726 skills · sorted by relevance
Turn a vague intention into a concrete goal with clear scope, measurable success criteria, and evidence of completion. Check existing goals before creating one, so the agent has a specific outcome to pursue without duplicating active work.
Create, edit, and review agent skills against a shared authoring standard. Clarify goals, completion conditions, and responsibilities, remove unsupported instructions, and validate changes according to their risk, with a report explaining what changed and why.
Publish or update a NemoClaw pull request and track automated checks and reviews through completion. It preserves the requested scope, coordinates repairs for valid findings, and reports the latest commit’s results and remaining blockers.
Turn a feature idea into a structured product requirements document. Clarify goals and scope through multiple-choice questions, then produce a Markdown file with small implementation tasks, checkable completion criteria, functional requirements, and success measures.
Convert an existing product requirements document into Ralph’s prd.json format. Break large features into small implementation tasks, order them by dependencies, and define checkable completion criteria so Ralph can work through them in sequence.
Build a daily or weekly worklog from recorded activity and checked outcomes. Separate plans, observed work, and verified completion, then summarize useful results and unfinished tasks with source links and clearly marked gaps or estimates.
Prepare a beta release of Paseo by following the project's release documentation. The skill directs the agent through the beta workflow and its completion checklist, keeping the task tied to the documented process.
Guides AI agents through repeated failures, passive behavior, and incomplete work using structured investigation, alternative approaches, and evidence from actual checks. It pairs these practices with forceful coaching modeled on corporate performance reviews.
Guide Pi agents through repeated failures or unverified completion using competing hypotheses, small verifiable actions, and relevant checks. It separates self-review from external pass-or-fail decisions and requires evidence and remaining risks in delivery reports.
Use cmux on macOS to organize visible teams of AI agents, send prompts, inspect terminal output, and monitor completion. Set up role-based teams or have several agents investigate the same problem; live operation remains unproven in the supplied material.
Turn an unclear idea into a specification with testable completion criteria. The skill supports discovery interviews, drafts from existing code, completeness checks, and records of decisions and verification in a shared project document.
Organize work in Linear with clear issue ownership, priorities, completion criteria, and delivery plans. Helps structure cycles, meaning time-boxed work periods, define project milestones, and plan automated status updates through GitHub integrations or the GraphQL API.
Monitor GitHub Actions builds and tests with the gh command-line tool. Track runs until completion, inspect branch or pull request checks, read failed job logs, and rerun failed jobs or entire workflows.
Create GitHub issues for OpenShell bugs, feature requests, and tasks using the gh command-line tool. Organize firsthand use cases, impact, and completion criteria into the project's templates, then return the created issue link.
Read CARLA Leaderboard result files to understand driving scores, route completion, and penalties. Investigate low scores, compare two runs, merge split results, or recalculate scores under version 2.0 or 2.1 rules without rerunning the simulation.
Coordinate work across an OpenRig agent team with clear assignments, attached context, completion criteria, and selected review checkpoints. Track queue status, identify blocked or idle owners, and resolve handoff gaps while leaving implementation with the assigned agents.
Manage OpenRig development work from setup to completion using shared specification, progress, and evidence files. Record what was actually checked and pass work to the next owner so handoffs and conversation compaction preserve the context.
Check whether a file creation or transformation task actually succeeded after an unclear execution error. Inspect output files and their contents to distinguish success, partial completion, and failure before deciding whether to retry.
Track tasks that require several output files with an upfront checklist, checks after each file is created, and a final review. Confirm that every required file exists and has a nonzero size before reporting completion.
Track every required output in a visible checklist, update progress as each is completed, and review the original requirements before finishing. When one output is blocked, try alternatives and continue work on the remaining deliverables.
Track every required output in tasks involving multiple files, reports, or recipients. Build a checklist, update each item with completion evidence, and review the original requirements before declaring the task finished.
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.
Add personality to interfaces through small interaction responses, completion animations, illustrations, and product-specific messages. Shape enjoyable moments around the brand and user context while preserving task flow, accessibility, and performance.
Design and improve welcome flows, empty screens, and guided tours that help new users complete their first useful task. Includes contextual hints, optional guidance, completion tracking, and ways to assess whether users understand what to do next.