Explore

Evaluate and prioritize research questions by importance, novelty, tractability, evidence, resources, ethics, and falsifiability.

Search, screen, synthesize, and cite scholarly literature and author metadata.

Turn an operational process into a clear SOP, role model, control map, and improvement backlog.

Retrieve official statistics from public international organizations and economic-data providers.

Inspect and atomically edit existing DOCX, XLSX, and PPTX files with hash-protected structured operations.

Generate a short Kun video from text or an authorized first-frame image.

Structure legal-risk reviews by issue, rule source, likelihood, impact, evidence, uncertainty, controls, and escalation.

Route requests to the narrowest real Kun tool family and define the required verification boundary.

Connect a task to MCP tools, workflows, resources, files, or visual outputs through explicit validated interfaces.

Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.

Revise Chinese text to sound specific, fluent, restrained, and human while preserving facts and author intent.

Design and generate accurate statistical visualizations with readable scales, labels, annotations, and source context.

Produce a dated, source-linked daily brief with prioritized developments, implications, and watch items.

Research, outline, draft, cite, and revise evidence-based articles, briefs, and reports.

Apply a coherent visual system, responsive behavior, interaction states, and accessibility to Kun components.

Create and publish one focused interactive UI component or choose a governed Kun visualization.

Render governed Kun charts and tables from structured data for trustworthy comparison and lookup.

Create and edit Kun Design screens, editable shapes, diagrams, design systems, layouts, and motion.

Open, inspect, navigate, and interact with public web pages using Kun's bounded structured browser.

Create, inspect, update, delete, and run Kun scheduled tasks or saved workflows.

恋爱军师与情绪支持 skill。用于心动、暧昧、追求、聊天记录或截图分析、约会、关系确认、多人选择、冲突、冷淡、投入失衡、分手、复合、出轨、婚姻或家庭问题；也用于分析关系信号、设计主动推进或退出策略、润色可直接发送的话术，以及把冷读、自然流、Blueprint、Mystery 等经典社交体系转译成真实、互惠、可退出的沟通能力。支持分析ChatLab已有数据和经同意可撤销的长期关系档案，不负责导出聊天软件数据。首次使用时为用户及一个或多个目标对象建立包含 MBTI、主观综合评分和关系背景的档案。

Use find_capabilities to discover the right Agenta tools for an agent you are building, report what each integration needs to connect, and wire the tools into the new agent's config. Use when a setup/builder agent must turn a plain-language task ("post to Slack and open GitHub issues") into attached, connected, ready-to-run tools.

Research a prospective company and prepare a short, source-backed fit assessment.

Use when searching the web for job openings, comparing job-board search strategies, validating listings, and extracting job details with Tavily.

How to give the person a small interactive page in the drive: a board, checklist, queue, form, table or dashboard. Read it when the ask is for something to look at and touch rather than a reply. Covers picking a starter with create_app, the app folder layout, and the window.agenta bridge for hand-written apps.

Write PR titles and descriptions the way a staff engineer would. Use when drafting or editing a pull request title and body, before running `gh pr create`, or any time the user asks for a PR description, summary, or release-notes-style writeup of a change. Apply this skill from the start, not as a cleanup pass after a generic first draft.

Write and file Linear issues (bugs and feature requests) the Agenta way. Use when the user asks to create, file, or draft a Linear or GitHub issue, write a bug report or feature request, or turn a problem into a tracked issue. Covers the title format, reproduction-first structure, when to use a todo list, and the team/project/label/priority/state conventions, plus filing it through the Linear MCP so the linked GitHub issue is auto-created and the PR links back.

Audit and update the supported LLM model list in assets.py against litellm's registry (models.litellm.ai). Use when adding new models, pruning outdated ones, or verifying the list is correct.

Update the API reference documentation by downloading the latest OpenAPI spec from production and regenerating the Docusaurus API docs

Run or inspect the relevant validation paths and turn failures, regressions, or missing coverage into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.

Refresh Agenta's harness catalogs, provider model lists, recommended defaults, and provider-supplied display names. Use for new OpenAI, Anthropic, Codex, Pi, or OpenRouter models and before releases that need current model choices.

Sync the findings record against local review artifacts and optionally a GitHub PR. Accept optional `path` and GitHub PR `url`; when `url` is provided, sync against both remote PR state and local state, otherwise default to local-only sync. Default to `path=infer`. Confirm effective variables before starting.

Perform a fresh-context scan of code and docs that turns verification observations and missing-test gaps into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.

Resolve findings by implementing the chosen fix path in code, tests, or docs. Accept optional `path` and a `priority` selector; by default resolve only the next highest remaining priority bucket, in order `P0`, `P1`, `P2`, `P3`. Also accept explicit levels or `all`. Default to `path=infer`. Confirm effective variables before starting.

Create a plan for a feature, and the files required to continue working on it. Use when the user asks for research for a feature or a plan to run it.

