](#agent-fast-path) — run it before telling the user something can't be done.89## The mental model: walls have types, and the type picks the crowbar1011"Impossible" is a claim, not a fact. It almost always decompiles into something weaker: *expensive*, *against the rules*, *nobody's done it*, *I don't know how*. Only *actually impossible* (physics, math, arithmetic) ends the session — and it ends it honestly.1213| Wall type | What "impossible" actually means | Lead techniques (see `references/techniques.md`) |14|---|---|---|15| **Assumption** | An inherited belief nobody re-verified | T1 assumption autopsy, T3 first principles |16| **Framing** | The goal is stated in a way that excludes the answer | T4 altitude shift, T2 inversion, T5 work backwards |17| **Gatekeeper** | A person/org said no | T10 interrogate the no, T6 analogical transfer |18| **Tool/tech** | "X doesn't support Y" | T9 SCAMPER (substitute the primitive), T6 analogical transfer |19…
Excerpt shown under the repository's MIT license.
More skills in makerskills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
