Business & Operations

Bulk-refresh research entries in ./research/ using parallel research-curator agents. Use when /refresh-research is invoked, stale research needs updating, or bulk re-verification of research entries is requested. Inventories entries by review date and age, runs RT-ICA pre-flight, spawns agents in waves of 5, updates README and Freshness Tracking, lints and commits. Supports --all, --stale, --category, --layer, and --dry-run flags.

Transforms validated /linear-walkthrough artifacts into one presentation-ready deck outline per major codebase component. Use when the user asks to create a presentation, prepare a walkthrough deck, build an onboarding deck, produce an architecture review deck, or summarize a codebase for a technical audience. Requires walkthrough directory output -- reads unified walkthrough, per-section files, validation reports, coverage maps, entry points, and open questions -- then orchestrates four para...

Produces a structured, end-to-end linear walkthrough of an unfamiliar codebase by orchestrating parallel subagents across four phases — discovery, tracing, validation, and synthesis. Use when onboarding to a new repository, understanding execution paths from entry points, generating navigable codebase documentation, or needing fact-checked coverage of architecture, deployment, testing, and operations.

Install and configure the GitHub CLI (gh) for AI agent environments where gh may not be pre-installed and git remotes use local proxies instead of github.com. Use when gh command not found, shutil.which returns None, need GitHub API access for issues or PRs or releases or workflow runs, or repository operations fail with 'failed to determine base repo' error. Provides auto-install script with SHA256 verification, GITHUB_TOKEN auth with anonymous fallback, and the required -R flag pattern for ...

Generic update orchestrator for an already-deployed warp route. Reads a Linear ticket describing any combination of warp-fee changes / ISM changes / hook changes / owner-address changes / additional-collateral-chain additions, edits the registry deploy.yaml accordingly, builds a per-chain strategy file from the artifact-context owner classifications, runs `hyperlane warp apply`, fork-simulates the resulting receipts via `/warp-route-check`, and hands off to `/warp-update-propose` to land the ...

A skill that allows a user to validate that a warp route deployment will be in the expected state after applying some configuration

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Assess whether an existing repo is ready for Codex-heavy development. Use before large harness work, when a user asks for an audit, roadmap, maturity score, or wants to know which Pax Fullstack Harness skills to apply first.

Monitor system resources: CPU, memory, disk, network, processes

Send messages to Slack channels via webhook or API

AWS S3 operations: list buckets, list/get/put/delete objects, head object, generate presigned URLs. Supports access key/secret or IAM role.

Redis operations: string, hash, list, set, zset, info, dbsize, ping. Supports password auth and multiple databases.

Preview and manage Pulumi infrastructure as code stacks

Analyze Nginx configuration and check for issues

Query NFT token information, ownership, metadata, and collection stats

Network diagnostic tools: ping, traceroute, netstat, ss

Query Kafka topics, consumer groups, and cluster info

Inspect Istio service mesh resources and configurations

Git operations for repository inspection and management (read-only by default)

Query Ethereum blockchain data including blocks, transactions, addresses, and gas prices

DNS query and resolution tools: A, AAAA, MX, TXT, NS, CNAME records

自我反思 + 自我批评 + 自我学习 + 自组织记忆。Agent 评估自身工作，发现错误并永久改进。

投资分析, 生成一份深度投资分析报告。不做传统投资分析——核心判断是项目是否是一台「秩序创造机器」。Use when user says '投资报告', '投资分析', '分析这个项目', '写投资报告', 'investment report', 'invest analysis', or provides entrepreneur conversation records wanting investment evaluation. Also trigger when user pastes or references meeting notes, pitch decks, or founder interviews and asks for analysis.

Validate built features through conversational UAT