Reason — Development skill for Claude Code
Think through a question using memory-backed retrieval.
How to install Reason
Installs to ~/.claude/skills/pnmcguire480-cairntir-reason/SKILL.md
mkdir -p ~/.claude/skills/pnmcguire480-cairntir-reason && curl -fsSL https://raw.githubusercontent.com/pnmcguire480/cairntir/HEAD/commands/reason.md -o ~/.claude/skills/pnmcguire480-cairntir-reason/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Reason does
description: Think through a question using memory-backed retrieval.
Use Cairntir's `reason` skill to think about the user's question with the help of stored memory.
- Call
cairntir_session_startto load the 4-layer context for the current wing - Call
cairntir_recallto retrieve memories specifically relevant to the question - Reason out loud with the retrieved memories in view — cite drawer ids inline
- Propose an answer, and flag any assumptions that should be stress-tested b
Alternatives in Development
- Quick Plan — Create a detailed implementation plan based on the user's requirements provided through the USER_PROMPT variab 3.4k ★
- Scope Recall Hermes — Local long-term memory for Hermes, Codex, Claude Code, WorkBuddy and dsh agents: one SQLite store, source-back 438 ★
- AgentSkillOS — Build your agent from 200,000+ skills via skill RETRIEVAL & ORCHESTRATION 373 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Recallnest
One memory, every terminal. Shared memory layer for any MCP client — Claude Code, Codex, Kimi, Antigravity (ag
Memory Agent
Local, file-backed personal memory agent — scans Claude Code / Codex sessions, extracts explicit user requirem
Think First Principles
Reason from fundamentals by decomposing a problem to its irreducible level, then stripping the inherited assum
Inspirer
Use when the user invokes /evo:inspirer or asks to brainstorm creatively, think outside the box, explore uncon
Think Issue Position Argument Mapping
Turn a tangled multi-question deliberation or transcript into an inspectable typed map by chaining shipped mov
Muse:Elon Musk
Think with Elon Musk (interpretive frame) — adaptive structured session (v2.2) using first-principles cost dec
Related Agents
Memory Hunter
Memory retrieval lane — given a spec (a consumer's question + task), hunts the wiki for the relevant slices an
Daily Copilot
The everyday work partner. Use for prioritization, thinking out loud, "remember this", "challenge this", "what
Exploit Developer
Stage 8 of Vulpine. Given the issue reports from stage 7, think through reliable exploit chains that combine t