В каталоге 183 730 навыков в 14 категориях.
Use when asked to recover prior work and current status before resuming. Returns a status-tagged capsule and one concret...
Use when asked to recover prior work and current status before resuming. Not for handoff snapshots: use handoff. Not for...
Query the memory system for relevant learnings from past sessions
Compute the Recall metric — provided by torchmetrics. Use when the user has predictions and ground-truth and needs to co...
Quick single-project context check. Reads next-session.md directly (no subagent) and outputs a 6-field briefing. For mul...
Reconstructs the development cycle from git history, distills sequential/parallel patterns, and produces actionable insi...
Spaced repetition and retrieval practice engine for the vault. Use when the user wants a review session, recall practice...
Query the cross-provider topic-memory corpus by keyword (and optional class) instead of grepping ~180 files. Use when yo...
Query the memory system for relevant learnings from past sessions using semantic search.
Search persistent memory, git history, and dev_env SSOT before work. Use at session start, when taking a new task, or wh...
Rebuild working context from handoffs, tickets, and live git state.
Run the retrieval recall gate with dead-gold triage and the binary A/B regression test. Required before release tags; us...
Recall knowledge base entries by meaning, not just keywords — hybrid search (lexical ripgrep + local vector embeddings +...
Drafts FDA product recall plans compliant with 21 CFR Part 7, covering Recall Committee governance, health hazard evalua...
Automatically search and retrieve relevant project memory from Mem0 when working on tasks that might benefit from past d...
Recall why a past change was made by locating the Claude Code transcript that produced it. Use when the user asks to "re...
Search past reasoning for relevant decisions and approaches
Recall the reasoning behind a past change by locating the Claude Code transcript that produced it. Use when the user ask...
Recall.ai integration for AI agents via ClawLink — browser login, no API key setup. Connect recallai through ClawLink's...
Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updatin...
FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preser...
Get session recap including preferences, recent context, and active goals. Use at the start of a session or when context...
Triggered by "monthly recap", "how did I do this month", "spending summary", "financial review", "weekly recap", "quarte...
Summarize your current session state - problem, progress, hints used, what's left to do.
Daily or period recap via `oma-recap`. Resolves a date or window from natural language, invokes `oma recap --json`, dele...
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据，按主题分组汇总"我都做了什么"，并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用...
Show recent Claude Code sessions across all projects, so the user can re-enter work after a reboot or context switch. Li...
Use when modifying recce/mcp_server.py, MCP tool handlers, error classification, or MCP-related tests. Also use when add...
Use when MCP server code is modified and needs full E2E verification against a real dbt project. Triggers after changes...
Consulta e opera o modulo de Recebimento Fisico (Fase 4): preenchimento de lotes, quantidades e quality checks com proce...
Verify that a requested bug fix changes observable behavior with a failing-before, passing-after reproduction and honest...
Audit a sealed runx receipt for governance, comparing exercised authority and any declared approval requirement with sig...
개인사업자의 영수증·카드 내역을 부가세와 종소세 관점에서 분류하고 증빙 누락·중복·공제 후보를 점검할 때 사용한다. 분류 결과를 신고서에 넣는 화면 작업은 vat-hometax·income-tax-hometax가 맡...
Use when compiling phone-camera photos of receipts into an A4 PDF expense-claim pack — straighten, B&W scan look, option...
Use AgentPMT external API to run the published workflow Receipt OCR to Zoho Books Expense Pipeline with wallet signature...
Retrieve bounded receipt evidence by exact ids or explicit filters, returning native verification results for downstream...
Render a completed diamond's work as a shareable, factual one-page "work receipt" (problem framed, assumptions tested, w...
Receipt OCR and structuring skill. Use when Codex needs to extract vendor, date, totals, and categories from receipts or...
Master receipt scanning operations including parsing, debugging, enhancing accuracy, and database integration. Use when...
Receipt OCR row-draft and continuation-packet binder for the reviewed workbook inputs and backup-ready route record.
Receipt OCR intake checkpoint for the sorted JPG receipt set and stat_ocr.xlsx workbook contract.
Receipt OCR workbook finalizer that writes the reviewed results sheet and closes the bound backup route.
Approve the receipt-image working set, extraction rule set, and selected-versus-non-selected candidates that will feed w...
Run and verify the daily receipt-to-Drive pipeline locally. Scans Gmail for purchase emails, uploads to Google Drive, an...
Generate a personal Claude Code usage & impact report ("receipts") from this machine's local session transcripts — for j...
Audit any document against its own sources — every factual claim extracted and graded as evidenced, partially evidenced,...