How the Agenta mobile app (web/mobile) installs and extends shadcn/ui registry components, themes them via the palette token bridge, and builds chat UI on @agenta/chat. Use when adding UI components under web/mobile, changing theme colors, editing components.json or globals.css, or building chat UI.

Motion design rules for the Agenta mobile app (web/mobile) — the shared presets in src/lib/motion, when to animate, and reduced-motion requirements. Use when adding any animation or transition under web/mobile, animating navigation, sheets, skeletons, or list/chat surfaces.

Feature-folder layout, states/ convention, and data-flow rules for the Agenta mobile app (web/mobile). Use when creating or moving files under web/mobile, deciding where a component lives, adding a new feature or screen, or wiring data into mobile components.

Hard-won GitButler mechanics for multi-lane work in this repo — committing to a specific lane in a stack, spreading a pile of edits back across an existing stack, ordering a stack and setting PR bases, and recovering from a scrambled workspace. Use when working with stacked branches, when `but rub`/`but absorb`/`but commit --only` mis-routes a change, when a stack collapses or a commit lands on the wrong lane, or when a hunk gets dropped. Not needed for ordinary single-lane work.

Where to put frontend code (package vs the web/mobile app layer) and how to use the @agenta/* packages. Use when authoring or moving code in web/packages, choosing which @agenta/* package owns something (ui, entities, entity-ui, shared, chat, sessions, playground, the *-ui domain packages, ...), using molecules, the loadable bridge, the EntityPicker, or writing package unit tests.

Helps add announcement cards to the sidebar banner system. Use when adding changelog entries, feature announcements, updates, or promotional banners to the Agenta sidebar. Handles both simple changelog entries and complex custom banners.

Domain routing and boundary guidance for authorized XXE testing, including file read, SSRF, blind XXE, and parameter entity variants. Use when a task belongs to the XXE domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized cross-site scripting testing, including reflected, stored, DOM-based, mXSS, and CSP bypass variants. Use when a task belongs to the XSS domain and needs scope, evidence, pivot, or exit criteria.

Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.

Domain routing and boundary guidance for authorized subdomain takeover testing, including dangling CNAME records, NS takeover, and cloud service takeover paths such as S3, Azure, and Heroku. Use when a task belongs to the subdomain takeover domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized server-side template injection testing, including Jinja2, Twig, Freemarker, Velocity, and Thymeleaf engines. Use when a task belongs to the SSTI domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized SSRF testing, including basic SSRF, blind SSRF, protocol smuggling, and cloud metadata access paths. Use when a task belongs to the SSRF domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized SQL injection testing, including union-based, blind, error-based, stacked query, and second-order SQL injection variants. Use when a task belongs to the SQL injection domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized reverse engineering analysis, including decompilation, debugging, protocol reversing, firmware extraction, and deobfuscation. Use when a task belongs to the reverse engineering domain and needs scope, evidence, pivot, or exit criteria.

Recon intake skill for first contact with a bare domain, URL, or IP address. Use to build an initial recon_profile and provide factual inputs for CVE lookup and attack-path routing.

Domain routing and boundary guidance for authorized reconnaissance and information gathering, including subdomain enumeration, port scanning, directory discovery, fingerprinting, and OSINT. Use when a task belongs to the recon domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized post-exploitation testing after initial access, including privilege escalation, persistence, lateral movement, data collection, and cleanup considerations. Use when a task belongs to the post-exploitation domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized payload construction and weaponization analysis, including shellcode, file format payloads, phishing payloads, and staged or stageless payload choices. Use when a task belongs to the payload construction domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized open redirect testing, including parameter redirects, meta or JavaScript redirects, and OAuth redirect_uri abuse. Use when a task belongs to the open redirect domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized network-layer security testing, including exposed services, protocol downgrade, man-in-the-middle risks, and segmentation bypasses. Use when a task belongs to the network testing domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized mobile application security testing, including insecure storage, certificate pinning bypass, exposed components, and binary reverse engineering. Use when a task belongs to the mobile testing domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized business logic vulnerability testing, including race conditions, flow bypass, price tampering, permission logic errors, and bulk operation abuse. Use when a task belongs to the logic testing domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized general injection testing outside SQL injection, including NoSQL, LDAP, XPath, and expression language injection. Use when a task belongs to the general injection domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized file operation vulnerability testing, including path traversal, arbitrary file read/write/upload, and LFI/RFI. Use when a task belongs to the file vulnerability domain and needs scope, evidence, pivot, or exit criteria.

Domain routing and boundary guidance for authorized defense evasion and bypass testing, including WAF bypass, AV/EDR evasion, logging considerations, and traffic obfuscation. Use when a task belongs to the evasion domain and needs scope, evidence, pivot, or exit criteria.