3,835 件 ・ 関連度順
概要と使いどころ
Investigate consistently failing SGLang CI tests by extracting the failure signature from scheduled or rerun workflows, bisecting the passing/failing commit window, checking runner or hardware specificity, and optionally reproducing on a remote GPU host.
日本語の概要は準備中です。原文の説明を表示しています。
Start and persistently pursue a goal to babysit an SGLang pull request until selected GitHub Actions workflows pass on the latest PR head. Use when asked to monitor, babysit, retry, or fix PR CI for lint.yml, pr-test.yml, pr-test-extra.yml, AMD, or other named workflows; classify failures as PR-related versus flaky or infrastructural, auto-fix and push only small clean fixes, rerun failed jobs only up to 10 times, and ignore unselected workflows.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill whenever the user needs ANY mailbox/email operation — checking, reading, searching, sending, replying, forwarding, organizing or deleting email, managing threads, connecting a personal mailbox, or registering a new mailbox. This skill is the single entry point for email tasks and orchestrates qwenpawmail-mcp for nine supported personal-mail domains.
日本語の概要は準備中です。原文の説明を表示しています。
Strategy Development Manager: convert academic papers and research reports into validated factors and strategies with automated backtesting, persistent storage, and decay monitoring.
日本語の概要は準備中です。原文の説明を表示しています。
Supply-chain bottleneck arbitrage. Given a super-trend (AI infra, energy transition, defense, semiconductor reshoring, space economy), decompose its physical supply chain down to Layer 2/3 choke points (optics, lasers, InP/SOI substrates, IC substrates, probe cards, specialty fiberglass...) and surface under-the-radar listed companies sitting on each bottleneck. Scores each link on 6 scarcity criteria, applies mandatory valuation gates (PS/PE/safety-margin) via the financial_rigor tool, and Munger-style reverse-validates. Outputs a ranked bottleneck opportunity board. Use when the user wants hidden beneficiaries of a structural trend rather than already-priced leaders.
日本語の概要は準備中です。原文の説明を表示しています。
Write a publication-grade 8-part deep-dive series on a single company (~120k words total): cognitive reset / moat / profit engine / hidden assets / era variable (e.g. AI) / financials Buffett-style / management / valuation+redlines. The core IP is NOT writing but REVISING — a strict fact-check checklist catches pseudo-precision (probability-weighted expectations, third-party MAU discrepancies, linear extrapolation), absolute language, and cross-article number inconsistencies that most finance long-forms violate. Each piece stands alone but shares one valuation/management/price framework. Use when the user wants textbook-level depth on one company for public publishing (a single research report or earnings note is NOT this — use investment-research / earnings-review instead).
日本語の概要は準備中です。原文の説明を表示しています。
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making documentation token-efficient for LLM input; or rewriting text in compressed notation.
日本語の概要は準備中です。原文の説明を表示しています。
Detect command injection against Modbus TCP/RTU in ICS/SCADA environments by monitoring unauthorized writes, anomalous function codes, malformed frames, and deviations from communication baselines using ICS-aware IDS and deep packet inspection. Use when deploying IDS for Modbus OT networks, investigating unauthorized PLC register/coil changes, or responding to FrostyGoop-style Modbus attacks.
日本語の概要は準備中です。原文の説明を表示しています。
Detect anomalies in Modbus/TCP and Modbus RTU industrial traffic via function code monitoring, register range validation, timing analysis, and deep packet inspection, using Zeek's Modbus analyzer, Suricata IDS with OT rules, and Python Markov chain models of normal transaction sequences. Use for deploying Modbus IDS in OT environments, baselining polling patterns, investigating suspicious Modbus traffic, or building function code allowlists.
日本語の概要は準備中です。原文の説明を表示しています。
Detect UEFI Secure Boot bypasses and bootkits such as BlackLotus and Bootkitty by verifying Secure Boot state, checking dbx revocation currency, and hashing EFI boot binaries against known-bad sets using mokutil, efi-readvar/dbxtool, CHIPSEC, sbverify/pesign, and Windows Confirm-SecureBootUEFI. Use when auditing fleet dbx rollout after a bootkit advisory or hunting for pre-OS persistence on a suspected-compromised endpoint.
日本語の概要は準備中です。原文の説明を表示しています。
Detect compromised O365 and Google Workspace email accounts by analyzing Unified Audit Logs and Azure AD sign-in logs for impossible travel, inbox rule creation/deletion (Set-InboxRule, New-InboxRule), external mail forwarding rules, and unusual Microsoft Graph API access or OAuth token use. Use when investigating suspected business email compromise (BEC), account takeover, or mailbox persistence via malicious inbox rules.
