828 skills · sorted by relevance
Route pricing, discount, partnership, sales channel, proposal response, and bookings forecast questions to one of seven specialist skills. Receive a concise digest of findings, recommended actions, and output files to support commercial decisions and human approval.
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.
Evaluate a technology adoption question, a document, or proposed approaches against project evidence and constraints. Receive a supported position with tradeoffs and uncertainty, with an optional panel that consults other models and reconciles their views.
Explain how something works, why it took its current form, or what happened during a period of work. Use supporting evidence, distinguish documented reasons from inference, and adapt the answer or document to its readers.
Triage employee questions in an HR inbox against policies documented in Notion. Prepare Gmail drafts with policy references for routine questions, and route ambiguous, legal, personal, or compensation matters to HR through Slack.
Assign new HubSpot leads to sales representatives using territory, specialist rules, and weekly lead counts. The skill records assignment reasons, highlights strong buying signals in Slack, and escalates cases that need human judgment.
Check a paper's numerical consistency using fixed rules, then record blocking or warning decisions and outstanding findings. The workflow preserves a traceable correction history, while explicitly leaving broader semantic review unavailable in its Codex mode.
Independently checks code changes against the original issue, runs tests, and verifies that edits stay within scope. Produces an approval, rejection, or request for human judgment, supported by test results and specific findings.
Inspect recent merges for leftover debug code, TODO comments, lint warnings, and technical debt, meaning deferred maintenance work. Create a prioritized cleanup list that separates small fix candidates from issues requiring human judgment.
Explore the overview and terminology of The Almanack of Naval Ravikant, or reflect on happiness, meditation, relationships, and judgment. The skill selects relevant book material and prioritizes separate topic skills when they are installed.
Test polly's coordination of coding agents using a scripted mock language model and live command-line tools. Check startup, task dispatch, safety rules, parallel delegation, and whether real agents make appropriate orchestration decisions.
Research employment questions about overtime, breaks, leave, worker classification, and final pay for a specific state or country. Receive an answer with cited legal sources, notes on recent changes, and issues requiring professional judgment.
Build your own case brief with a preferred template, focused questions, and feedback on your understanding. The skill guides legal study by checking facts, issues, holdings—the court’s answers—and reasoning, while flagging uncertain interpretations.
Compare AI regulations or guidance with existing company policies and practices. Determine applicability, identify missing requirements, and create a prioritized remediation plan with owners and deadlines, while highlighting legal uncertainties that need attorney judgment.
Review OpenClaw frontend code and rendered screens for departures from Carapace design rules, accessibility issues, responsive defects, and inconsistent copy. Produce evidence-based JSON and Markdown reports that distinguish documented violations from judgment-based suggestions and guide narrowly scoped fixes.
Classify agent work as ready to continue, needing human judgment, or intentionally paused. Structure decision requests with evidence, a recommended choice, and clear outcomes, then connect the recorded decision to the next responsible agent.
Choose, build, and review charts that answer a clear analytical question. The skill checks chart types, labels, units, colors, and data sufficiency, then refines the visual in its intended report, dashboard, notebook, or other output.
Use when the user explicitly wants autonomous progress without routine clarification stops: "plow ahead", "do not stop", "use your best judgment", "keep going until done", "finish while I am away", "do not ask questions unless truly blocked", or similar. Convert ordinary ambiguity into stated assumptions, proceed through implementation and validation, stop only for true blockers, and end with a clear recap of decisions, changes, verification, and residual risk.
The English summary is being prepared. Showing the original description.
Experimental workflow for summarizing work that still needs human judgment across configured pull requests, issues, feedback, errors, and delivery signals. Use for a human decision queue or bounded review.
The English summary is being prepared. Showing the original description.
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
The English summary is being prepared. Showing the original description.
Research technology and advanced-manufacturing investments using Serenity-inspired supply-chain bottleneck analysis. Use for theme scans, company thesis challenges, candidate comparisons, or learning this method. Prioritize A-shares unless another market is requested. Return research priorities, dated evidence, profit implications, and conditions that would change the judgment.
The English summary is being prepared. Showing the original description.
Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level.
The English summary is being prepared. Showing the original description.
Compare research records you provide to see changes in facts, scores and judgments. Use when the user asks to investment review with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
The English summary is being prepared. Showing the original description.
Find connections between notes and update MOCs. Requires semantic judgment to identify genuine relationships. Use after /reduce creates notes, when exploring connections, or when a topic needs synthesis. Triggers on "/reflect", "/reflect [note]", "find connections", "update MOCs", "connect these notes".
The English summary is being prepared. Showing the original description.