Read a batch of receipt images directly via vision, classify each into expense categories, optionally reconcile against...
Register received or authored project documents by confirmed coordinates, preserve their filenames and provenance, and f...
Ingest and parse incoming messages, events, or signals into structured form. Use when processing external inputs, handli...
Read incoming retalk messages from this session's user's DESIGNATED sender(s) — one-shot, or as a background --follow re...
Use this skill when the user receives an externally-authored, multi-feature product brief -- a PRD, a solution handoff,...
Use when receiving code review feedback, before implementing suggestions. Requires technical rigor and verification, not...
Process Godot code review feedback — use when the code-reviewer agent has provided feedback, before implementing suggest...
Use when you have received code review feedback and need to process it. [DEPRECATED] Routes to code-review --feedback
Use when receiving code review feedback — before implementing suggestions, especially if feedback seems unclear or techn...
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or techni...
Assesses and responds to incoming code review feedback on PRs (reviewer comments, requested changes), especially when su...
Teaches how to receive review feedback properly — verify-before-implement on every comment, different skepticism levels...
Use when receiving code review feedback, before implementing it: verify technically, no blind agreement.
Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, dis...
Use when code review feedback has come back on a change, before responding to or resolving any of it.
（中文）Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or te...
Verifies review feedback with technical rigor, not blind agreement. Use when receiving review before implementing sugges...
receiving-code-review
Use when receiving code review feedback, before implementing any of it — especially if feedback seems unclear, technical...
收到代码审查反馈后、实施建议之前使用，尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证，而非敷衍附和或盲目执行
Receive and act on code review feedback with technical rigor, not performative agreement or blind implementation
Use when receiving code review feedback, processing reviewer comments, or responding to suggested changes from human or...
Use when receiving review feedback. Reason about each item — don't performatively agree.
Use when explicitly invoking the legacy receiving-code-review entrypoint; incoming feedback is owned by review.
Use when explicitly invoking the legacy receiving-code-review entrypoint; incoming feedback is owned by code-review.
Handles feedback incorporation from code reviews
Code review requires technical evaluation, not emotional performance.
Use when processing code review feedback. Technical evaluation of feedback, verify before implementing. No performative...
Evaluate code review feedback on its technical merits, verify each suggestion against the codebase, then implement the f...
Processes code review feedback by classifying each finding, reproducing or validating it against the real contract, appl...
当你收到代码评审反馈，并且准备实现建议之前使用；特别是在反馈不清楚或技术上可疑时，它要求技术性核实，而不是表演式认同或盲目照做
Use when receiving critical feedback on an analysis or manuscript, before implementing suggestions, especially if feedba...
You MUST use this when receiving feedback that evaluates a text-based work artifact you produced or are responsible for...
Use when receiving feedback, before implementing suggestions, especially if feedback seems unclear or technically questi...
PR feedback, review comments, code review response, address review, respond to feedback, handle reviewer suggestions, fi...
Process reviewer feedback for GitHub PRs and GitLab MRs. Use after pushing a commit to recheck reviews, or when asked to...
Use when feedback on your own change arrives (a reviewer's comments, a list of findings, a bot report) and before acting...
Fetches a Jira ticket with all linked tickets and Confluence pages, then creates a standardized project workspace folder...
Validates answers that depend on current external facts, including prices, versions, policies, rankings, recommendations...
Summarizes the last few commits. Use when the user asks what changed recently.
Son degisiklikler logu. Check when debugging or understanding recent fixes.
最近のコミットをセキュリティ・パフォーマンス・保守性の観点からレビュー。「最近の変更をレビュー」「今日のコミットを確認」「コードレビューして」と言われた時に使用
Use Recent Data to find and apply recently accessed topics and resources.
Guide for using Recent Data (topics, resources, pages). Use when working with recently accessed items, implementing rece...
Lists the most recent emails received, sent, drafted, or starred in Gmail. Defaults to last 24 hours, or accepts custom...
Discovers and lists recently modified or created files in Google Drive with professional metadata and summaries. Returns...
Use AgentPMT external API to run the Recent News Article Aggregator tool with wallet signatures, credits purchase, or cr...
Recent quarter performance analysis, quarterly earnings review, last quarter results, quarterly financial performance, a...
Med-adapted recent-quarter review: last print financials, pipeline-milestone awareness, and FDA-event context — reads th...
Render Rove's recent releases as a self-contained, Rove-styled HTML page (Chinese by default). Reads shipped notes from...
recenter on where we are, what's done/left, and where necessary reflect on our work's principle compliance, performance,...