Menú
Prime agent with Orbit project context (both repos + optional GitHub issue)
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Input: $ARGUMENTS
Build a working mental model of both Orbit repos so subsequent skills (/plan, /implement) have warm context.
Parse $ARGUMENTS. Count numeric tokens (123, #123) — split on whitespace OR commas (100,101,102 is two arguments).
| Numeric arg count | Mode |
|---|---|
| 0 or 1 | Single-issue / context-only — continue with the steps below. |
| ≥ 2 | Multi-issue — jump to the "Multi-issue mode" section. Do NOT run the single-issue steps in the main session. |
#N), treat as a GitHub issue in thomasluizon/orbit-ui-mobile.--quick skips the deep codebase tour and only reads conventions + recent commits.gh issue view {N} --repo thomasluizon/orbit-ui-mobile --json number,title,body,labels,milestone,assignees,state
Extract:
repo:frontend / repo:backend / repo:both and parity-requiredIn parallel:
C:\Users\thoma\Documents\Programming\Projects\orbit-ui-mobile\CLAUDE.md (root + scoped per workspace)C:\Users\thoma\Documents\Programming\Projects\orbit-api\CLAUDE.md (root + scoped per project)WORKFLOW.md (repo root)--quick)orbit-ui-mobile (focus areas based on issue labels):
| Issue scope | Read |
|---|---|
| Always | packages/shared/src/types/, packages/shared/src/api/endpoints.ts, packages/shared/src/query/keys.ts |
| Frontend | A representative feature in apps/web/app/(app)/ and apps/mobile/app/ + matching hook |
| Backend | A representative CQRS feature in orbit-api/src/Orbit.Application/ |
orbit-api (if backend or both):
src/Orbit.Application/Habits/ as the canonical CQRS examplesrc/Orbit.Domain/Entities/Habit.cs for entity patternstests/Orbit.Application.Tests/Commands/Habits/ for test patterns (unit tests only — no integration suite)git -C "C:\Users\thoma\Documents\Programming\Projects\orbit-ui-mobile" log --oneline -10
git -C "C:\Users\thoma\Documents\Programming\Projects\orbit-ui-mobile" branch --show-current
git -C "C:\Users\thoma\Documents\Programming\Projects\orbit-api" log --oneline -10
git -C "C:\Users\thoma\Documents\Programming\Projects\orbit-api" branch --show-current
User passed 2+ issue numbers. Create one paired worktree per issue, prime each one in a background subagent, and report all paths when done.
gh issue view <N> to confirm it exists.For each issue N, create matched issue-<N> worktrees in BOTH repos with git worktree add (branch name mirrors the issue number):
git -C "C:\Users\thoma\Documents\Programming\Projects\orbit-ui-mobile" worktree add ".claude/worktrees/issue-<N>" -b issue-<N>
# only if the issue's Repos label is `backend` or `both`:
git -C "C:\Users\thoma\Documents\Programming\Projects\orbit-api" worktree add ".claude/worktrees/issue-<N>" -b issue-<N>
issue-<N> (mirroring the issue number)C:/Users/thoma/Documents/Programming/Projects/orbit-ui-mobile/.claude/worktrees/issue-<N>C:/Users/thoma/Documents/Programming/Projects/orbit-api/.claude/worktrees/issue-<N> (if the issue's Repos label is backend or both)Use the Agent tool to spawn ONE subagent per issue, in parallel (multiple Agent tool calls in a single message). Each subagent:
cwd set to the orbit-ui-mobile worktree path./prime <N> inside its worktree (single-issue mode).Concurrency cap: 3 subagents at a time. Queue the rest. (Pass excess as a follow-up batch when the first batch completes.)
When all subagents return, print a single table:
Issue Title Repos Parity Worktree
#100 Add streak freeze both yes .claude/worktrees/issue-100
#101 Fix timezone bug frontend yes .claude/worktrees/issue-101
#102 Migrate to new validator backend no .claude/worktrees/issue-102
Then list any failures (subagent error, worktree creation failure) with the underlying message.
Scannable summary:
Keep it concise. Bullets, not paragraphs.
The aggregated table + suggested next step:
/plan <A> <B> <C> # same N issues, parallel plans
Single-issue: /plan {issue-number}
Multi-issue: /plan <N1> <N2> <N3> (continues the parallel flow)
Deep code review of a diff across both Orbit repos against one shared rubric, orchestrating the five review subagents and a backward-compat guard. Use when the user asks to review a PR, file, folder, or staged changes in orbit-ui-mobile or orbit-api. Replaces /review and /security-review.
Get an independent cross-model second opinion (GLM-5.2 via opencode) on a specific, load-bearing technical claim or a Critical code-review finding — a different model reads the claim + code and returns AGREE / DISAGREE / UNSURE. Use to stress-test a single Critical finding, a risky assertion, or a close call before you commit to it. Auto-fired inside /pr-review on each Critical finding that survives the skeptic. Not for open-ended research (use /deep-research) or multi-lens judgement (use /llm-council).
Break a PRD into GitHub issues across orbit-ui-mobile + orbit-api
Answer an open-ended "what's the best way to…?" question with orchestrated multi-agent deep web research. Decompose the question, fan out narrow research subagents in parallel, verify the load-bearing claims adversarially, iterate to saturation, then synthesize ONE opinionated, source-backed, decision-ready recommendation. Orbit-aware (dual-repo stack, solo-dev cost calibration). Use for technology/vendor choices, architecture & tooling decisions, cost comparisons, migration approaches, or best-practice questions — anything whose answer needs current external evidence beyond the codebase. Not for code edits, single-fact lookups, or questions answerable from the repo alone.
Create implementation plan with cross-repo codebase analysis
Repo-wide code-quality audit across both Orbit repos against the same rubric /pr-review uses. Reports dead/stale code, SOLID/clean-arch violations, comment-policy breaks, DRY, naming, function size, and DESIGN.md drift — each finding evidence-backed with file:line. Use when the user asks to audit code quality, find tech debt, or check the codebase against the standards. Not for a single diff (use /pr-review).