В каталоге 183 730 навыков в 14 категориях.
Bind a check or action to the input snapshot it actually used. Use before relying on cached verification, consuming a re...
Use this skill when an audit, attestation period or customer review is coming and someone asks "is our evidence up to da...
Use when improving a Coworld player through one diagnosed failure and completed comparison evidence.
Grade the quality and strength of veterinary evidence using a veterinary-specific evidence hierarchy. Textbooks carry mo...
Grade the evidence behind a claim before betting on it — the hierarchy for business evidence (experiments usage data s...
Verifies completion claims with evidence before declaring done. Use before stating "done", "complete", "fixed", "shipped...
Use when any verdict, approval, or benchmark is pinned to a content hash — build the hash from an explicit manifest cove...
Estructura y estilo del template HTML para reportes de evidencia de ejecucion de test cases. Incluye header, tabla de pa...
Sanitize security evidence before sharing, reporting, or writing up findings. Use for bug bounty reports, guided MCP ass...
Evidence-capture and PoC-redaction discipline for bug-bounty submissions: cookie redaction protocol (which fields to mas...
Automatically audit evidence whenever a request depends on factual accuracy, current web information, research, comparis...
Validate claims against sources and score confidence; use when asked to verify research output accuracy.
Weights a pile of "validation" by what people DID, not what they said. Takes interview quotes, sign-ups, LOIs, pilots, p...
Record every material claim as a row in `00-control/evidence-ledger.md` carrying a source-authority level and a claim st...
Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch audito...
Use when you have tandem MS/MS spectra annotated by at least two of GNPS (FBMN), ISDB-LOTUS (CFM-ID 4.0 spectral matchin...
Write or rewrite a document in evidence-locked mode: no unsourced sentences — every substantive claim carries a footnote...
- When to Use
Evidence mode operational spec for the team lead. An extension of code mode that maintains a durable, observable evidenc...
Turn a folder of exports already on disk into an integrity-checked ISO 27001 or SOC 2 evidence pack, recording who colle...
Use when someone asks to build an evidence pack for this, document proof of this work, compile the evidence for this tas...
Resolve stale facts and authority conflicts.
Use this skill when an auditor, assessor or regulator has sent a request list and the team asks "turn the auditor's requ...
Build and validate a durable CLAIM ledger for documentary, historical, technical, educational, press-kit, festival, and...
进行时效性强的多来源研究，包含 primary-source retrieval、矛盾核查、证据分级、引用和省 Token 的综合分析。适用于开放式调查、due diligence、市场/政策研究，以及来源质量或新旧程度会改变结论的问题。仅...
Review a small code or documentation change and return only evidence-backed correctness findings. Use in the Codex How T...
Find and compare research evidence, trace claims to sources, and prepare useful literature briefs for interdisciplinary...
指定薬剤・適応・国・データベース特性に基づき、PubMed/Web検索で先行RWD研究・RCT・ガイドラインを調査し、 エビデンスランドスケープを要約する。JMDC/MDV等クレームDBとの差別化観点を必ず含める。
Generate snapshot evidence for video monitoring event candidates. Use when Codex has an event, event_id, evidence_frame_...
Evidence citation and domain scope standards for Neo4j subagents. Prevents hallucination and ensures audit trail.
Turn a pile of sources into a defensible claim. Use for "what does the literature actually say?", conflicting studies or...
Synthesize discovery, repository, social, and validation evidence into DecisionRecords and AcceptanceRecords, producing...
Create structured, evidence-backed synthesis documents from large crawled or collected information corpora. Use when Cod...
Evidence-tag grammar and tagging discipline for paper artifacts. Preloaded into every agent that writes, audits, verifie...
- Completing code implementation
Archived skill guidance for evidencias-eventos.
Evidently AI skill for data drift detection, model performance monitoring, target drift analysis, and automated reportin...
Use Evidently OSS (100+ evaluation metrics, declarative testing API) to detect data drift, target drift, and model-perfo...
Open interactive WinRM shells with evil-winrm using passwords, NT hashes, certificates or Kerberos tickets, and load scr...
This skill should be used when the user asks about "LTV", "loan-to-value", "collateral factor", "supply cap", "borrow ca...
This skill should be used when the user asks about "deposit", "withdraw", "mint", "redeem", "eToken", "shares", "assets"...
EdgeVLA - Open-source edge vision-language-action model for robotics. Standardizes Open-X Embodiment datasets for consis...
Read-only EVM client: wallets, tokens, gas across 8 chains.
