4,112 件 ・ 関連度順
概要と使いどころ
Performs fast first-pass triage of an unknown file to decide depth of analysis: file type identification, hashing, reputation lookup, packing/entropy check, and string review. Activates for requests to triage, classify, or do initial assessment of an unknown or suspicious file.
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。
Hunts for anomalous authentication such as password spraying, brute force, and impossible-travel logons by aggregating Windows logon success/failure events per account and source over time. Activates for requests to hunt anomalous logons, detect password spraying or brute force, or find suspicious authentication patterns.
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。
Reverse engineers binaries using radare2/rizin interactively, covering analysis initialization, navigation, disassembly and graph views, patching, and the visual mode workflow. Activates for requests to reverse a binary with radare2 or rizin, learn r2 commands, or navigate and disassemble a sample in r2.
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。
Collects volatile evidence from a potentially compromised host in correct order of volatility: memory, network state, running processes, logged-on users, and open handles, while preserving integrity and minimizing footprint. Activates for requests to collect volatile evidence, perform live response, or capture host state before shutdown.
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。
VST3 format adapter for Pulp — SingleComponentEffect wiring, bus arrangement negotiation, parameter / MIDI event routing, state round-trip, and the pitfalls discovered while wiring the adapter against Steinberg's SDK.
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。
ChIP-seq analysis — peak calling, differential binding, motif discovery, and QC with phantom-peak metrics.
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。
Bulk RNA-seq differential expression — experimental design, count modeling with DESeq2/edgeR, and enrichment.
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。
Coordinate teams of role-based agents — role definitions, task delegation, sequential and hierarchical workflows, and shared memory. Use when a job naturally splits into specialist roles collaborating.
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。
Master orchestrator for B2B SaaS marketing campaigns using the CATALYST framework (Coordinated Agents for Targeted, Analytics-Led, Year-round SaaS Transformation). Coordinates 90 specialist agents across 17 marketing disciplines. Use this skill for ANY large-scale marketing initiative: full GTM launches, annual marketing plans, multi-channel campaigns, quarterly planning, or any task requiring coordination across content, SEO, paid media, social, email, design, sales enablement, product marketing, analytics, project management, and client operations. Also triggers on: marketing strategy, campaign plan, GTM launch, quarterly plan, marketing ops, full-funnel campaign, marketing audit, growth plan.
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。
Master orchestrator for B2B SaaS content creation and the editorial production system behind it. Use this skill to produce blog articles, whitepapers, case studies, video scripts, newsletters and ghostwritten thought leadership, to develop content strategy, and to run the publishing line itself — content briefs, editorial calendars and production capacity, review and approval workflow, subject-matter-expert access, the style guide, an AI-drafting policy, and a content inventory with owners. Also triggers on: blog, article, case study, whitepaper, newsletter, video script, ghostwriting, content calendar, editorial, thought leadership, content strategy, content brief, content operations, content ops, editorial workflow, managing editor, who reviews this, our content pipeline is stuck, content is stuck in review, content audit, content inventory, content governance, style guide, house style, SME interview, expert interview, freelance writers, AI content policy, how much content can we actually produce. Also owns the customer academy and customer education: online courses, onboarding curriculum, tutorials, certification programs, digital credentials and badges, exam and pass-mark design, course freshness when the product UI changes, and whether the academy should sit behind a login. Triggers on: customer academy, customer education, online course, course library, learning path, curriculum, tutorial, certification program, certified users, digital badge, Open Badges, recertification, exam, pass mark, LMS, Skilljar, our tutorial shows the old UI, our course is out of date, should the academy be gated, do certified customers renew better.
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。
Chanjing AI creation Open API client: submit image/video tasks, poll task status, list and get tasks, and optionally download outputs when the user runs download_result.py. Reads and writes local credentials.json; calls open-api.chanjing.cc.
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。
Reviews audio DSP and audio processing code for realtime safety violations. Use whenever the user asks to review, audit, or check audio processing code — including plugin process callbacks, audio engine render functions, DSP implementations, or any code that runs on the audio thread. Trigger on phrases like "review my processBlock", "check this DSP code", "is this safe for the audio thread?", "review my JUCE plugin", or when you see an audio callback and spot potential realtime violations. Flag issues proactively even when the user hasn't explicitly asked for a review.
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。
Diagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow despite demeaner_backend="cupy64" and an idle GPU. Use when: (1) a script looping dozens of pf.feols models on a 100k+ row panel takes ~1 min/model, (2) process inspection shows ~1-1.5 cores busy and nvidia-smi shows ~0% GPU utilization with a resident cupy context, (3) planning any worker prompt that will run a model grid (robustness variants x FE structures x domains). Root cause: per-model CPU-side single-threaded fixed costs (formulaic model-matrix build, interaction construction, singleton detection, cluster vcov) dominate wall time; GPU demeaning is a small slice. Fix: shard the model grid across OS processes and/or use pyfixest multiple-estimation syntax; mandate this IN THE WORKER PROMPT.
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。
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
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 custom editor tooling including Custom Inspectors, PropertyDrawers, EditorWindows, Gizmos, and Handles. Use when building designer-facing tools, spatial visualization, batch operations, or custom component UIs. Triggers on requests like "create a custom inspector", "add gizmos", "build an editor window", "make this component designer-friendly", "add a debug visualization", "create a level editor tool", "add a property drawer", "make a batch rename tool", or any editor tooling work. Always uses SerializedProperty and Undo for safety.
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。
Wwise audio middleware integration for Unity including events, banks, RTPC, spatial audio, and callback handling.
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。
When a GDD is revised, scans all ADRs and the traceability index to identify which architectural decisions are now potentially stale. Produces a change impact report and guides the user through resolution.
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。
Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.
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。
Unity lifecycle and execution order correctness patterns. Catches common mistakes with initialization ordering, destruction timing, fake-null, disabled components, editor vs runtime init, DontDestroyOnLoad, and async destruction. PATTERN format: WHEN/WRONG/RIGHT/GOTCHA. Based on Unity 6.3 LTS documentation.
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。
Unity 6 packages and services guide. Use when working with Package Manager, installing/updating packages, scoped registries, or Unity Gaming Services (Authentication, Cloud Save, Analytics, Leaderboards, Matchmaker). Covers essential packages list and version compatibility. Based on Unity 6.3 LTS documentation.
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。
Unity 6 audio system guide. Use when working with sound effects, music, AudioSource, AudioClip, AudioListener, Audio Mixer, spatial audio, or audio optimization. Covers 3D sound, mixer groups, snapshots, and audio import settings. Based on Unity 6.3 LTS documentation.
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。
用于证明前端重构保持了既有行为、选择合适的安全网、逐步验证结构修改，或依据证据给出 PASS、PARTIAL、NOT PROVEN 的行为保持结论。
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 when proving that a frontend refactoring preserved existing behavior, selecting an appropriate safety net, validating each structural step, or assigning a PASS, PARTIAL, or NOT PROVEN preservation verdict.
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 when building or reviewing substantial forms with React Hook Form, Zod schemas, typed validation, dynamic fields, controlled third-party inputs, file upload, multi-step flows, dependent validation, or form performance. Do not use for trivial 1-3 field forms without validation; Chinese triggers include form, form validation, dynamic fields.
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。