AGENT SKILLS · ミッション装備
実際に使われている Agent Skills
公開リポジトリの検証済み Skills を比較し、機能、内容、導入状況、出典を確認してから追加できます。
- 掲載範囲
- 検証済み
- Skills
- 23,248
- リポジトリ
- 3589
- 最終同期
- 2026/11/04
full-aigc-skillsjianying-audio
Design and edit JianYing audio layers through Rust CLI media and timeline capabilities, including probing, volume, fades, sound effects, relinking, and playback checks.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-draft
Design and validate jianying-job/v2 or compatible plan documents using the Rust domain model, schema gates, microsecond timing, and evidence-aware output contracts.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-edit
Create a new JianYing draft or edit an existing draft through an isolated Rust jianying-job/v2 workflow with measured media facts and explicit evidence gates.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-export-prep
Prepare proxy or native JianYing exports through Rust capability, runtime, approval, and artifact gates without confusing preview output with final delivery.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-harness
Operate the Rust JianYing agent harness across persistent jobs, exact approvals, isolated configuration, MCP transports, recovery, and host-neutral result contracts.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-inspect
Inspect JianYing media and drafts read-only through Rust CLI probes, structural summaries, validation, and explicit evidence-level reporting.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-narration
Condense narration video through measured media analysis, governed ASR reuse, protected speech boundaries, isolated timeline edits, and playback-level acceptance.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-recover
Recover JianYing Rust jobs and drafts through task inspection, audit, explicit retry, transaction snapshots, and fail-closed handling of ambiguous external operations.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-setup
Diagnose the Rust jianying CLI, media tools, draft roots, configuration profile, and native runtime readiness without silently installing or mutating the host.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-subtitles
Import, edit, style, translate, export, and verify JianYing captions through Rust CLI commands while preserving measured timing and evidence boundaries.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-transitions
Select and apply JianYing transitions through Rust catalogue and timeline capability gates, validating adjacent segments, resource authorization, duration, and playback.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
full-aigc-skillsjianying-use
Route JianYing editing requests through the single Rust jianying CLI, asking only essential questions and stopping on missing capabilities or insufficient evidence.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
jdharmongit
Use this skill for project-specific git workflows: formatting commits, executing git flow operations (feature, release, hotfix), and determining version tags. Trigger on requests to commit changes, summarize branch changes, tag releases, or manage git-flow branches. Do NOT trigger for general git help or basic troubleshooting.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月8日
jdharmonprompt-engineering
Write, audit, and port prompts using each vendor's official prompting guidance. Use this whenever the user is working on a prompt, system prompt, agent instruction file, AGENTS.md/CLAUDE.md, tool description, or LLM-facing template — including when they say a model "isn't listening," is too verbose or too terse, over- or under-uses tools, ignores format instructions, or when they're switching a prompt from one model or provider to another. Also use when the user asks how to prompt a specific mod
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月8日
jdharmonpython
Python conventions built entirely on uv. Use whenever installing Python packages, creating or activating a virtual environment, installing or running a Python CLI tool, choosing or pinning an interpreter version, running a Python script, setting up a new Python project, or adding dependencies to an existing one. Also use when about to write any pip, pipx, pyenv, poetry, virtualenv, or python -m venv command — those are all replaced here.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月8日
paulnsorensensliced-bread-depth
- Score each slice of a Sliced Bread codebase as a deep module: classify its crust shape, measure where implementation mass sits relative to the crust, and recommend which crusts to break down. Use when the user asks "are our slices deep", "review the crusts", "which modules should we break down", "is this facade too fat", or after a compliance review passes but a slice still feels monolithic. Do NOT use for boundary compliance on a change set (sliced-bread-review) or a rule-violation sweep (sli
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月19日
theanadimuktsoftware-development-workflow
Routes software-development requests to the smallest relevant set of installed specialist skills. Use for command-style requests such as /spec, /plan, /architect, /build, /test, /debug, /review, /code-simplify, /webperf, or /ship; also routes frontend design, motion, mobile, and ADHD-friendly output requests without embedding upstream skill content.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月20日
zelinewangclaudemem
Captures knowledge notes and session reports that persist across conversations. Provides full-text search with faceted filters, code structure analysis, and bidirectional cross-referencing between notes and sessions. Use when saving knowledge for future sessions, recalling past work, searching stored context, wrapping up a session, or analyzing code structure. Default: local, zero network. Cloud embedding backends (Gemini, Voyage, OpenAI) are opt-in via claudemem setup.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月9日
zlliangbuilding-skills
Creates, edits, or improves agent skills (SKILL.md). Use whenever the task is to author a new skill, refactor or shorten an existing one, fix its frontmatter or triggering description, or split it for progressive disclosure. Load this before researching other skills or writing any SKILL.md.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月7日
zllianggh-cli
Uses GitHub CLI (gh) for GitHub repositories, issues, pull requests, actions, releases, gists, and API calls. Use when a task requires GitHub operations from the command line.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月7日
zllianggit-commit
Creates Git commits with Conventional Commits analysis, safe staging, and concise message generation. Use when the user asks to commit changes or create a git commit.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月7日
zlliangwriting-issues-and-prs
Writes, edits, reviews, or improves concise titles, bodies, and comments for issues, pull requests, and merge requests on GitHub and GitLab, and for work items (tickets, stories, tasks, epics) on Jira, Linear, and similar issue and project trackers.
- 1時間の導入数
- 1
- GitHub Stars
- 0
- 更新日
- 9月7日
docling-projectdignified-python
Opinionated production Python standards with automatic version detection (3.10-3.13). Use when writing, reviewing, or refactoring Python in repos that want modern type syntax, explicit condition checks where practical, pathlib operations, interface guidance, and pragmatic production patterns.
- 1時間の導入数
- 1
- GitHub Stars
- 6.7万
- 更新日
- 9月18日
vercel-labsnative-sdk
Discovery skill for the Native SDK, the complete toolkit for building native desktop applications. Apps are authored in TypeScript + declarative Native markup (.native) by default and compiled to native code with no JS runtime in the binary; Zig cores are an explicit alternative, and WebViews are the optional web-content path. Use when the user asks what the Native SDK is, how to build a Native SDK app, author native UI, scaffold an app, configure app.json or legacy app.zon, add bridge commands,
- 1時間の導入数
- 1
- GitHub Stars
- 7687
- 更新日
- 9月16日