日本語の概要は準備中です。原文の説明を表示しています。
Detects and analyzes fileless malware that operates entirely in memory using PowerShell, WMI, .NET reflection, registry-resident payloads, and living-off-the-land binaries (LOLBins) without writing traditional executable files to disk. Use for requests involving fileless threat detection, in-memory malware investigation, LOLBin abuse analysis, or WMI persistence examination.
日本語の概要は準備中です。原文の説明を表示しています。
Detect Azure service principal abuse in Microsoft Entra ID using KQL detection queries (Sentinel/Splunk) against Azure AD Audit and Sign-in Logs, covering added credentials, privileged role assignment, admin consent bypass, and service principal enumeration. Use when investigating suspected privilege escalation or persistence via service principals, or building threat-hunting queries for Entra ID identity abuse.
日本語の概要は準備中です。原文の説明を表示しています。
Detect DLL side-loading and search-order hijacking (MITRE T1574) where adversaries plant malicious DLLs for legitimate signed applications to load, by analyzing Sysmon Event ID 7 DLL-load events, checking signatures/hashes against known-good versions, and flagging path anomalies with EDR tools like CrowdStrike, MDE, or SentinelOne. Use when investigating EDR alerts on unsigned DLLs, hunting for APT persistence via trojanized applications, or triaging incidents involving DLL hijacking.
日本語の概要は準備中です。原文の説明を表示しています。
Deploy and configure the Havoc C2 framework (teamserver, HTTPS/HTTP/SMB listeners, Nginx redirectors, and Demon agents) with malleable traffic profiles and OPSEC-hardened infrastructure for authorized red team operations. Use when standing up or hardening Havoc C2 infrastructure for a written, authorized adversary emulation engagement.
日本語の概要は準備中です。原文の説明を表示しています。
Deploy and harden a Sliver C2 team server (BishopFox's Go-based adversary emulation framework) with multi-protocol listeners (mTLS, HTTP/S, DNS, WireGuard), redirectors, domain fronting, and multi-operator support for authorized red-team operations. Use when standing up resilient C2 for a red-team engagement or generating beacon/session implants that must survive blue-team detection.
日本語の概要は準備中です。原文の説明を表示しています。
Map advanced persistent threat (APT) group TTPs to the MITRE ATT&CK framework using the attackcti Python library to query STIX/TAXII data for group-technique associations, then generate ATT&CK Navigator layer files to visualize and compare defensive coverage against adversary profiles. Use when profiling an APT group's techniques, building Navigator coverage heatmaps, or assessing technique coverage gaps against a specific threat actor.
日本語の概要は準備中です。原文の説明を表示しています。
Build an automated adversary infrastructure tracking system in Python (dnspython, python-whois, shodan, networkx) that pivots across passive DNS, certificate transparency logs, WHOIS records, and IP enrichment to map threat-actor C2 networks and flag newly registered domains matching known patterns. Use when pivoting from known indicators to discover related C2 infrastructure or maintaining a continuously updated map of a threat actor's network.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes Windows Security, System, and Sysmon event logs in Splunk to detect authentication attacks, privilege escalation, persistence mechanisms, and lateral movement using SPL queries mapped to MITRE ATT&CK techniques. Use when SOC analysts need to investigate Windows-based threats, build detection queries, or perform forensic timeline analysis of Windows endpoints and domain controllers.
日本語の概要は準備中です。原文の説明を表示しています。
Generate domain permutations with dnstwist and check DNS resolution to detect typosquatting, homograph phishing, and brand impersonation domains registered against your organization. Use when asked to monitor for lookalike domains, investigate a phishing domain, or assess brand-impersonation risk.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes malicious VBA macros embedded in Microsoft Office documents (Word, Excel, PowerPoint) to identify download cradles, payload execution, persistence mechanisms, and anti-analysis techniques. Uses olevba, oledump, and VBA deobfuscation to extract the attack chain. Activates for requests involving Office macro analysis, VBA malware investigation, maldoc analysis, or document-based threat examination.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes bootkit and advanced rootkit malware infecting the Master Boot Record (MBR), Volume Boot Record (VBR), or UEFI firmware for below-OS persistence, covering boot sector analysis, UEFI module inspection, and anti-rootkit detection. Use when compromise survives OS reinstallation or antivirus/EDR fails to detect malware despite clear infection signs.
日本語の概要は準備中です。原文の説明を表示しています。
Systematically evaluate cyber-campaign evidence to attribute an operation to a threat actor, using the Diamond Model and Analysis of Competing Hypotheses (ACH) to weigh infrastructure overlaps, TTP consistency, malware code similarity, and timing/language artifacts into confidence-weighted attribution assessments. Use when an incident investigation needs a defensible attribution confidence level.
日本語の概要は準備中です。原文の説明を表示しています。
Persistent markdown project wiki stored under repository omx_wiki with keyword search and lifecycle capture
日本語の概要は準備中です。原文の説明を表示しています。