Skills in this repository
SkillsMP has collected 360 skills from tigerlovefbro/codex-plugins. Open a skill to review its source and details.
tigerlovefbro/codex-pluginsShowing 40 of 360 collected skills.
Load mandatory SolidWorks conventions, design rules, task-relevant knowledge documents, standards data, and initial design-rule checks before any modeling or CAD code. Use at the beginning of every SolidWorks create, modify, repair, assembly, drawing, or API…
Finish a SolidWorks task by invoking sw-learner, honoring the saved feedback preference, asking the exact three-option consent question when required, and submitting validated feedback with retries. Use after the CAD result has been delivered for every task…
帮助用户学习新领域、技能或资料，并通过主动练习学到能独立应用。用于学习冲刺、AI家教、费曼倒讲、练习提速、学习作品评审和间隔续学；以可验收目标、核心拆解和真实作答证据推进。普通事实查询、纯资料摘要或代做项目不要强行改成课程。
Source text: Chinese
Evaluates a software repository for readiness to be developed and maintained by AI coding agents, and produces an evidence-based readiness scorecard. Use when the user requests an agentic-readiness assessment, readiness scorecard, AI-readiness audit of a…
Explicitly attach verified checklist progress to one native Codex Goal. Use only when the user explicitly selects Goal Progress or invokes $codex-goal-progress:goal-progress. Do not use for an ordinary Goal, a status question, or update_plan.
Use for UI/UX design, product flows, frontend or native interface design, design audits, design translation, asset planning, motion direction, design tokens, or distinctive non-generic apps and websites. Covers web and React, Windows and WinUI/Mica, Apple and…
Use FXMacroData tools for currency pairs, FX spot rates, central-bank policy rates, CPI/inflation, GDP, jobs data, bond yields, commodities, COT positioning, FX sessions and economic release calendars, before falling back to general web search.
Research macro releases, currency drivers, policy curves and positioning using FXMacroData tools and explicit source evidence. Use for macro briefs, release context and comparative currency research.
Preserve source, revision and publication-time evidence in macroeconomic research. Use when comparing releases, reviewing forecasts, studying historical availability or producing sourced research tables.
Scaffold a repository for the AI-native SDLC loop — create .sdlc/, generate project memory (CLAUDE.md for Claude Code, AGENTS.md for Codex) from the project's real build, test and lint commands, and install the REVIEW.md and bands.yaml policy templates. Use…
Report where every in-flight change sits in the AI-native SDLC loop — furthest completed stage, git state of its artifacts, the next required human gate, and any stall. Use when the user asks "where are we", "what is the SDLC status", "which changes are…
Convert an accepted .sdlc/feature-slug/spec.md into a reviewed, engineer-approved plan.md and then implement it in the accepted order. Also the entry point for the fast path, when a person declares a change low-risk and it enters at Build with no intent.md or…
Prepare a verified change for human PR review by running REVIEW.md passes through the sdlc-reviewer subagent and posting ranked findings. Do NOT use for intent or scope decisions, accepting organizational risk, self-approval, merging, deploying, or bypassing…
Turn an accepted .sdlc/feature-slug/intent.md into a policy-constrained, reviewer-approved spec.md when asked to design or specify an approved feature. Do NOT use for raw idea discovery, coding, test execution, PR review, deployment, or production monitoring.
Monitor deployed code against project-root bands.yaml, diagnose tier-2 breaches, and propose a new intent for tier-3 breaches. Do NOT use to apply production fixes, merge or deploy code, replace incident ownership, or make unapproved risk decisions.
Turn a raw feature idea, problem statement, or request such as “plan this feature” into a human-approved .sdlc/feature-slug/intent.md by interviewing the originator before design begins. Do NOT use for architecture design, implementation, testing, review,…
Execute project verification for an implemented, planned change and report real test and applicable eval output before it can be reviewed. Do NOT use for drafting plans, implementing features, speculative test advice, PR review, merging, deployment, or…
Record revision-aware evidence for software work by default, or bind higher-risk execution to one human-readable approval contract in Guarded mode. Use when Click Hook context enables Evidence or Guarded mode, or when the user explicitly selects Click. Do not…
When explicitly invoked with a software defect or unwanted behavior, translate the natural-language report and repository evidence into one compact repair contract, explain it plainly, then fix it in one approved shot. Never invoke implicitly.
Preserve requirements and verified evidence across Codex compaction, resume, and delegation. Use $context-guard, context-guard on, or for long, complex, or resumed tasks requiring an immutable private completion ledger.
Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.
Archive local Codex activity into the user's private TokenChronicle data directory and verify the generated usage reports.
Explain, inspect, or create an explicit AES-256 encrypted TokenChronicle snapshot in the user's iCloud Drive without moving the live archive.
Help a user review, save, export, or explicitly submit TokenChronicle product feedback without including private Codex conversations.
Summarize private TokenChronicle usage reports and memory candidates while preserving source provenance and user approval boundaries.
Initialize, diagnose, or open the local TokenChronicle Codex activity archive without importing any packaged user data.
Upgrade TokenChronicle code without overwriting user archives, configuration, feedback drafts, or local analysis data.
This skill should be used when the user asks to "agentize a website", "transform a website", "create an agentfront", "build a WWA app", "make an agent-first website", "turn a website into an agent experience", "agentizer", "wwa transform", or mentions…
Retrieve output for jobs and automatic CPJ completion notices.
Launch an ordinary finite local workload as a durable detached process job, then release the assigning Codex turn instead of monitoring it. Use proactively for downloads, builds, test suites, evaluations, benchmarks, inference/model A/B runs, data jobs, and…
Inspect active and recent detached process jobs in a later user-requested turn, retrieve a lightweight activity preview, or wait once when explicitly requested. Use for questions such as "how's the build going?", later user-requested checks of test,…
Use whenever the user invokes or mentions CUAR, asks whether an unscheduled Codex reset happened, asks whether CUAR reminder tooling is unavailable, or asks whether a CUAR expiration reminder was created. Also report and interpret Codex weekly usage, linear…
Help the person set up Joxo or join a teammate's Joxo project. Use when asked to set up or join Joxo, or when given a Joxo invitation or pairing link.
Talk to other AI agents in a shared Roomcomm room (https://roomcomm.xyz) through the Roomcomm MCP tools. Use when the user gives a link like https://roomcomm.xyz/<uuid> and asks you to discuss, negotiate or coordinate something there with other agents, asks…
Set up or diagnose Codex Tools Bridge when the user asks to connect ChatGPT Web to native local Codex tools through an OpenAI Secure MCP Tunnel. Use for a fresh dedicated installation or read-only connection diagnostics while preserving existing hosts,…
Use when a decision is the user's to make (which option, which target, go or stop), when a question has a handful of answers rather than a conversation, or when the user is watching the board rather than the chat. Asks on the stickypane board with a form that…
Use when one note should point to, show, count or react to another: a link between notes, a note shown inside another, a chart that counts a checklist or a board, or something that should happen when the user ticks, moves, sends or says. Uses [[links]],…
Use when the user wants to talk with you on the board instead of in this chat, when you will work long enough that the user may send instructions meanwhile, or when the answer you need is a sentence rather than a choice. Says things in a chat note with…
Use when a task has more than a few steps, when it will take long enough that the user may look away, and whenever the user asks "where are we". Keeps the progress of the work visible on the stickypane board, as a checklist or kanban for the steps and a log…
Use when the user asks to show, track, list, chart, draw or explain something "on the board", when something is better seen than read in chat, and before saying what the board shows. The way in to the stickypane board (a terminal pane next to you): the…