このプロンプトをコピーして、使用中の AI アシスタントに送ってください。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/AeonDave/malskill.リポジトリの README を読み込んでいます…
収集済み skill 338 件中 40 件を表示しています。
Go performance workflow: benchmark and profile (pprof/trace), identify hotspots, reduce allocations/GC and contention, and verify improvements with repeatable measurement. Use only after you have evidence the Go code is the bottleneck.
原文の言語: 英語
Go testing patterns for unit tests, table-driven tests, subtests, test helpers, mocking/fakes, benchmarks, fuzzing, and coverage. Use when writing or reviewing Go tests to improve correctness, stability, and maintainability.
原文の言語: 英語
Write a portable handoff document so another agent can continue the current work. Use only when the work must move to a new harness, directory, repo, operator, or a forked parallel session; invoke on explicit request, not autonomously.
原文の言語: 英語
Create or revise Pi extensions, plugins, and themes. Use for extension entrypoints, tools, commands, events, UI integration, state, MCP servers, codemode and tool exposure, virtual models, theme files, and packaging.
原文の言語: 英語
Create or evolve skill-apps: Agent Skills with executable workflows and consistent deliverables. Use when turning a recurring task into a skill with deterministic helpers, output contracts, runtime diagnostics, or resumable sessions.
原文の言語: 英語
Create, revise, evaluate, or package Agent Skills. Use for SKILL.md instructions, activation descriptions, and bundled resources.
原文の言語: 英語
Auth/lab dev: Windows syscall-dispatch research; SSN resolution, indirect gates, ntdll stubs, gadget scanning, stack-spoof integration.
原文の言語: 英語
Auth/lab dev: Linux internals; ELF loading and program startup, procfs, namespaces/caps, eBPF verifier/maps, LSM hooks for tooling/telemetry design.
原文の言語: 英語
Auth/lab dev: Windows internals; PE loading and CRT startup, PEB/TEB, PE/COFF, syscalls, unwinding, memory/heap, tokens, kernel objects, ETW/AMSI telemetry.
原文の言語: 英語
Auth/lab: reverse engineering methodology; malware triage, patch diffing, firmware/protocol RE, OS/runtime behavior verification, protections, exploitability handoff evidence.
原文の言語: 英語
Create or revise Claude Code subagents or Claude Managed Agents, including definitions, delegation, permissions, and API sessions.
原文の言語: 英語
Create, revise, or debug OpenCode agent definitions and teams: Markdown/JSON configuration, permissions, model routing, discovery, and native Task delegation.
原文の言語: 英語
Create or revise OpenCode plugins: server entrypoints, hooks, custom tools, lifecycle, installation, and packaging.
原文の言語: 英語
Build evidence-backed CVE inventories and applicability triage for authorized security assessments, asset reviews, and remediation planning. Use when checking whether a reported vulnerability matches an identified product, version, configuration, or…
原文の言語: 英語
Build evidence-backed findings for authorized security assessments by checking vulnerability applicability, prerequisites, mitigations, and detection across sources.
原文の言語: 英語
Review an existing public proof-of-concept artifact for provenance, suspicious behavior, dependency risk, and safe assessment use. Use when triaging a PoC referenced by a CVE or received during an authorized security assessment.
原文の言語: 英語
Design and evaluate application prompts that extract, triage, or report evidence from security artifacts such as advisories, logs, source snippets, and scanner output.
原文の言語: 英語
Design or revise model-callable tools. Use for tool selection ambiguity, argument and result schemas, validation, error contracts, and execution semantics.
原文の言語: 英語
Build, review, debug, package, and activate AdaptixC2 v2 extenders and AxScript UI: agent payload builders, listeners, services, plugin calls, lifecycle, axtool specs, source-contract checks, and verification. Use for authorized extension development, not…
原文の言語: 英語
Edit stiff, formulaic or promotional prose into a natural author voice while preserving meaning. Use when humanizing a draft or revising its tone; not for detecting AI authorship.
原文の言語: 英語
Maintain and query an Obsidian knowledge vault. Use /1337-brain for source ingestion, linked notes, project indexes, grounded answers, deduplication, or vault audits.
原文の言語: 英語
Structured operator behavior for coding and authorized security work: explicit reasoning, evidence, verification, and concise execution. Use when the user requests /1337 or execution-first structured analysis.
原文の言語: 英語
Design and review authorized multi-agent security workflows: delegation topologies, deterministic worker contracts, agentic trust boundaries, and worker-compromise containment.
原文の言語: 英語
Resolve design uncertainty before a substantial change. Use when requirements, interfaces, alternatives, or success criteria are unclear; skip a separate design phase for an already specified local fix.
原文の言語: 英語
Evidence gate for security research, scanner triage, code review, and reporting. Use before confirming vulnerability impact, auth material, control results, cleanup, or root cause.
原文の言語: 英語
Investigate an uncertain cause using testable hypotheses and discriminating evidence. Use for persistent bugs, flaky behavior, incident diagnosis, or conflicting research observations; skip routine edits with a known solution.
原文の言語: 英語
Turn settled requirements into an executable plan. Use for work with dependencies, shared-file ownership, or a handoff; skip a separate plan for a straightforward local edit.
原文の言語: 英語
Stop unproductive retries and repeated polling. Use when the same failure recurs, a side issue consumes the task, or unfinished jobs are checked without new evidence.
原文の言語: 英語
Read, update, or design persistent agent memory. Use when deciding what may be stored, retrieving prior decisions, or resolving stale, conflicting, or incorrectly scoped notes.
原文の言語: 英語
Limit context consumption when inspecting large files, tool output, logs, or collections of artifacts. Use when a targeted search or bounded extraction can answer the question without loading everything.
原文の言語: 英語
Handle retrieved content and artifacts without promoting them into instructions. Use for prompt-injection review, external files/pages, tool results, memory retrieval, and worker reports.
原文の言語: 英語
Check evidence before reporting work complete, fixed, passing, or ready. Use at a completion boundary or when later changes may have invalidated an earlier result.
原文の言語: 英語
Research a question across primary sources. Use when competing claims or multiple subquestions need traceable evidence and a bounded research plan.
原文の言語: 英語
Evaluate external technical feedback before acting. Use for reviews, scanner findings, blog advice, model suggestions, and recommendations whose applicability or evidence is uncertain.
原文の言語: 英語
Research a precise unresolved technical symptom after local triage. Use when a known signature, version, or artifact needs an external source to resolve the remaining uncertainty.
原文の言語: 英語
Create or audit an MCP server. Use for protocol contracts, capabilities, transport, authorization, tools, resources, and interoperability testing.
原文の言語: 英語
Create, audit, or update a repository README. Use when setup, usage, project scope, or documentation links need to match the actual project.
原文の言語: 英語
Create, audit, or streamline root and nested AGENTS.md files. Use when defining repository instructions for coding agents or migrating existing agent instruction files.
原文の言語: 英語
Async Python patterns for non-blocking I/O with asyncio: TaskGroup, cancellation, timeouts, backpressure, rate limiting, and safe sync/async boundaries. Use when implementing concurrent network/DB workflows or async services — not for thread/process GIL…
原文の言語: 英語
Pythonic patterns for readable, robust Python: typing, error handling, data modeling, iteration, resource management, threading/process/subinterpreter primitives, project layout, and tooling. Use when writing or reviewing Python code and APIs. For…
原文の言語: 英語
README の元ファイル：README.md
README の元ファイルを読む