菜单
Efficiently bring upstream NanoClaw updates into a customized install, with preview, selective cherry-pick, and low token usage.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | update-nanoclaw |
| description | Efficiently bring upstream NanoClaw updates into a customized install, with preview, selective cherry-pick, and low token usage. |
Your NanoClaw fork drifts from upstream as you customize it. This skill pulls upstream changes into your install without losing your modifications.
Run /update-nanoclaw in Claude Code.
Preflight: checks for clean working tree (git status --porcelain). If upstream remote is missing, asks you for the URL (defaults to https://github.com/nanocoai/nanoclaw.git) and adds it. Detects the upstream branch name (main or master).
Backup: creates a timestamped backup branch and tag (backup/pre-update-<hash>-<timestamp>, pre-update-<hash>-<timestamp>) before touching anything. Safe to run multiple times.
Preview: runs git log and git diff against the merge base to show upstream changes since your last sync. Groups changed files into categories:
.claude/skills/): unlikely to conflict unless you edited an upstream skillsrc/): may conflict if you modified the same filescontainer/): triggers container rebuildpackage.json, pnpm-lock.yaml, tsconfig*.json): lockfile changes trigger dep installUpdate paths (you pick one):
merge (default): git merge upstream/<branch>. Resolves all conflicts in one pass.cherry-pick: git cherry-pick <hashes>. Pull in only the commits you want.rebase: git rebase upstream/<branch>. Linear history, but conflicts resolve per-commit.abort: just view the changelog, change nothing.Conflict preview: before merging, runs a dry-run (git merge --no-commit --no-ff) to show which files would conflict. You can still abort at this point.
Conflict resolution: opens only conflicted files, resolves the conflict markers, keeps your local customizations intact.
Validation: runs pnpm run build and pnpm test. If container files changed, also runs the container typecheck and ./container/build.sh.
Breaking changes check: after validation, reads CHANGELOG.md for any [BREAKING] entries introduced by the update. If found, shows each breaking change and offers to run the recommended skill to migrate.
The backup tag is printed at the end of each run:
git reset --hard pre-update-<hash>-<timestamp>
Backup branch backup/pre-update-<hash>-<timestamp> also exists.
Only opens files with actual conflicts. Uses git log, git diff, and git status for everything else. Does not scan or refactor unrelated code.
Help a user with a customized NanoClaw install safely incorporate upstream changes without a fresh reinstall and without blowing tokens.
git status, git log, git diff, and open only conflicted files.The update process itself evolves, so run its newest version before doing anything else:
upstream remote exists (default https://github.com/nanocoai/nanoclaw.git) and fetch: git fetch upstream --prune. Detect the upstream branch (main or master).git checkout upstream/<branch> -- .claude/skills/update-nanoclaw/.claude/skills/update-nanoclaw/SKILL.md. If it changed, follow the updated version from the top instead of this one.This is the only working-tree change expected before the preflight check; the full update commits it along with everything else.
Run:
git status --porcelain
If output is non-empty:.claude/skills/update-nanoclaw/ are the Step 0a self-refresh — ignore those and proceed.Confirm remotes:
git remote -v
If upstream is missing:https://github.com/nanocoai/nanoclaw.git).git remote add upstream <user-provided-url>git fetch upstream --pruneDetermine the upstream branch name:
git branch -r | grep upstream/upstream/main exists, use main.upstream/master exists, use master.upstream/main should use upstream/$UPSTREAM_BRANCH instead.Fetch:
git fetch upstream --pruneCapture current state:
HASH=$(git rev-parse --short HEAD)TIMESTAMP=$(date +%Y%m%d-%H%M%S)Create backup branch and tag (using timestamp to avoid collisions on retry):
git branch backup/pre-update-$HASH-$TIMESTAMPgit tag pre-update-$HASH-$TIMESTAMPSave the tag name for later reference in the summary and rollback instructions.
Compute common base:
BASE=$(git merge-base HEAD upstream/$UPSTREAM_BRANCH)Show upstream commits since BASE:
git log --oneline $BASE..upstream/$UPSTREAM_BRANCHShow local commits since BASE (custom drift):
git log --oneline $BASE..HEADShow file-level impact from upstream:
git diff --name-only $BASE..upstream/$UPSTREAM_BRANCHBucket the upstream changed files:
.claude/skills/): unlikely to conflict unless the user edited an upstream skillsrc/): may conflict if user modified the same filescontainer/): triggers container rebuild (+ typecheck if agent-runner/src/ changed)package.json, pnpm-lock.yaml, tsconfig*.json): lockfile changes trigger dep installversions.json): a changed onecli-gateway / onecli-cli value requires upgrading the OneCLI gateway/CLI to match — see Step 5.5Large drift check: If the upstream commit count and age suggest the user has a lot of catching up to do, mention that /migrate-nanoclaw might be a better fit — it extracts customizations and reapplies them on clean upstream instead of merging. Offer it as an option but don't push.
Present these buckets to the user and ask them to choose one path using AskUserQuestion:
If Abort: stop here.
