blind-spot-pass
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…
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
$ npx -y skills add sangrokjung/claude-forge --skill relay --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/relayContext preview
The summary Claude sees to decide when to auto-load this skill.
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
name: relay description: 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. allowed-tools: Bash(bash:*), Bash(git:*), Bash(date:*), Bash(hostname:*), Bash(uname:*), Read, Write, Glob, Grep, AskUserQuestion disable-model-invocation: true
> Think of a relay race: the runner hands off the baton before stopping. Before context fills up, this > skill produces two things: ① a one-line `/compact` command that compresses everything so far, and > ② a handoff document (a "baton") that lets the next session start running immediately on the next task.
**When**: context is 70%+ used, work is about to be interrupted, or the user asks to "relay / hand off / next session / baton / handoff."
**Important (invariant)**: this skill **never runs `/compact` directly** (a skill cannot execute `/compact`). It only produces **the one-liner the user pastes in**.
Let `$SKILL` be the absolute path of the directory containing this SKILL.md. Scripts live in `$SKILL/scripts/`.
From `$ARGUMENTS`:
Run `bash "$SKILL/scripts/relay-collect.sh"` → capture one JSON object. (facts about git/plan/session-summary/tasks/artifacts) This JSON is the source of truth for every "fact." **Do not retype it from memory — quote it verbatim.**
If NEXT_TASK is empty and `--no-ask` was not passed, ask **one** AskUserQuestion: "What's the first thing to do next?" — options pulled from `plan.next_unchecked` / `session_summary.next_steps` / `tasks.items` in the collect JSON, plus "type it myself." Tag the answer `[from-user]`.
`bash "$SKILL/scripts/relay-build-focus.sh" "<NEXT_TASK>" "<files>" "<decision>"`
`bash "$SKILL/scripts/relay-write-baton.sh" "<NEXT_TASK>" <path-to-collect.json or -> "<focus line>"`
Follow `references/next-prompt-spec.md` to write §2 (context needed) and §4 (repro pitfalls), plus §1's body.
write-baton **with the prose file as the 4th argument** to splice it in.
(a) absolute path of the baton (b) preview of the next prompt — excerpt from §1 MISSION (c) the `/compact` one-liner, output **as a single fenced code block, verbatim**
**Never write (c) inline.** A long inline line wraps in the terminal and becomes hard to select and copy. A code block keeps it as one selectable unit.
anything else in the meantime, the line is gone, and whatever was on the clipboard before gets silently overwritten without consent. On-screen text stays in scrollback and can be copied again anytime.
call in step 4. Even then, still emit the (c) code block.
`hooks/post-compact-restore.sh` is wired to settings.json's SessionStart (matcher `"compact"`). Right after `/compact`, this hook injects the pointer (the carryover left by write-baton) into the session **exactly once (consume-once)**.
path above — just Read that path.
`tests/relay.bats` uses [bats-core](https://github.com/bats-core/bats-core). It is **not required** to u
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.
Repo: sangrokjung/claude-forge
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…
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,…
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js…
Use when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development. Covers Spec-Driven…
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use…