Use this skill when the user asks to "check balance", "what's the balance of", "is this a contract or EOA", "get address...
Deep EVM bytecode analysis and decompilation capabilities for smart contract security, gas optimization, and reverse eng...
Use for targeted EVM chain, account, transaction, RPC, explorer, bridge, and DEX evidence: chain name/ID, native symbol,...
Use this skill when the user asks "block info", "what's in block", "latest block", "get block details", or mentions view...
This skill should be used when the user asks to resolve an EVM chain name or chain ID, find chain metadata such as a def...
Use this skill when the user asks to "get contract source code", "show verified contract", "fetch source from etherscan"...
Expert in Ethereum Virtual Machine internals - gas optimization, assembly/Yul, opcode-level optimization, and low-level...
Use this skill when the user asks "gas price", "how much is gas", "current gas", "check gas fees", or mentions checking...
Use this skill when the user asks for "transaction details", "show me tx", "what happened in this transaction", "look up...
Run the evm-wallet Docker e2e tests (build, start stack, wait for healthy, test, diagnose failures).
Routes evo trajectory-evaluation workflows for APE/RPE, trajectory I/O, result analysis, configuration, and programmatic...
Complete pipeline for binary STL parsing, connected component extraction, volume computation, material density lookup, a...
Builds and solves AC Optimal Power Flow using Pyomo+IPOPT with polar coordinate formulation.
Push the LLM to reconsider refine and improve its recent output. Use when the user asks for advanced elicitation.
analyst agent
architect agent
Creates Atheris-based coverage-guided fuzz drivers for Python libraries using FuzzedDataProvider for structured input ge...
Parses BibTeX files using bibtexparser 1.4.2 and cleans LaTeX/BibTeX artifacts from fields like title, author, year, DOI...
Set the active feature context for artifact organization. Creates subfolders in planning-artifacts and implementation-ar...
Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user...
Analyzes a Python repository to identify the root causes of build failures, including syntax errors, import errors, test...
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".
Compares parsed BibTeX citation metadata against API results using fuzzy string matching and multi-factor scoring to cla...
Queries external academic APIs (CrossRef, Semantic Scholar, DBLP, doi.org) to verify whether a citation exists. Implemen...
Encodes all Civ6 Gathering Storm district adjacency bonus rules, placement validity, population limits, and civ-specific...
Parses .Civ6Map SQLite database files to extract map dimensions, terrain, features, resources, and river edge data. Prov...
Utility functions for cleaning raw clinical lab CSV data - handling decimal comma formats, scientific notation normaliza...
Assign human-readable, non-overlapping representative names to clusters using TF-IDF and centroid proximity.
Perform adversarial code review finding specific issues. Use when the user says "run code review" or "review this code"
Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change"
Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture...
Break requirements into epics and user stories. Use when the user says "create the epics and stories list"
Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a n...
Create product brief through collaborative discovery. Use when the user says "lets create a product brief" or "help me c...
Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "c...
Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications"...
Generates the complete visualization.js file implementing a D3.js v6 force-simulation bubble chart with sector clusterin...
Compares two pandas DataFrames (old vs new) by a key column to identify deleted rows and modified fields, then exports r...
Solves DC-OPF with spinning reserve co-optimization using PuLP/CBC. Extracts LMPs from dual variables, reserve MCP, bind...
dev agent
Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story f...
Generates Graphviz DOT visualization files from parsed dialogue graph structures using the graphviz 0.20.3 Python API.
Serializes dialogue graph to JSON file and generates Graphviz DOT visualization. Handles UTF-8 encoding, DOT node stylin...
Parses dialogue script text into intermediate section structures using regex, then builds a validated JSON graph schema...
Document brownfield projects for AI context. Use when the user says "document this project" or "generate project docs"
Extracts text from PDF, DOCX, and PPTX files using PyPDF2, pdfplumber, pdftotext CLI, and stdlib zipfile+XML fallbacks.
A utility module for filling Word document templates (.docx) with data from JSON files. Handles split-run-aware text rep...
Conduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]"
Patches Apache Druid 0.20.0 for CVE-2021-25646 - a JavaScript injection vulnerability where empty-string keys in JSON pa...
Muxes normalized TTS audio segments into the original video at precise time offsets using FFmpeg, and generates the JSON...
Edit an existing PRD. Use when the user says "edit this PRD".
Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the pros...
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user r...
Identifies and patches CVE-2025-32433 in Erlang/OTP SSH server source code by inserting an authentication-state check in...