2,311 件 ・ 関連度順
概要と使いどころ
OCR scanned or image-only corpora with vision-language models in three phases: `evaluate` picks a system by measured CER/WER against stratified human ground truth, `run` builds the production pipeline, and `clean` corrects raw OCR with LLM and rule-based passes, diagnostics, and span-level provenance. Born-digital documents with a text layer go to $doc-to-markdown.
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 testing boolean type validation
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 testing boolean type validation
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 platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
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。
Organize DI registrations using IServiceCollection extension methods. Group related services into composable Add* methods for clean Program.cs and reusable configuration in tests.
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。
Microsoft.Extensions.Options patterns including IValidateOptions, strongly-typed settings, validation on startup, and the Options pattern for clean configuration management.
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。
Open a ready-to-use local 3D model composition workbench for GLB or GLTF files. Use when the user says "打开模型工作台", asks to place, rotate, scale, arrange, or frame one or more 3D models, or needs a clean composition screenshot before website or Image 2 design. If the user has not supplied a model, request GLB/GLTF files first; after models are available, generate the workspace, start its localhost server, and open it automatically.
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 clean git branches from feature work, excluding agent-ops files. Use for PR preparation.
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。
Standardized branch creation with type detection, issue ID extraction, and worktree setup. Creates working branches (-WB) and integrates with selective-copy for clean PRs.
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 when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'. Also use proactively when discovering valuable findings worth preserving.
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。
Manage agent fleet through CRUD operations and lifecycle patterns. Use when creating, commanding, monitoring, or deleting agents in multi-agent systems, or implementing proper resource cleanup.
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 and query a local Markdown knowledge base ("vault"). TWO functions — (1) CONVERT raw files (PDF, Word/docx, PowerPoint/pptx, Excel/xlsx, csv/tsv, images, html, md/txt, json/yaml/code, audio/video) into clean Markdown with retrieval-friendly frontmatter; local-first (pandoc / python-pptx / openpyxl / pymupdf4llm / whisper), with cloud OCR (MinerU) only as a fallback. (2) ANSWER questions over the resulting vault with retrieval discipline — self-monitor coverage, flag missing/lossy content, and propose Maps-of-Content (MOCs). Triggers: "build/sync my local knowledge base", "convert these files to markdown for AI", "整理我的资料库", "把文件转成 md 给 AI 读", "本地知识库", "读我的本地 vault 回答", "这个主题我的资料里怎么说". Not for: one-off web research, or files that are already in a single doc you can read directly.
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 the user wants to create a new CLAUDE.md from scratch for a repository, bootstrap project memory for a new repo, set up a repo for Claude Code for the first time, or completely rewrite an existing CLAUDE.md deemed unsalvageable. Produces a lean, high-signal file under 80 lines (120 hard cap) by scanning the repo for mechanical content (stack, commands, structure) and interviewing the user for judgment content (WHY, gotchas, out-of-scope, approval gates, testing philosophy, external docs like Confluence pages). NOT for auditing or incrementally improving an existing CLAUDE.md — that is the claude-md-improver skill's role.
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。
API developer specializing in clean, well-documented REST APIs
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 operating ProjectClownfish cluster workflows in this repo: reviewing GitHub Actions run artifacts, tuning worker/applicator guardrails, importing ghcrawl clusters, dispatching canaries, scaling batches, or deciding whether autonomous write-mode cluster cleanup is safe to ramp.
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。
Orchestrate a named multi-skill loop such as /loop /review /fix until clean or blocked. Use when the user explicitly asks to loop skills, rerun a review/fix cycle, or says /loop with one or more skill names.
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。
Run a high-thoroughness end-to-end implementation loop using clean worker worktrees, per-slice planning, implementation, explicit review/fix iteration, orchestrator integration, and final commit/PR drafting. Use when the user explicitly wants a Ralph/Wiggum-style loop, autonomous multi-agent execution, a delegated feature/bugfix carried from confirmed scope through review-ready completion, or RFC-driven implementation that should be reviewed, bumped to In Progress, decomposed into phases, and executed through nested sub-loops. Supports Codex subagents by default and external CLI workers such as OpenCode when explicitly requested and available.
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。
Report which local git worktrees under tmp/ are safe to close, need a human look, or are explicitly protected. Use when the user says /fleet-audit, asks what worktrees can be cleaned up, or wants a status check across all Ralph-loop/spike worktrees before running closeout on any of them.
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。
Run the Incan review/fix loop end to end: review, fix actionable findings, and review again until clean or blocked. Use when the user wants an autonomous review-and-repair pass or says /review-and-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。
Review touched code for maintainability smells such as duplication, awkward indirection, suspicious clones, dead code, poor naming, and Boy Scout cleanup opportunities. Use when a broad review needs a dedicated maintainability pass or when the user asks for code-smell review specifically.
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。
Fix actionable in-scope findings in the current Incan worktree, usually after /review. Use when the user asks to fix review findings, clean up reported issues, apply in-scope review feedback, or says /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。
Use whenever the user wants to find, shortlist, vet, or enrich US management consultancies — strategy, operations, executive coaching, leadership development, org-development/change management, PMO/program management, sales/revenue operations consulting. Triggers on "find me three top strategy consultancies in California", "shortlist boutique ops-consulting firms with healthcare experience", "we need an executive coach for our new CEO", or "pull contact info for these 10 consulting firm domains", even when described indirectly (post-merger integration help, change-management partner, fractional COO). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Skip in-house strategy hires, "help me build a strategy" do-the-work asks, framework comparisons (Lean vs Agile, BCG matrix, etc.), academic/MBA-program questions, life/career coaching for individuals, non-US firms, individual freelancers.
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 reviewing, writing, or debugging Go code under exercises/part2/ (and matching embedded code in docs/part2/**/*.mdx). Thinks hard about correctness, idiomatic Go, error handling, resource cleanup, concurrency, and — crucially — what the tests would catch: edge cases, races, leaks, timeouts, and port conflicts. Knows the repo's module-mode quirk (GO111MODULE=off) and which dirs carry go.mod.
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 reviewing, debugging, or giving feedback on Go code in this repo (exercises/part2, website/tools, or any *.go file) or when asked for a "code review", "review this Go", "revisa este código Go", or "crítica de código". Reviews for correctness, idiomatic Go, error handling, resource cleanup, concurrency, performance, and security, and always ends with a test-thinking pass (what a test would catch). For exercises/part2, prefer the go-exercise-reviewer skill which knows the module-mode quirk; this skill covers general Go anywhere in the repo.
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。