Use when one Relayfile workspace must be mounted on several machines and an agent placed on a remote host inside the live tree without cloning. Covers joining an existing workspace with write opt-in, per-node mount scopes and credentials, fleet enrollment and placement, and byte-level proof that remote mirrors are current. Treats daemon liveness, lag/status lines, and fleet-node presence as non-proof.
Updates affected docs in the same task as code or workflow changes — README, API docs, CLI --help, config, wiki. Use when renaming endpoints, adding flags/config, or fixing stale references.
Thorough, user-invoked tech debt and architecture audit of the current codebase. Produces TECH_DEBT_AUDIT.md with file-cited findings, severity, effort estimates, and a required "looks bad but is actually fine" section. Use when the user asks for a debt audit, codebase health check, architecture review, or code quality assessment of an entire repo. Does not auto-invoke.
First step for the Q3-vs-Q2 hedge-fund 13F comparison. Inventories both /root/2025-q2 and /root/2025-q3 datasets, freezes a validated working set, and records the accession-number lookup method so later stages resolve funds without rescanning. Use this before running any AUM, holdings-count, holdings-delta, or top-holder analysis for answers.json.
Audit components for hardcoded tenant strings, non-semantic colors, or missing feature flags. Use before PR review or to check tenant isolation readiness.
Wenn es um AVV und AGB Schnittstelle in AGB-Recht-Prüfer geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten Schritt; liefert eine Schnittstellenkarte mit Kollisions-, Zuständigkeits- und Nachweisfragen. Auswahlstichwort: Avv Und Agb Schnittstelle; Arbeitsfeld: AGB-Recht-Prüfer.
Unified application security skill for Coding Agent systems like OpenCode. Use when reviewing or writing code that touches authentication, authorization, user input, payments, database access, secrets, deployment, dependencies, or AI/agent workflows. Includes OWASP Top 10 (2025), ASVS 5.0 highlights, agentic AI security, vibe-coded pitfalls, insecure defaults detection, supply chain risk signals, and CI/CD agent action hardening.
Implement or stub Neru functionality for a specific OS/backend: port contract, build-tagged file slots, factory wiring, CodeNotSupported stubs, capability matrix, contract tests, and the docs ownership table. Use for any change under internal/adapter/platform or any *_darwin/_linux/_windows file. Not for pure-Go domain logic.
Verify an implemented capability against its acceptance criteria and protect it with regression tests. For MPCORE_ORGANIZATION.MPCORE_COMPONENT backends generated from MP Core MPCORE_VERSION.
Search the web, retrieve page contents, get cited answers, and gather research or code context using the local Exa CLI. Use this skill whenever the user wants Exa-powered web research, semantic search, recent source discovery, domain-filtered search, similar-page discovery, URL content extraction, or web-grounded answers with citations. Common scenarios include finding current sources before summarizing a topic, searching with domain or date filters, pulling page text from known URLs, finding pages similar to a reference URL, and gathering compact web context for technical questions. Prefer this skill when the user explicitly mentions Exa or when Exa CLI is the intended search tool.
Audit and rewrite a LinkedIn profile end-to-end for 2026: headline, About 7-step, Featured, banner, photo, Experience metrics, Skills, custom URL, recommendations. Triggers on "review my profile", "rewrite my headline", "fix my About", "optimize banner", "profile audit", "LinkedIn bio". Converts resume-style profiles to ones that convert 3-5x better. Not for writing feed content (use linkedin-post-writer).
This project is a cheat engine or framework specifically designed for Unreal Engine 4 games. It provides UE4-aware memory scanning, GObject enumeration, UProperty traversal, and SDK generation capabil