781 skills · sorted by relevance
Write and review asynchronous C++ networking code using Boost.Asio or standalone Asio. The skill selects an implementation style for the installed library and C++ version, then checks memory lifetimes, concurrent writes, error handling, and build settings.
Implement pending tasks from an OpenSpec change, a planned set of development work. The skill reads relevant specifications and design files, makes focused code changes, and updates task completion as work progresses.
Archive several OpenSpec changes together after reviewing their documents, task completion, and specification conflicts. The agent checks actual code to decide which specification updates to apply, asks for confirmation, and reports successes, skipped changes, and failures.
Archive an OpenSpec change after checking its documents, task completion, and specification differences. The skill offers a choice about updating the main specifications, then moves the change into a dated archive and reports the result.
Manage shared project tasks in Beads, from finding available work and claiming tasks to tracking dependencies, recording follow-up work, and closing completed items. Keep project status available across sessions and handoffs.
Track work across sessions with persistent issues, dependencies, and progress notes. Use the bd command-line tool to find unblocked work, claim issues, record completion, and recover task context after conversation compaction.
Guide a pull request through conflict resolution, review feedback, and automated checks. The skill monitors progress, fixes failures, and completes a squash merge, combining the branch’s changes into one commit once checks and reviews are addressed.
Read sprint plans and work records to summarize completion, remaining time, blocked tasks, and emerging risks. Compare progress with elapsed time, flag stale work, and provide a concise status report with at most one recommended action.
Review a completed development task against its acceptance criteria, check differences from design and architecture documents, and prompt code review. After approval, update the task's status and identify the next story to work on.
Coordinate role-based agents to design, implement, integrate, and test a game combat feature. The workflow covers gameplay rules, enemy behavior, visual effects, and audio planning, with a final report on completion, test results, and unresolved issues.
Review test files and manual verification records for development tasks. Check whether expected behavior, edge cases, screenshots, and required approvals are covered, then report evidence gaps and distinguish completion blockers from advisory improvements.
Review a sprint or milestone by comparing planned work with actual results. Summarize completion, estimation gaps, and blockers, then produce a retrospective with specific improvement actions, owners, and deadlines for the next iteration.
Review a development milestone using sprint reports, feature status, bugs, and risks. Summarize completion, quality, and delivery pace, then recommend whether to proceed, proceed with conditions, or stop, with scope choices and action items.
Control a running OpenWork app from the shell to inspect UI changes and reproduce chat states. Start fresh sessions, select models, send prompts, wait for completion, capture screenshots, and run JavaScript, with no visible window by default.
Turn a named NemoClaw issue into an implementation plan with clear ownership, scope, completion criteria, and validation evidence. For larger changes, define independently useful steps, their dependencies, and delivery order.
Find repeated tasks in recorded activity or starred examples, then describe their steps, exceptions, and human decisions. Assess a small automation candidate using captured evidence, available tools, permissions, and clear completion criteria.
Prepare a stable Paseo release by following the documented release flow and completion checklist. Use it for a fresh patch or minor release, or to promote a beta version to stable.
Turn a brief idea into a task brief an AI agent can execute independently. Ground it in investigation, define scope and acceptance checks, and include progress tracking and recovery instructions in a brief ready for `/goal`.
Call Gemini and OpenMaaS models such as Llama, DeepSeek, and Qwen through Google Cloud Agent Platform. Prepare authentication and SDK code, run prompts, configure connection endpoints, and troubleshoot common request errors.
Review Apache ShardingSphere pull requests or authorized downstream changes using repository evidence. Assess code correctness, merge readiness, or CI failures, then produce consolidated findings or a ready-to-copy reply to a review discussion.
Use pointed workplace reminders inspired by 《置身钉内》 and 《置身钉外》 to examine reports, meetings, and delivery claims. Turn organizational concerns into concrete next steps and check completion against user outcomes and evidence.
Guide an AI agent through repeated failures, passive behavior, or unverified completion with strict Japanese coaching. It structures investigation, encourages different approaches, and requires evidence before reporting work as complete.
Help an AI agent work through stalled coding, research, writing, and other tasks using diagnosis, alternative approaches, and evidence-based verification. It combines stern corporate-style roleplay with escalating checks and structured handoffs when problems remain unresolved.
Switches AI productivity coaching to a Chinese-mother nagging style while retaining the core PUA investigation and verification rules. It provides situation-specific narration and increasingly forceful reminders as failures accumulate, including prompts to try different approaches.