725 skills · sorted by relevance
Work through project decisions one question at a time, with a recommended answer and a short explanation. Record settled choices in project documentation, including scope, completion criteria, constraints, risks, and unresolved questions.
Create goals and support ongoing progress using guidance for the relevant life area. Record commitments, consider changing priorities and competing goals, and review completion or extension when a goal’s timeframe ends.
Coordinate work between AI agents through MemPalace’s event log. Create tasks with clear goals and completion criteria, generate pasteable handoffs, track claims, and deliver patches for verification. Explicitly requested launches support Codex and Claude.
Design rewards for reinforcement learning, where feedback guides model behavior. Choose how to score outcomes and intermediate actions, check for scoring loopholes, and use independent tests to detect incomplete work presented as finished.
Design and troubleshoot agent workflows that stop too early or keep repeating. The skill explains how to separate creation from review, verify real results, give actionable repair instructions, and set clear completion criteria and resource limits.
Clarify ambiguous requests before implementation by asking a small set of essential questions. Use concise choices and suggested defaults to agree on goals, scope, constraints, and completion criteria before starting work that depends on those answers.
Manage coding work from issue intake through implementation, review, deployment, and acceptance checks. Track each completion requirement against fresh evidence, with defined retry limits and explicit escalation when progress needs human input.
Implement PR review actions already selected for fixes, run relevant checks, and create focused commits. Post progress and completion replies, resolve applicable threads, and update the action records and their Markdown summary.
Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.
Follow Conductor's development plans using test-driven development: write a failing test, implement the change, then improve the code. Manage phase verification, progress updates, and focused git commits as tasks move toward completion.
Break a large development brief into ordered goals and save plans, progress events, blockers, and evidence in the repository. Coordinate Claude Code sessions through handoff instructions, with final completion requiring cleanup, verification, and code review evidence.
Write or revise instructions, specifications, tickets, and skill files so an agent can act without prior chat history. Make rules checkable, explain their reasons, define completion criteria, and keep authoritative information in one place.
Prepare batches of merged SGLang pull requests for a release branch. It checks conflicts and previous attempts, starts the cherry-pick workflow, monitors completion, and reports created pull requests or failure reasons.
Compose compact, structured prompts for coding, debugging, review, and research with Codex or GPT-5.4. This internal skill defines task scope, completion criteria, output format, verification steps, and evidence requirements using consistent XML tags.
Coordinate a worker agent in a tmux-based OMX Team through startup acknowledgements, task claims, status transitions, and mailbox checks. Keep task ownership, completion evidence, and idle status visible to the team.
Review contact, lead capture, quote, survey, and checkout forms to identify obstacles to completion. Get prioritized recommendations for fields, layout, wording, mobile usability, and error messages, plus ideas for comparing alternative designs through tests.
Find current official documentation for OpenAI products and APIs, then get concise guidance with source citations. Use it to check implementation approaches, model capabilities, and limits, with code examples grounded in the documentation.
Ask AI questions, generate code, and summarize text through 9Router using OpenAI or Anthropic request formats. Receive responses incrementally with streaming, and use provider combinations that automatically try another provider when needed.
Build transcription workflows for uploaded or stored audio and video using Zoom AI Services Scribe. Consult guidance on authentication, single-file requests, batch jobs, completion notifications, and saving transcript results for further processing.
Design and audit an agent's system prompt, the instructions that guide its work. Define a concrete outcome, starting input, available tools, completion checks, fallback behavior, and final report so the prompt describes a complete run.
Design instructions for agents that write, fix, review, or refactor code. Define behavior based on file access, select suitable tools, and set clear verification and completion rules for repository changes or copyable code output.
Design a general-purpose assistant for tasks such as email summaries, short reply drafts, and note capture. The playbook defines task boundaries, completion criteria, and concise responses, with only the tools needed for the requested work.
Update the GitHub issue linked to completed Factory work after verifying the target repository. Remove specified triage labels and, for open issues, add a pending-close label and completion comment without closing the issue.
Turn a vague request into a goal with one outcome, verifiable completion checks, boundaries, a stopping agreement, and instructions for blockers. It drafts the objective for review without starting the work described.