architect
Produces Alon's design-doc system BEFORE code: SOURCE_OF_TRUTH, ARCHITECTURE_ROADMAP, TODO_WORKFLOW, CLAUDE.md (+ modular docs/architecture). Model first: data…
Preflight sync + situational brief before repo work: fetch origin, ahead/behind divergence, recent commits, open PRs/issues, dirty-state warnings, one recommended first action. Read-only — never pulls or rewrites a dirty tree without explicit OK. Use proactively before starting
$ npx -y skills add alonbaron/claude-skills --skill up-to-date --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/up-to-dateContext preview
The summary Claude sees to decide when to auto-load this skill.
Preflight sync + situational brief before repo work: fetch origin, ahead/behind divergence, recent commits, open PRs/issues, dirty-state warnings, one recommended first action. Read-only — never pulls or rewrites a dirty tree without explicit OK. Use proactively before starting
name: up-to-date description: > Preflight sync + situational brief before repo work: fetch origin, ahead/behind divergence, recent commits, open PRs/issues, dirty-state warnings, one recommended first action. Read-only — never pulls or rewrites a dirty tree without explicit OK. Use proactively before starting work in any repo with a remote, especially shared or long-untouched ones. Also on "up-to-date", "sync first", "pull latest", "catch me up on the repo". Not for repos without a remote or quick mid-task re-checks. argument-hint: "[optional: 'docs' to also refresh library docs, or a path]"
Get current before doing work. Goal: a short situational brief so you build on the latest code with full context. **Read-only by default. Never mutate a dirty tree, never force, never discard local work without explicit confirmation.**
When work is about to start in a repo with a remote, invoke this without being asked: announce in one line ("Running up-to-date on <repo>") and proceed. Proactive runs stay strictly read-only — the sync decision (step 7) still requires explicit OK.
1. **Confirm it's a git repo with a remote.** If not, say so and stop — there's nothing to sync. 2. **Local state:** `git status --short` and `git stash list`. Note uncommitted changes, untracked files, stashes. This gates everything below. 3. **Fetch:** `git fetch --all --prune`. (Fetch is safe; it changes nothing local.) 4. **Divergence:** current branch vs its upstream — `git rev-list --left-right --count @{upstream}...HEAD`. Report ahead/behind. No upstream (new local branch, or detached HEAD) → that command fails; say so plainly, fall back to `origin/<default-branch>` for the comparison, and note the branch is unpushed. Never report "in sync" from a failed command. 5. **Recent activity:** `git log --oneline -15` on the branch, and the same for the default branch if you're not on it. Summarize what changed, not every line. 6. **Open work (if `gh` is available and the remote is GitHub):** `gh pr list` and `gh issue list`. Surface anything touching the files you're about to work on. 7. **Sync decision:**
8. **Library currency (only if asked or `docs` arg given):** for the key deps in play, use context7 (resolve-library-id → query-docs) to pull current API docs, so code targets today's API, not stale memory.
authors.
without explicit user OK.
guess at remote state.
`git status` answer it without the full brief.
next, before code.
The user knows: what branch they're on, whether it's behind/ahead/clean, what changed recently, what open work overlaps, and the one safe next action.
Apply on every run — canonical home `~/.claude/CLAUDE.md`:
Six Claude Code skills (architect, review-swarm, ask-the-council, prompt-generator, up-to-date, ponytail) bundled as an installable plugin.
Produces Alon's design-doc system BEFORE code: SOURCE_OF_TRUTH, ARCHITECTURE_ROADMAP, TODO_WORKFLOW, CLAUDE.md (+ modular docs/architecture). Model first: data…
Convenes a panel of opinionated advisors (parallel Claude subagents, each with a distinct mandate and a forbidden move so they genuinely diverge), then a…
Forces the laziest solution that actually works — YAGNI, reuse before new code, stdlib before custom, native platform before dependencies, one line before…
Turns a vague ask into a rigorous, grounded, token-efficient prompt: role + objective, testable done criteria, anti-hallucination (verify or say "I don't…
Local, free, multi-specialist review of a diff: parallel Claude subagents (correctness, security/trust boundaries, data/perf, architecture-altitude,…