메뉴
Guides Gantry tool, skill, MCP server, browser, local CLI, semantic capability, inventory, and permission lifecycle work. Use when changing durable capability selection, visible attached sources, transient request_permission flows, or agent access review paths.
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
Orchestrate a Gantry plan to a finished PR — Claude writes a goal-prompt doc, delegates implementation stages to the Codex plugin (xhigh + ponytail), verifies and commits between stages, and closes with the autoreview loop. Use when the user asks to implement a plan/goal prompt, "run the goal pipeline", "same as the goal", or hands over a docs/architecture/*-goal-prompt.md to execute.
End-to-end Gantry plan implementation pipeline. Use when the user asks to implement or pursue a plan, goal prompt, feature, fix, refactor, PR update, or "same as the goal" workflow with subagent implementation, ponytail simplicity, no-commentary implementation, autoreview, build, launchctl restart, Knacklabs lead gen smoke, and PR/pipeline closeout.
Gantry self-administration reference for current host runtime operations: CLI commands, settings.yaml runtime settings, .env credential keys, agent management, scheduler tools, memory tools, browser tools, diagnostics, and service control. Use when asked to manage Gantry itself.
Drives Gantry agent-chat tests through the local Control API session path and captures assistant responses. Use when testing an agent response, permission prompt, skill behavior, or runtime chat flow without needing Telegram UI rendering.
Use when creating or revising a Gantry product, UX, permission, job, ingress, provider, settings, or agent-flow plan that must be decision-complete with no room for assumptions. Triggers for PM plan, product manager plan, no assumptions, UX flow, user flow, agent flow, acceptance criteria, validation plan, provider-neutral plan, or Surface Impact Matrix.
Drives Gantry tests through the visible Telegram UI with Chrome. Use only when testing Telegram rendering, Telegram buttons, topic routing, or visible Telegram conversation behavior; use agent-chat-test for direct runtime agent-chat tests.
| name | capability-lifecycle |
| description | Guides Gantry tool, skill, MCP server, browser, local CLI, semantic capability, inventory, and permission lifecycle work. Use when changing durable capability selection, visible attached sources, transient request_permission flows, or agent access review paths. |
Use this skill for durable agent capability work and for changes that could blur visibility, inventory, authority, or one-off permission grants.
docs/architecture/capability-management.md, docs/decisions/2026-05-20-simple-permission-and-job-tool-lifecycle.md, and docs/architecture/codebase-refactor-principles.md.sources are attached/onboarded resources, capabilities are durable authority, and inventory is read-only discoverability.request_access (target.kind=capability) for reviewed semantic capability changes, Browser, exact Gantry admin tools, and provider/channel permissions.request_access (target.kind=run_command) only for one-off exact command access or scoped RunCommand(<literal argv pattern>) fallback when no reviewed capability fits.browser.use; do not persist provider-private browser tool names as authority.local_cli capabilities, require pinned executable identity, auth/preflight, protected paths, denied environment overrides, and reviewed command templates.sources, capabilities, inventory, transient permission, or runtime projection.