702 skills · sorted by relevance
Use when the user asks to "audit our launch plan", "are we ready to launch", or evaluate launch execution/outcomes; runs one typed RAMP preflight, execution, or outcome profile without mixing time horizons. Not for recording launch state — use launch-registry; not for running launch day — use launch-day-conductor. 发布就绪审计/RAMP分阶段评估/发布前放行
The English summary is being prepared. Showing the original description.
Tests associations between categorical variables in clinical data using chi-square, Fisher's exact, Boschloo, Cochran-Mantel-Haenszel, and modern McNemar variants with calibrated confidence intervals (Wilson, Newcombe, Miettinen-Nurminen). Use when analyzing categorical outcomes, paired binary endpoints, or testing treatment-outcome independence in confirmatory or exploratory clinical trials.
The English summary is being prepared. Showing the original description.
Drug and chemical toxicity assessment via adverse outcome pathways (AOPs), real-world FAERS adverse event signals, FDA labels, and toxicogenomic associations. Triangulates molecular initiating event to cellular outcome to organ-level toxicity to clinical adverse event. Use for hepatotoxicity/cardiotoxicity/nephrotoxicity prediction and toxicology reports.
The English summary is being prepared. Showing the original description.
Tests associations between categorical variables in clinical data using chi-square, Fisher's exact, Boschloo, Cochran-Mantel-Haenszel, and modern McNemar variants with calibrated confidence intervals (Wilson, Newcombe, Miettinen-Nurminen). Use when analyzing categorical outcomes, paired binary endpoints, or testing treatment-outcome independence in confirmatory or exploratory clinical trials.
The English summary is being prepared. Showing the original description.
Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with structured-planning and debug-and-fix. Does not replace root-cause debugging — adds plan-level path selection.
The English summary is being prepared. Showing the original description.
Tests associations between categorical variables in clinical data using chi-square, Fisher's exact, Boschloo, Cochran-Mantel-Haenszel, and modern McNemar variants with calibrated confidence intervals (Wilson, Newcombe, Miettinen-Nurminen). Use when analyzing categorical outcomes, paired binary endpoints, or testing treatment-outcome independence in confirmatory or exploratory clinical trials.
The English summary is being prepared. Showing the original description.
Produces a narrow-interval quality signal for a WinDAGs skill that a third party can verify without inspecting model weights or method internals. The mechanism is attribution-kNN over a tamper-evident outcome log (task→skills→accept/reject store), combined with a conformal-prediction calibration certificate that provides a formal coverage guarantee. Thompson/Beta sampling is explicitly rejected as a category error: it produces a selection signal for stationary i.i.d. rewards, not an attestation signal for context-dependent LLM output quality. The resulting bundle — outcome-log Merkle root + conformal threshold + optional TEE guardrail signature — constitutes a "narrow-interval trust" credential: verifiable, bounded, and internals-opaque.
The English summary is being prepared. Showing the original description.
Design or audit an agent identity, credential, session, continuity, and reputation plan. Use when attributed outcomes must survive key rotation, restart, recovery, or review; when choosing Elo, TrueSkill, a contextual bandit, or an LLM judge; and when making Sybil, newcomer, calibration, collusion, and evidence limits explicit. Produces a supplied-plan consistency audit, never proof of observed delivery, cryptographic identity, or live enforcement. NOT for proving personhood, global Sybil resistance, or an unobserved delivery.
The English summary is being prepared. Showing the original description.
Coordinate repairs across multiple OpenClaw issues or pull requests, which propose code changes. Assign owners, prove defects, verify fixes, and track outcomes through merging or closing resolved items within the authorized scope.
Prepare REA changelogs and GitHub release notes from a fixed Git revision. Turn verified changes into clear user outcomes, preserve accurate contributor credit, and keep the release text aligned with Release Please, the automated release workflow.
Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.
Evaluate prediction markets as information sources for products, agents, dashboards, and business decisions. Record probabilities implied by market prices with sources and timestamps, assess signal quality, and compare other evidence to recommend suitable uses and explain limitations.
Write and review C# and .NET tests using xUnit examples. Covers unit tests, mocks that replace dependencies, API and database integration tests, reusable test data, and project organization to check behavior and outcomes.
Organize engineering work carried out by AI agents with clear completion criteria, small verifiable tasks, and evaluations before and after implementation. Match model choice to task complexity and track tokens, retries, time, and outcomes to manage cost.
Independently reviews deliverables handed over through Kanban, checks them against acceptance criteria and test evidence, and records an approval, actionable change request, or escalation when a human decision or external prerequisite is needed.
Turn a topic or script into a finished MP4 with MoneyPrinterTurbo. The skill handles installation, configuration, generation, and delivery, with support for voice-over, subtitles, background music, and recovery from fixable generation errors.
Build a narrowly scoped feature or integration using existing repository structures. Define observable acceptance criteria and non-goals, complete the working path across relevant layers, and stop when focused checks confirm the requested outcome.
Verify that existing work meets its acceptance conditions using the smallest sufficient set of checks. Reuse results that still match the repository state, report outcomes precisely, and stop once the evidence is complete without adding unrelated work.
Clarify an unclear request through one question at a time, with the agent sharing its best guess for each answer. Produce a user-confirmed statement covering the desired outcome, audience, timing, success criteria, constraints, and exclusions.
Read email linked to assigned Paperclip tasks, send new messages or replies through an assigned AgentMail inbox, and check delivery outcomes. Follow task permissions and preserve retry identifiers to avoid duplicate sends.
Review another agent’s recent work records to identify recurring problems and propose small changes to instructions, skills, or tool descriptions. Produce evidence-backed drafts and reviewable diffs, checking that proposed rules would preserve successful outcomes from past tasks.
Create acceptance criteria and a manual validation plan for feature changes. Cover successful flows, unusual inputs, failures, and performance limits, with observable outcomes and clear evidence requirements so reviewers can decide whether each criterion passes.
Turn product requirements, roadmaps, architecture reviews, and retrospectives into HTML slides for decision-making. Choose one of eight visual themes to create a consistent, horizontally navigable deck, using source evidence and real numbers to support review.
Create an HTML year-end self-review deck for a product manager, organizing responsibilities, results, lessons, and requests around supporting evidence. The template uses rounded cards and pastel colors to present the case to managers or review committees.