170 skills · sorted by relevance
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.
The English summary is being prepared. Showing the original description.
Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code reasoning, or tasks needing deep project context.
The English summary is being prepared. Showing the original description.
60-second SEO snapshot powered by the DataForSEO API. Three parallel calls (DataForSEO Labs domain overview, Backlinks summary, ranked keywords) for core metrics on any domain — total keywords, traffic estimate, backlinks, top rankings — without waiting for a full audit.
The English summary is being prepared. Showing the original description.
Next.js App Router routing primitives: file-based routes, dynamic and catch-all segments, route groups, parallel routes, intercepting routes, middleware, programmatic navigation, link patterns. Use this skill to: - Pick the correct dynamic segment syntax for the route shape. - Use route groups to organize without affecting URLs. - Implement parallel/intercepting routes for modal-style navigation. - Build effective middleware for auth, redirects, A/B tests. - Use Link and useRouter correctly. Do NOT use this skill for: - Data fetching per route (see nextjs-data-fetching). - General file conventions (see nextjs-conventions). - RSC vs Client (see server-component-patterns).
The English summary is being prepared. Showing the original description.
Pythonic wrapper around RDKit with a simplified interface and sensible defaults. Preferred for standard drug discovery work — SMILES/SELFIES/InChI conversion, molecule standardization and sanitization, descriptors, ECFP and other fingerprints, Tanimoto distance matrices, Butina clustering and diverse subset picking, Bemis-Murcko scaffolds and scaffold splits, BRICS/RECAP fragmentation, 3D conformer generation, SDF/CSV/Excel and cloud I/O, and parallel processing via n_jobs. Returns native rdkit.Chem.Mol objects, so it composes with RDKit throughout. Also trigger on datamol, `import datamol as dm`, dm.to_mol, dm.standardize_mol, dm.cluster_mols, or dm.pick_diverse. For advanced control or custom parameters, use the rdkit skill directly.
The English summary is being prepared. Showing the original description.
Enhance an existing marketing plan with parallel research. Use when the agent has a draft plan (brand strategy, campaign brief, content calendar, launch plan) that needs strengthening with real data. Triggers on 'deepen this plan', 'strengthen this strategy', 'research gaps in my plan', 'make this plan better', 'this plan is too surface level', 'add research to this', 'validate this plan', 'back this up with data', or when a plan exists but lacks audience data, competitive positioning, or keyword strategy. Make sure to use this whenever someone has an EXISTING plan that feels thin or unresearched — even if they just say 'is this plan good enough?' or 'what's missing here?', they likely need deepening. This skill ENHANCES existing plans — it does not create new ones. If no plan exists, route to /brainstorm or /launch-strategy first.
The English summary is being prepared. Showing the original description.
Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.
The English summary is being prepared. Showing the original description.
Playwright-first strategy for shared DB + shared test accounts. Use when E2E tests collide in QA/staging, need safe parallelism, or require deterministic cleanup without touching baseline data. Covers per-test ownership, namespacing, ID-based teardown, serial shared-state suites, and optional stale-data janitor jobs.
The English summary is being prepared. Showing the original description.
Orientação especializada para treinamento com Fully Sharded Data Parallel do PyTorch (FSDP) - sharding de parâmetros, precisão mista, CPU offloading, FSDP2
The English summary is being prepared. Showing the original description.
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
The English summary is being prepared. Showing the original description.
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
The English summary is being prepared. Showing the original description.
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
The English summary is being prepared. Showing the original description.
Build Python workloads on Modal for cloud execution, including GPU model training and inference, web APIs, scheduled jobs, and parallel batch processing. Configure container environments, persistent storage, and automatic scaling through the Modal SDK.
Optimize scientific Python workloads for NVIDIA GPUs by choosing suitable libraries and reducing bottlenecks. Compare outputs with the CPU version and measure complete processing time, including data transfers, to determine whether the GPU implementation provides a useful improvement.
Plan and write literature reviews using multiple scholarly databases. Document searches, screen papers, synthesize findings, and check citations, then prepare Markdown or PDF reports with transparent selection counts, evidence limitations, and reproducible search records.
Follow practical agent-browser workflows to inspect pages, click elements, fill forms, extract information, and take screenshots. The guide also covers waiting for page changes, saving login state, and keeping separate browser sessions for different tasks.
Research private companies through six perspectives, including business, finances, competition, and technology. Cross-check evidence, separate facts from inferences, and produce a valuation range, possible exit routes, and a map of missing information.