If Full update or Rebase:
git merge --no-commit --no-ff upstream/$UPSTREAM_BRANCH; git diff --name-only --diff-filter=U; git merge --abort
Run:
git merge upstream/$UPSTREAM_BRANCH --no-editIf conflicts occur:
git status and identify conflicted files.git add <file>git commit --no-editIf user chose Selective:
BASE=$(git merge-base HEAD upstream/$UPSTREAM_BRANCH)git log --oneline $BASE..upstream/$UPSTREAM_BRANCHgit cherry-pick <hash1> <hash2> ...If conflicts during cherry-pick:
git add <file>git cherry-pick --continue
If user wants to stop:git cherry-pick --abortRun:
git rebase upstream/$UPSTREAM_BRANCHIf conflicts:
git add <file>git rebase --continue
If it gets messy (more than 3 rounds of conflicts):git rebase --abortCheck if the merge changed any lockfiles or package manifests:
git diff <backup-tag-from-step-1>..HEAD --name-only | grep -E '^(pnpm-lock\.yaml|package\.json)$'
pnpm installgit diff <backup-tag-from-step-1>..HEAD --name-only | grep -E '^container/agent-runner/(bun\.lock|package\.json)$'
command -v bun succeeds: cd container/agent-runner && bun install./container/build.shSkip this step if neither lockfile changed.
Check which areas changed to determine what to validate:
CHANGED_FILES=$(git diff --name-only <backup-tag-from-step-1>..HEAD)Host build (always):
pnpm run buildpnpm test (do not fail the flow if tests are not configured)Container typecheck (only if container/agent-runner/src/ files are in CHANGED_FILES AND bun types are available):
pnpm exec tsc -p container/agent-runner/tsconfig.json --noEmitCannot find type definition file for 'bun'), skip with a note — type errors will surface at container runtime insteadContainer image rebuild (only if any container/ files are in CHANGED_FILES):
./container/build.shIf build fails:
The OneCLI gateway and CLI are external components pinned in versions.json; when a pin moves, the running version must be upgraded to match or the new code may fail against it.
If git diff <backup-tag-from-step-1>..HEAD -- versions.json shows the onecli-gateway or onecli-cli value changed, follow docs/onecli-upgrades.md before the service restart (Step 8). Otherwise skip.
After validation succeeds, check if the update introduced any breaking changes.
Determine which CHANGELOG entries are new by diffing against the backup tag:
git diff <backup-tag-from-step-1>..HEAD -- CHANGELOG.mdParse the diff output for lines that contain [BREAKING] anywhere in the line. Each such line is one breaking change entry. The format is:
[BREAKING] <description>. Run `/<skill-name>` to <action>.
If no [BREAKING] lines are found:
If one or more [BREAKING] lines are found:
/<skill-name> part).multiSelect: true so the user can pick multiple skills if there are several breaking changes.Updating your installed skills is part of updating NanoClaw, not an optional
extra. Channel and provider code ships on long-lived branches (channels,
providers) that the host merge above doesn't touch — so stopping here leaves
that code on whatever version you installed, which is how an important upstream
fix gets silently left behind. The default is to continue into /update-skills,
which re-applies your installed channels/providers to pull their latest code.
Detect whether anything is installed: read src/channels/index.ts and
src/providers/index.ts, collecting import './<name>.js'; lines (excluding
cli).
Hand-off — default in, minimal opt-out. Use AskUserQuestion (single-select). Name the installed skills in the question so the choice is concrete:
/update-skills to bring them up to date?"/update-skills, which re-applies your installed channels/providers to pull
their latest upstream code. You pick which ones there."/update-skills myself later" — description: "Your
installed skill code stays as-is and may be behind upstream."Keep it to these two options — the per-skill selection lives inside
/update-skills, not here.
/update-skills using the Skill tool. (If the re-apply
touches container code, /update-skills rebuilds the agent image itself — see
its Step 4 — so nothing container-related is owed back here.)/update-skills can be run anytime, then proceed.Proceed to Step 7.9.
After validation has succeeded, record that this install reached the new version through the supported path. Without this, the startup tripwire stops the host on its next start.
pnpm exec tsx scripts/upgrade-state.ts set "" update-nanoclaw
package.json version.If validation did NOT succeed, do not stamp — leave the tripwire to catch the broken state.
Proceed to Step 8.
Show:
git rev-parse --short HEADgit rev-parse --short upstream/$UPSTREAM_BRANCHgit diff --name-only upstream/$UPSTREAM_BRANCH..HEADTell the user:
git reset --hard <backup-tag-from-step-1>backup/pre-update-<HASH>-<TIMESTAMP>setup/lib/install-slug.sh. Run from your NanoClaw project root:
source setup/lib/install-slug.sh && launchctl kickstart -k gui/$(id -u)/$(launchd_label)source setup/lib/install-slug.sh && systemctl --user restart $(systemd_unit) (or, if you want to confirm the unit name first: systemctl --user list-units --type=service | grep "$(. setup/lib/install-slug.sh && systemd_unit)")pnpm run dev.claude/skills/update-nanoclaw/diagnostics.md.Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn.
Use OpenCode as an agent provider. OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per group via `ncl groups config update --provider opencode`; host passes OPENCODE_* and XDG mount when spawning containers.
Configure which host directories agent containers can access. View, add, or remove mount allowlist entries. Triggers on "mounts", "mount allowlist", "agent access to directories", "container mounts".
Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.
Distill a reusable skill from anything — a directory, a URL, pasted notes, or what you just did together — or refine an existing skill with new learnings. Use when the user says '/learn', 'learn this', 'turn this into a skill', 'capture this workflow', 'make a skill from <source>', or 'improve/update the <name> skill'. Produces or updates a .claude/skills/<name>/SKILL.md authored to NanoClaw's skill guidelines. (This CREATES or REFINES a skill from a source; it does not install existing skills from a registry.)
Add Discord bot channel integration via Chat SDK.