recallnet

Same-session deep-verification methodology. Chain-of-Verification with Saboteur / New Hire / Security Auditor personas. For gate-level cross-model verification that writes the prosecution doc, use /verify — which uses this skill's methodology as its payload.

End-to-end orchestrator for building a trading executor from data collection through live deployment. Use when the user asks to build an executor, create a new strategy, implement a trading system, or says 'build me an executor for X'. Also use when resuming an in-progress executor build — the skill reads the executor directory to determine current stage and picks up where it left off. Covers the full lifecycle: data collection, scoring, strategy promotion, and live deployment. Cross-model `/verify` is the single gate at PROMOTE and LIVE. This skill should be used for ANY new executor work in this repo, even partial tasks like 'add scoring to my executor' or 'wire up live mode'.

Launch Anthropic Claude as an independent agent for code review, verification, and reasoning. Uses the claude CLI with full file system access, or the API for pure reasoning tasks. Primarily for teams whose primary agent is Codex or Gemini and want a Claude read on the work.

Set up or repair codecontext adoption in a project. Use this whenever the user wants to add @context annotations to a repo, install the codecontext toolchain, update AGENTS.md guidance, improve agent workflows around decision capture, or audit whether an existing codecontext setup is coherent. Prefer this skill over vague "document the tool" work: it is specifically for making a repo actually usable with codecontext.

Launch OpenAI Codex/GPT as an independent agent for code review, verification, and precision analysis. Uses the codex CLI with full file system access, or the API for pure reasoning tasks.

Create and maintain executor strategy overview presentations. Use when scaffolding a new executor, updating strategy documentation, or when the QA check requires a strategy-overview.marp.md file. Generates Marp slide decks with codePaths tracking for CI enforcement.

Launch Gemini as an independent agent for codebase analysis, planning, and large-context synthesis. Uses the gemini CLI with full file system access.

Plan and file goals and feature issues through conversation. Use when the user wants to create goals, plan features, file issues, or discuss what to build next.

Set up or repair codecontext adoption in a project. Use this whenever the user wants to add @context annotations to a repo, install the codecontext toolchain, update AGENTS.md guidance, improve agent workflows around decision capture, or audit whether an existing codecontext setup is coherent. Prefer this skill over vague "document the tool" work: it is specifically for making a repo actually usable with codecontext.

Check which @context annotations are affected by recent code changes. Use after editing code to verify context accuracy and flag stale annotations.

Surface @context annotations before editing a file. Shows critical constraints, tradeoffs, and risks sorted by priority. Use when about to modify unfamiliar or complex code, or when the user asks what constraints apply to a file.

Check all staged files for stale @context annotations before committing. Use as a pre-commit verification step.

Work in a dedicated Git worktree, make all commits there, and land changes through `mq` instead of merging directly into `main`. Use after onboarding, once the user already understands the repo's setup and wants the contribution workflow.

First skill for new contributors, fresh clones, and setup questions in the mainline repo. Separates developing mainline from using mq on another repo, verifies the local baseline, explains canonical-root trust, and clarifies which commands should or should not work in this source checkout.

Scaffold a self-improving agent harness for the current project. Scans the codebase to understand what it does, proposes domain-specific pipeline stages with quality gates, and generates files that mechanically prevent repeated failures.

Execute the agent pipeline defined in .harness/pipeline.md. Runs stages sequentially, enforces quality gates mechanically, and asks the user for approval at human gates directly in the conversation.

Install Recall's docs governance stack into a repo. Use this whenever a team repo needs astrochicken-style docs governance, remark-based frontmatter/link validation, freshness checks, orphan detection, docs policy bootstrapping, or a fast one-command setup instead of copied scripts.

Plan and file goals and feature issues through conversation. Use when the user wants to create goals, plan features, file issues, or discuss what to build next.

Query live reward and incentive data from Polymarket, Limitless, and Kalshi prediction markets. Use when building agents that farm LP rewards, track maker rebates, discover sponsored reward opportunities, compare platform incentives, or analyze market-making earnings across prediction markets.

Set up and manage Frictionless Data Package repos created from the recallnet source-data-package-template. Use this skill whenever the user is working in a repo created from the source-data-package-template, mentions adding source data, creating a data package, setting up a new data ingestion repo, registering data resources, or working with datapackage.json. Also use it when the user asks about LFS setup for data repos, date-folder conventions, or Frictionless Data Package structure in the context of recallnet repos.

Query live reward data from Polymarket, Limitless, and Kalshi prediction markets. Covers sponsored rewards, LP rewards, maker rebates, points systems, and incentive programs. Use when building reward-tracking bots, analyzing prediction market incentives, comparing platforms, or when the user asks about market maker earnings, LP yields, or reward distributions.