Coordinates specialist agents in Claude Code to work from product requirements through design, implementation, testing, deployment, and operations. Includes task queues, saved progress, parallel reviews, and recovery workflows for managing extended development work.
Coordinate four AI researchers to examine a company's business, finances, competition, and management risks in parallel. Combine sourced findings into an investment report with valuation checks, arguments for and against investing, and suggested price ranges.
Audit a website for visibility in AI search, including how easily its content can be quoted, technical access, content quality, and structured data. Receive a weighted score out of 100 and a prioritized improvement plan.
Assess API business workflows for flaws that automated scanners can miss. The skill examines skipped steps, simultaneous transactions, authentication tokens, GraphQL, and webhooks, helping testers document weaknesses and their financial or operational impact during authorized assessments.
Improve CircleCI build and test pipelines by identifying slow or unreliable jobs, then adjusting caching, data sharing between jobs, triggers, and parallel execution. Receive incremental configuration changes with expected effects, validation criteria, and rollback guidance.
Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER + ivreg + did + bacondecomp + HonestDiD + eventstudyr + rdrobust + rddensity + Synth + gsynth + synthdid + MatchIt + WeightIt + cobalt + ebal + grf + DoubleML + mediation + marginaleffects + modelsummary + kableExtra + gt + ggplot2 + ggpubr + cowplot + binsreg. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step R pipeline an applied economist runs on every paper — (1) data import & cleaning (read_dta/read_csv, naniar, janitor, validate-merges), (2) variable construction (mutate/across/winsorize/group_by + lag/lead with dplyr), (3) descriptive statistics & Table 1 (gtsummary, modelsummary::datasummary, tableone), (4) classical diagnostic tests (shapiro/jarque.bera.test/bptest/dwtest/bgtest/vif/adf.test/kpss.test/Hausman), (5) baseline modeling (fixest::feols, ivreg, did::att_gt, eventstudyr, sun_ab, did_imputation, synthdid, rdrobust, MatchIt, WeightIt, grf::causal_forest, DoubleML, mediation), (6) robustness battery (modelsummary stack, clubSandwich CRSE, fwildclusterboot, ri2, robomit Oster, bacondecomp, HonestDiD), (7) further analysis (interactions + marginaleffects, mediation::mediate, gsem via lavaan, dose-response splines, grf CATE), (8) publication-ready tables & figures (modelsummary, kableExtra, gt, stargazer, texreg, flextable to LaTeX/Word/HTML; ggplot2 + ggpubr + cowplot + binsreg + iplot for figures). **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation, IPTW + g-formula + TMLE doubly-robust triplet via `WeightIt` / `gfoRmula` / `tmle` / `ltmle`, Mendelian randomization via `MendelianRandomization` / `TwoSampleMR` / `MRPRESSO`, KM / Cox / AFT / RMST survival via `survival` / `survminer` / `flexsurv`, E-value sensitivity via `EValue`, principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `DoubleML`, S/T/X/R/DR meta-learners via `causalweight` / `grf`, causal forest via `grf::causal_forest`, BART/BCF via `bartCause` / `bcf`, matrix completion via `MCPanel`, CATE distribution + policy tree via `policytree`, off-policy evaluation, conformal causal via `conformalInference` / `cfcausal`, fairness audit via `fairmodels`, DAG learning via `pcalg` / `bnlearn` / LLM-assisted). Use when the user asks for a complete R empirical analysis, wants a tidyverse-style reproducible R script / Quarto workflow, prefers fixest over reghdfe, needs the R counterpart to StatsPAI / 00.1 / 00.2, or names a specific R step in isolation ("feols with cluster", "MatchIt nearest neighbor", "bacondecomp in R", "gtsummary table 1", "modelsummary to Word"). Mode A triggers on "target trial emulation R", "tmle ltmle", "MendelianRandomization", "TwoSampleMR", "MRPRESSO", "survival cox AFT", "STROBE R", "EValue R", "公共健康 R", "流行病学 R". Mode B triggers on "DoubleML R", "grf causal forest", "policytree", "bartCause bcf", "conformal causal R", "fairmodels", "pcalg NOTEARS", "因果机器学习 R".
The English summary is being prepared. Showing the original description.
Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to parallel agents with per-task model selection. Use when capturing chat to Notion, running the To-Do queue, suggesting, approving, or discussing tasks, or coordinating multi-task batches. Trigger with "/agency-os" subcommands or natural-language variants ("add a suggestion: …", "let's discuss X", "run the queue").
The English summary is being prepared. Showing the original description.