codex-consult
Use when the user explicitly wants a Codex-side orchestration pass — consultation, curation, or review — instead of direct ChatGPT web automation. Triggers include "consult/analyze this with Codex", "curate these options with Codex", "review/critique this with Codex", or explicit mentions of codex_local_consult, codex_local_curate, codex_local_review, or the codex_orchestrator_* tools. One skill, three modes.
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- codex-consult
- description
- Use when the user explicitly wants a Codex-side orchestration pass — consultation, curation, or review — instead of direct ChatGPT web automation. Triggers include "consult/analyze this with Codex", "curate these options with Codex", "review/critique this with Codex", or explicit mentions of codex_local_consult, codex_local_curate, codex_local_review, or the codex_orchestrator_* tools. One skill, three modes.
03 SKILL.md 正文
⚠️ DEPRECATED (2026-07-18): this skill routes to tools that do not exist. The mounted Codex MCP exposes only
mcp__codex__codex(start a thread) andmcp__codex__codex-reply(continue by threadId). Thecodex_local_consult/curate/reviewandcodex_orchestrator_*tools referenced below were never mounted (no PromptBridge server). Usemcp__codex__codexdirectly (frame the mode in the prompt) or thecodex-invokeexec-rail until this skill is rebased onto the real two-tool surface.
Codex Consult
One skill for the local Codex orchestration lanes. Read the mode from the user's intent — the procedure is the same: dispatch a single scoped prompt to Codex and return its synthesis. There is no need for a separate skill per interaction; the prompt plus the chosen mode determines the behavior.
Modes
| Mode | Use when | Preferred tool (fallback) |
|---|---|---|
consult |
structured analysis, tradeoff review, decision or architecture support | codex_local_consult (codex_orchestrator_consult) |
curate |
compare options and select or synthesize the best one | codex_local_curate (codex_orchestrator_curate) |
review |
critique, audit, or pressure-test a plan or patch | codex_local_review (codex_orchestrator_review) |
Behavior
- Keep the task scoped and decision-oriented; pass one clear prompt.
- Prefer the
codex_local_*tool for the chosen mode; fall back to the matchingcodex_orchestrator_*tool if the local lane is unavailable.
Replaces
04 同仓库更多 Skills
clarify-requirements
Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.
openmm-md
Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein / protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.
visual-review
Take screenshots of web pages and UI using Playwright for visual review and iteration
status
Diagnostic status report — shows metaswarm installation state, project setup, and potential issues
start
Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work
setup
Interactive project setup — detects your project, configures metaswarm, writes project-local files