3846 个 · 按相关度排序
Execute an implementation plan in one session by assigning a fresh subagent, a separate task-focused agent, to each task. Check specification compliance first, then code quality, and repeat fixes and reviews before proceeding.
中文简介正在准备中。当前显示英语简介。
Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.
中文简介正在准备中。当前显示英语简介。
Evaluate a proposed software change before implementation. It examines project files and official sources, compares options and trade-offs, and builds a concrete plan covering affected systems, effort, risks, and unresolved questions for the user's approval.
中文简介正在准备中。当前显示英语简介。
Create the OpenSpec documents needed to begin implementing a feature or fix. Follow the workflow's dependency order and templates, using completed documents as context until all prerequisites for implementation are ready.
中文简介正在准备中。当前显示英语简介。
Convert a Notion specification into a linked implementation plan and manageable tasks. Extract requirements and acceptance criteria, record uncertainties, and keep task statuses, checklists, blockers, and milestone updates aligned as the work progresses.
中文简介正在准备中。当前显示英语简介。
Apply Apache ShardingSphere’s written coding standards during implementation or review, covering naming, Java constructs, tests, and Maven dependencies. Also audit a specified scope without editing files, combining automated checks with manual inspection of applicable rules.
中文简介正在准备中。当前显示英语简介。
Convert a Notion specification into a linked implementation plan and manageable tasks. Extract requirements and acceptance criteria, record uncertainties, and keep task statuses, checklists, blockers, and milestone updates aligned as the work progresses.
中文简介正在准备中。当前显示英语简介。
Draft and refine Linear or Superset tickets using a consistent structure for context, references, and implementation notes. Clarify the desired outcome, record where requests came from, and add code details when enough context is available.
中文简介正在准备中。当前显示英语简介。
Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.
中文简介正在准备中。当前显示英语简介。
Checks cryptographic code against known attacks and edge cases using Project Wycheproof test vectors, predefined inputs and expected results. Helps load cases, interpret failures, compare implementations, and integrate checks into automated testing.
中文简介正在准备中。当前显示英语简介。
Review token contracts and the protocols that accept them for ERC20/ERC721 compliance, privileged controls, and unusual transfer behavior. Produces evidence-based risk assessments and prioritized fixes, with supply and holder analysis when deployed contract details are provided.
中文简介正在准备中。当前显示英语简介。
Compare implementation code with a specification, whitepaper, or design document. It checks individual requirements, independently challenges reported mismatches, and writes evidence-based reports covering missing or partial implementation, contradictions, undocumented behavior, and requirements that cannot be judged.
中文简介正在准备中。当前显示英语简介。
Turn Notion product requirements and feature specifications into linked implementation plans and manageable tasks. Extract requirements, flag ambiguities, and keep task status, milestones, blockers, and decisions aligned as work progresses.
中文简介正在准备中。当前显示英语简介。
Guide code changes in iPolloWork by reusing existing implementations, limiting new files and dependencies, and keeping responsibilities clear. Review runtime costs, run focused checks, and audit the final changes for duplication and maintainability issues.
中文简介正在准备中。当前显示英语简介。
Compare a Linear issue and its acceptance criteria with implementation evidence. Identify gaps, retain links to tests and pull requests, and update progress only when the relevant implementation, review, or deployment milestone is supported.
中文简介正在准备中。当前显示英语简介。
Fetch design structure, screenshots, variables, and assets from Figma through MCP, a connection between the agent and Figma. Use these references to guide code implementation within an existing project and troubleshoot connection setup.
中文简介正在准备中。当前显示英语简介。
AI DevKit · Implementation phase guidance for executing feature plans and checking implementation against design. Use when the user wants to implement planned tasks, update implementation docs, verify code matches design, or run dev-lifecycle phases 5 and 7.
中文简介正在准备中。当前显示原文说明。
Break a trusted implementation plan (or other provided context) into independently-grabbable, atomic work items, written to a single work-items.md file. Use when the user wants to convert a plan into work items, create implementation tickets or tasks, divide a plan into work units, or break the plan down into grabbable pieces. Do not use when there is no implementation plan yet or the plan is not yet trusted — use plan-implementation to produce the plan or iterative-plan-review to harden it first. Does not sequence work into demoable delivery phases — use plan-a-phased-build for that. Does not write code — use tdd to implement a work item.
中文简介正在准备中。当前显示原文说明。
Authentication & Authorization Implementation Patterns workflow skill. Use this skill when the user needs Build secure, scalable authentication and authorization systems using industry-standard patterns and modern best practices and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
中文简介正在准备中。当前显示原文说明。
Authentication & Authorization Implementation Patterns workflow skill. Use this skill when the user needs Build secure, scalable authentication and authorization systems using industry-standard patterns and modern best practices and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
中文简介正在准备中。当前显示原文说明。
Study a merged or shipped tdmcp implementation and extract reusable learnings: code improvements, runtime/UX lessons, test gaps, docs updates, roadmap items, and harness changes. Use when the user asks to learn from a completed feature/project/PR/build, analyze what can be improved from an implementation, or turn a real installation experience into actionable tdmcp improvements. This is a post-implementation learning harness; it does not replace tdmcp-pipeline for building or tdmcp-quality-audit for broad repo audits.
中文简介正在准备中。当前显示原文说明。
Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE after completing any significant implementation work. Triggers: 'review work', 'review my work', 'review changes', 'QA my work', 'verify implementation', 'check my work', 'validate changes', 'post-implementation review'.
中文简介正在准备中。当前显示原文说明。
Delegate implementation to Codex or to a sandboxed Claude Code (`claude -p`), have a model from the other vendor review the diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex or a sandboxed Claude to write code, mentions handing off / delegating implementation to one of those backends, asks for a cross-vendor review of delegated code, asks to work through a plan or spec unit-by-unit with an implementation backend doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer runs in the real environment behind backend-specific git and publication boundaries, must not be pointed at a full test suite by default, and its self-report is a claim rather than evidence. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the engineering-mode skill when it is installed.
中文简介正在准备中。当前显示原文说明。
Delegate implementation work to a dedicated implementer subagent, then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants a separate model to write code, mentions handing off / delegating implementation, asks to work through a plan or spec unit-by-unit with a subagent doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer self-reports success, must not run the full test suite by default, must not touch git, and its report is a claim rather than evidence. Cursor port of implementation-loop. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the cursor-engineering-mode skill (it ships in this same plugin).
中文简介正在准备中。当前显示原文说明。