메뉴
Diagnose/fix worktrees missing the generated openspec-* (opsx) skills after worktreeInit. Root cause: bare `npx openspec` can resolve a squatted registry stub instead of the real CLI.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | fix-worktree-opsx-skills-not-created |
| description | Diagnose/fix worktrees missing the generated openspec-* (opsx) skills after worktreeInit. Root cause: bare `npx openspec` can resolve a squatted registry stub instead of the real CLI. |
| version | 1 |
| created | 2026-07-13 |
| updated | 2026-07-13 |
Use when a git worktree lacks the OpenSpec experimental-workflow skills (.pi/skills/openspec-explore, openspec-new-change, etc.), the /opsx: slash commands are missing, or openspec-apply-change stalls in a worktree. Also when auditing the .pi/settings.json worktreeInit hook.
.pi/.gitignore has skills/openspec-*/** (only openspec-shared is tracked). So every fresh worktree starts without them and must regenerate via openspec init.openspec binary is provided by the SCOPED package @fission-ai/openspec (declared in packages/server, hoisted to root node_modules/.bin/openspec). The BARE name openspec on npm is a squatted 0.0.0 stub that does nothing.npx openspec init .... When the local .bin/openspec isn't resolvable from the worktree root (hoisting/install timing/npx cache), bare npx openspec fetches openspec@0.0.0 → init creates nothing → no opsx skills, while the && chain still exits 0.npx @fission-ai/openspec init --tools pi --force. npx then resolves the local install (or fetches the CORRECT scoped package) and can never hit the 0.0.0 stub.npx @fission-ai/openspec init --tools pi --force → ls .pi/skills/ | grep openspec- shows 8 generated skills + openspec-shared (9 total). CLI prints 8 skills and 8 commands in .pi/ and /opsx:new.npx @fission-ai/openspec init --tools pi --force (safe — the openspec-* dirs are gitignored so this won't dirty git).npx --no-install @fission-ai/openspec in a worktree that hasn't run npm ci yet — nothing is installed, so it errors. The worktreeInit chain runs (npm ci || npm install) FIRST, so plain npx @fission-ai/openspec is correct.test ! -d .pi/skills/openspec-explore correctly re-triggers init when only the skills are missing (OR-chained), so the gate is fine — the bug was the command, not the gate.openspec init --force may rewrite tracked AGENTS.md/CLAUDE.md; the gitignored .pi/skills/openspec-* dirs are safe to (re)generate.Ship an OpenSpec change after openspec-apply completes. When only QA/manual tasks remain, marks them done (tested later), archives + syncs specs, commits, pushes, opens a PR against develop, watches CI, waits for CodeRabbit, auto-applies safe fixes and re-pushes, loops until CI green + no actionable review threads, then squash-merges with branch delete and removes the worktree. Use after implementation is done and the change is ready to land. Triggers: "ship this change", "ship it", "land the change", "merge and clean up", "post-apply ship".
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality (test file exists + passes in the docker harness), not the tasks.md checkbox. Owns the red-test fix loop (never re-invokes apply on a checked task), runs the docker harness on its auto-derived port with always-teardown, then drives ship-change INLINE with a manifest-aware defer. Boundary-reverse escape hatch writes SHIP_IT_BLOCKED.md. Runnable headless. Triggers: "ship it", "build and ship this change", "run ship-it", "implement + test + land in the worktree".
Switch a monorepo extension/skill package between its published npm source and its local working-tree source, guaranteeing exactly one source per package. Use when "my edits don't take effect", "load local extension", "test the published npm build", or reconciling dev vs distribution package sources.
Generate and edit images using Google Gemini image models via the nano-banana CLI. Use when the user asks to create, generate, make, or edit images with AI. Supports text-to-image, image editing, style transfer, and multi-image composition. Trigger on requests like "create an image", "generate a picture", "make me a logo", "edit this photo", "add X to this image".
Render a scripted video project into mp4 clips with the Google Veo 3.1 API. Reads a project's shot package (the shots/*.md format produced by the veo-showreel-production-kit) and generates one clip per camera cut — reusing the Full Veo prompt, negative prompt, seed, aspect/resolution, world-anchor reference and first-frame storyboard sketch already written in each shot file. Backed by the `pi-veo` CLI (a TypeScript port — no Python). API key is configurable per project via a .env. Use when: "render the Veo video for <project>", "generate the videos from the shot scripts", "make the clips with Veo", "re-render shot 03B".
Turn a video timeline + voiceover into a reproducible, sliceable Veo 3.1 prompt package with a consistency anchor and AI storyboard sketches.