Claude Forge

Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact itself (a skill cannot do that) — it produces the one-liner the user pastes in.

Turn a one-line description of a repetitive task into a reusable, self-guarding slash command. loop-forge diagnoses the task into one of 5 loop shapes (Batch / Pipeline / Refine / Watch / Explore), interviews for the blanks, and auto-injects two safety devices the user didn't know they needed — an independent verifier (maker ≠ checker) and a hardstop (a budget/count/cooldown ceiling) — then previews the result and stamps it as a `/command` they can run forever. Use when the user says "/loop", "/loop-forge", "/make-it-loop", "automate this", "make this repeatable", "turn this into a command", "do this for all 100 items", "do X every time Y happens", "generate several and pick the best", or otherwise wants to capture a recurring task as a reusable slash command instead of re-typing the prompt by hand. Works in any language: it interviews the user and writes the stamped command in the user's own language. Non-goal — it does not schedule unattended runs (launchd/cron) or publish externally on its own; it stamps t

Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified", "is this actually done", "maker checker", "second pair of eyes on this change". Not for prose, docs or typo edits.

Use when detecting and running project build systems automatically. Supports npm/yarn/pnpm/pip/poetry/gradle/maven/cargo/go/make. Triggers on build, test run, project setup, package manager detection.

Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development. Covers Spec-Driven Development, Context Engineering, and post-dev workflow.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

Measure and shrink the always-loaded context of a Claude Code harness (CLAUDE.md + rules without paths frontmatter) back under budget — migrate narrative to reference files, convert rules to path-scoped or skill-triggered loading, and verify zero governance loss with deterministic preservation checks. Use on "harness diet", "context diet", "rules diet", "CLAUDE.md too long", "always-load budget", "trim my rules", "context bloat", "하네스 다이어트", "룰 다이어트", "컨텍스트 다이어트", "always-load 줄여줘". Not for one-off prose editing or project docs cleanup.

Use when searching, installing, or improving AI skills and prompts via prompts.chat or skills.sh. Triggers on skill search, prompt lookup, install skill, improve prompt, prompts.chat.

Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.

Use *before* starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm new to this", "I don't know what to ask", "teach me before we start", "blind spot pass", "unknown unknowns", "find my unknowns", or the Korean "내가 뭘 모르는지 알려줘" / "이 분야 처음인데" / "먼저 가르쳐줘" / "블라인드 스팟", or when you hand off a task while admitting you're a non-expert in that field (color grading, video editing, legal, tax, finance, design, an unfamiliar codebase, etc.). Do NOT use for simple factual questions, domains you already know, or directly-actionable work — answer those directly or route to planner / architect.

Clean up translation-ese and AI-writing tics in Korean prose so it reads like a person wrote it — content (facts, numbers, proper nouns, quotes) stays 100% unchanged, only style and rhythm are touched. Single-pass, done in this session. Triggers — AI 티 없애줘, 번역투 고쳐줘, 한글 자연스럽게 윤문해줘, sounds like a machine translation, remove AI tells from this Korean text, make this Korean read naturally. Not for: marketing copy generation (write it clean the first time — see rules/korean-writing-quality.md), English text, plain spell-check (see korean-spell-check), or book-length manuscripts.

Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.

Use when orchestrating Agent Teams for parallel development - team composition, task distribution, dependency management, and result aggregation. Triggers on /orchestrate, multi-agent coordination, parallel team work, task delegation to teammates.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use Nara/PNU Korean spell-check surfaces conservatively to proofread Korean text, chunk long input, and return change-focused correction suggestions.

Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.

Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.

Count Korean text deterministically with exact grapheme, line, and byte contracts for self-intros and form limits.