4,851 件 ・ 関連度順
概要と使いどころ
Write commit messages under the agent-commits convention - a Conventional Commits fork with no chore catch-all, intent-only type tokens, facts in trailers, and legally-grounded AI provenance (Assisted-by, never Co-authored-by). Use when composing a commit in a repo whose commitlint.config.js extends agent-commits, when deciding between feat/fix/refactor/perf, or when recording AI participation.
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。
Investigate and fix failing CI. Takes a PR reference, one or more CI run/job URLs, or freeform text describing where the failures are, then enumerates failing workflows/jobs/steps, determines the root cause (often one shared cause behind several red checks), proposes a fix plan, applies code changes, commits, pushes, watches the new runs, and repeats until checks pass. Use when the user says "fix CI", "CI is red", "checks are failing", "the build is broken on my PR", "fix the failing jobs", or pastes a failing CI run URL. Do NOT use for authoring new workflows, or for read-only diagnosis with no fix intent — use gha-log-reader for that.
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。
Create and commit a durable handoff document that gives a fresh agent the context and prompt to continue the current planning or implementation work. Use only when explicitly invoked as `$handoff` or when the user explicitly requests a handoff.
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。
Execution pipeline for Codex. Detect epic/task/bug mode and implement with Codex models only. Usage: /implement <issue#>
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 an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
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。
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
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。
Rebases a feature branch onto its latest base, resolving conflicts while preserving the intent of local changes, optionally force-pushing and watching CI afterward. TRIGGER when: the user wants to rebase a feature branch, update a branch against its base, or replay local work on top of the latest upstream. DO NOT TRIGGER when: merging a release branch into dev → merging-branches; only watching CI on an already-open PR → monitoring-pull-requests.
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。
Opens a pull request, publishing the current branch as a PR. TRIGGER when: the user wants to open a pull request, publish the current branch as a PR, or take the current work through to an open PR. DO NOT TRIGGER when: only committing changes → commit; babysitting CI after the PR is already open → monitoring-pull-requests.
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。
Code simplification suggestions — clarity, unnecessary complexity, redundant abstractions. Advisory only.
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。
Code simplification suggestions — clarity, unnecessary complexity, redundant abstractions. Advisory only.
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。
[Dev Data] Use when you need to implement or enhance test data seeders that simulate QC happy-path scenarios via application-layer commands. Flag: --mode=review reviews a target seeder (or the current changes / current work-context result) against every universal seed-data rule AND the project-specific seeder conventions — read-only, evidence-backed PASS/FAIL.
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。
[Workflow] Use when activating the Architecture Audit workflow to review the whole project's architecture, run an architecture health check, or check production readiness/scalability in one pass — read-only, produces one consolidated Architecture Health Report.
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。
[Testing] Use when you need to drive an integration-test suite to fully green — each round runs /integration-test-verify (whole system by default, or the target named in the prompt), and on ANY failure combines /debug-investigate + /integration-test-review (report-only) to adjudicate the fault (test wrong · test not optimal · source wrong), then /fix to resolve it at the owning layer, then /changes-review on that round's fix diff, then re-runs a FRESH full verify — looping until the whole suite passes its 2-consecutive-green-runs gate with zero failures.
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。
[Implementation] Use when you need to start coding & testing an existing plan. Flags: --approval=off (auto/trust mode, no approval gate), --tests=off (skip the test step), --parallel={auto|on|off} (default off — sequential; --parallel/=on opts in to parallel sub-agent waves; =auto fans out only when the plan declares PAR/SEQ tags and write sets).
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。
[Utilities] Use when a project needs to add, change, list, or remove its OWN protocol rules layered on top of a framework skill — a named overlay of extra project rules that applies whenever the targeted skill runs, stored with the project rather than in the portable framework. `/project-skill-protocol list` prints every overlay with its target and description; `add` drafts a new overlay and confirms it before writing; `update` applies a surgical change; `delete` removes it. Overlays are ADDITIVE ONLY — they never replace, override, or waive anything the skill already does. Triggers: skill protocol, project protocol, custom protocol for skill, extend a skill, overlay rules, add rules to a skill, project rules for skills, skill protocol overlay.
