hoanganhduc/coding-system-rebuild - Page 2

cross-agent-delegation

Use when drafting, validating, or normalizing bounded cross-agent task/result packets for parent-controlled handoffs. This is a packet-contract skill, not a runtime delegation broker.

decision-doubt-loop

Use in-flight, the moment you are about to let a non-trivial decision stand — a branching or control-flow change, crossing a module/service/agent boundary, an assertion the type system or proof checker cannot see, a high-stakes or irreversible action, or an…

deep-research-workflow

Use when a research task benefits from an explicit phased workflow with structured source handoff across search, analysis, and writing, and when preserving citations across phases matters.

docling

Use when the user wants to parse, convert, chunk, or structurally analyze PDFs, DOCX, PPTX, HTML, images, audio transcripts, or similar documents with Docling. Prefer this skill for local document parsing before ad hoc text extraction.

get-available-resources

Use at the start of computationally intensive local tasks to detect CPU, memory, disk, and optional accelerator availability before planning execution.

hetzner-research-compute

Use when a research or engineering task needs automatic heavy-compute routing to a disposable Hetzner Cloud CPU or high-memory server through the local broker, with agent-driven provision, run, collect, and destroy under hard cost caps.

kaggle-research-compute

Use when a research or engineering task needs automatic heavy-compute routing to free Kaggle Kernels through the local broker, with agent-driven push, poll, fetch, and a multi-run resume loop across concurrent kernels; free CPU (quota-free) and GPU under a…

lean-research-library

Use when any Lean formalization task starts (reuse Mathlib and the personal research library before proving anything new) and when it ends (gate finished results into the library and flag mathlib-PR candidates, always asking the user first). Also scaffolds…

modal-research-compute

Use when a research or engineering task needs automatic heavy-compute routing through the unified local broker, including Modal-backed remote CPU, high-memory CPU, or GPU execution.

model-router

Use when choosing an appropriate model, reasoning level, and role for subagents or multi-agent research work.

opengauss

Use when preparing optional Math Inc. OpenGauss readiness for Lean prove/formalize workflows in the formal research lane. Inert doctor and config guidance only; never auto-installs or claims formal proof from Gauss success.

paper-review

Use for review-only requests for papers or books when the user did not explicitly ask for annotation. Handles the normal single-agent review flow.

remote-bridge

Cross-target remote control via Zulip (default control) and optional Telegram mobile notify, with mailbox approvals/instructions for autonomous research loops. Not for OpenClaw.

research-briefing

Use when starting a nontrivial research task to frame scope, success criteria, evidence plan, and the right downstream workflow before expensive browsing or multi-agent work begins.

research-report-reviewer

Use when a research draft or report exists and needs a pre-final review for unsupported claims, ambiguity, scope drift, or missing evidence before delivery.

research-verification-gate

Use immediately before calling a research answer done, final, or complete to verify evidence coverage, dates, remaining gaps, and delivery readiness.

self-improving-agent

Use when a task fails, a user corrects the assistant, a capability is missing, or a recurring better pattern should be logged and considered for canonical ai-agents-skills integration.

session-logs

Use when the user asks about earlier conversations, prior outputs, historical context, or past work that may live in Codex memories, Codex session logs, or optional legacy OpenClaw logs.

source-research

Use when the user wants research, source gathering, current-information lookups, cross-source synthesis, or extraction from URLs/PDFs/videos using web search, page inspection, local tools, and sub-agents.

url-to-screenshot-runtime

Runtime engine for url-to-screenshot. Use to detect a browser, capture and verify a URL-to-PNG result, browser-print and structurally inspect a PDF, or run the offline self-test of the deterministic core, without network, package installation, or live browser…

url-to-screenshot

Use when the user wants to capture a web page (an http or https URL) to a clean PNG screenshot, in viewport or full-page mode, with cookie-consent dismissal, timeouts, SSRF-safe URL admission, and blank-output verification, across Linux, macOS, and Windows.…

venue-ranking-evidence

Use when identifying a journal, conference, or proceedings series from a partial name, acronym, alias, ISSN, or source ID; preserving source-specific rank, quartile, metric, classification, membership, or coverage observations; or proving that the public…

paper-review

Single-agent paper review workflow.

permissioned-github

Guidelines for interacting with GitHub and request permissions from the user when commands fail due to restrictions in the agent environment.

url-to-screenshot-runtime

Runtime engine for url-to-screenshot: headless-browser CDP capture, SSRF-safe URL admission, consent dismissal, blank-output detection, and an offline self-test of the deterministic core.

url-to-screenshot

Capture a URL to a clean PNG screenshot with browser detection, cookie-consent dismissal, viewport or full-page modes, timeouts, SSRF-safe URL admission, and blank-output verification across Linux, macOS, and Windows.

vnu-eoffice

Route VNU eOffice requests to an existing vnu_eoffice package or CLI: monitor updates, list latest incoming/outgoing documents, search by keyword, download attachments, and send requested files through Telegram.

url-to-screenshot-runtime

Runtime engine for url-to-screenshot: headless-browser CDP capture, SSRF-safe URL admission, consent dismissal, blank-output detection, and an offline self-test of the deterministic core.

url-to-screenshot

Capture a URL to a clean PNG screenshot with browser detection, cookie-consent dismissal, viewport or full-page modes, timeouts, SSRF-safe URL admission, and blank-output verification across Linux, macOS, and Windows.

vnu-eoffice

Route VNU eOffice requests to an existing vnu_eoffice package or CLI: monitor updates, list latest incoming/outgoing documents, search by keyword, download attachments, and send requested files through Telegram.

url-to-screenshot-runtime

Runtime engine for url-to-screenshot: headless-browser CDP capture, SSRF-safe URL admission, consent dismissal, blank-output detection, and an offline self-test of the deterministic core.

url-to-screenshot

Capture a URL to a clean PNG screenshot with browser detection, cookie-consent dismissal, viewport or full-page modes, timeouts, SSRF-safe URL admission, and blank-output verification across Linux, macOS, and Windows.

vnu-eoffice

Route VNU eOffice requests to an existing vnu_eoffice package or CLI: monitor updates, list latest incoming/outgoing documents, search by keyword, download attachments, and send requested files through Telegram.

annotated-review

Use only when the user explicitly mentions both annotation and review for a paper task. Produces annotated review outputs and supports an explicit add-to-Zotero step when the user asks for it.

axiom-axle-mcp

Use when preparing optional AxiomMath AXLE MCP setup for manual formal-proof assistance.

calibre

Use when the user wants to search, retrieve, send, add, update, sync, export, convert, or clean books from the managed Calibre library runtime.

digest-bridge

Use when the user wants to extract arXiv IDs or DOIs from research or RSS digests and turn them into getscipapers requests or manifests.

draft-writing

Use when drafting, rewriting, polishing, or revising prose while preserving author intent by tracking claims, evidence, caveats, and revision deltas.

formal-skeleton-helper

Use when the user wants a minimal Lean-style theorem skeleton, namespace wrapper, or generated formal statement stub.

getscipapers-requester

Use for external DOI/ISBN/title resolution, manifest creation from pasted text, and paper retrieval after the local library-first workflow does not satisfy the request or the user explicitly opts out of library use.