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。
[User-Invoked] Use ONLY when the user explicitly types /dual-ai or /dual-ai <workflow-id> — fans out one prompt, or one workflow invocation per tool, to two fresh parallel AI sessions (Claude Code + Codex CLI), both pre-set to xhigh reasoning effort and full-permission mode before the prompt executes. NEVER auto-activate.
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。
[Code Quality] Use when you need to combine /changes-review + /fix in a recursive loop — each round runs /changes-review (report-only) to surface validated findings over a fixed diff scope, then /fix to resolve them, then loops again with a FRESH full /changes-review over the CHANGED diff until one complete pass produces zero validated findings (nothing left to fix).
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。
[Utilities] Use when the user invokes, lists, saves, updates, or deletes a PROJECT-SPECIFIC saved prompt — a named, reusable procedure stored with the project rather than in the portable framework. `/custom-prompt list` prints every defined prompt with its description; `/custom-prompt <free-text request>` matches the request to the closest saved prompt and executes it only after a confirmation gate; `/custom-prompt save|update|delete ...` maintains the registry — save never stores raw wording, it drafts the best version of the prompt and confirms the name, description, inferred goal, and steps with the user first. Triggers: custom prompt, custom prompts, list custom prompts, save this prompt, save this prompt task, update this prompt, my saved prompt, project prompt, playbook, recipe, runbook.
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。
Read-only reviewer for agent-flow. Judges one diff against the acceptance criteria, AGENTS.md rules, protected paths and risk boundaries; returns a JSON verdict with line-anchored findings. Use when launched with AGENT_FLOW_ROLE=reviewer or asked for an agent-flow review of a diff.
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。
Expert SwiftUI guidance for macOS apps — covers writing and reviewing code with runtime-level understanding of observation, concurrency, performance, and platform integration. Use when user asks to "build a SwiftUI view", "review my SwiftUI code", "fix observation issues", "bridge AppKit", "architect state management", "debug view updates", or works on any macOS SwiftUI project — building features, reviewing existing code, debugging view updates or performance, fixing concurrency issues, architecting state management, bridging AppKit, or making design decisions. Do NOT use for iOS/iPadOS-only SwiftUI, UIKit bridging, or basic Swift language questions. Focuses on non-obvious traps and deep patterns, not basics.
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。
TypeScript-only skill for generating and debugging high-resolution AI images through sub2api OpenAI-compatible APIs. Use this whenever the user wants a TS/Node sub2api image generator, 4K image generation, stream=true /v1/images/generations or /v1/responses image generation, Cloudflare 524 timeout avoidance, partial image capture, or SUB2API_BASE_URL/SUB2API_API_KEY based image generation.
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 designing types and collections for hot paths and low-allocation .NET code. Keywords: readonly struct, sealed class, ValueTask, Span, FrozenDictionary, FrozenSet, allocation optimisation.
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。
Legacy. Use only when images (photos, illustrations, screenshots) must reach TypeSafe's Jev (System One) model as text, because the request can't send the `TypeSafe-Danger-Zone-Images` header that lets Jev read images directly. Triggers on "turn this photo into a Jev state", "describe these images for Jev", "decode images for System One", or a Jev project whose decision depends on what a picture shows. Handles 1 to about 100 images; produces a neutral, complete decode and a JSON state, checked against Jev.
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。
Install or upgrade the event4u agent-config suite. This marketplace plugin is a bootstrap shim — it ships hooks plus this pointer only; ALL skills, rules, and commands are installed via `npx -y @event4u/agent-config init`. Use when the user asks to install, set up, or upgrade agent-config, or wonders why this plugin contains no other skills.
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。