Process user-provided patent figures and generate formal drawing descriptions. Use when user says \"附图处理\", \"figure description\", \"附图说明\", \"drawings description\", or wants to…
Drive a multi-party deliberation in a Slack channel or thread. The agent is an involved orchestrator — presses rigorously, brings evidence, names trade-offs, surfaces…
Use when: auditing code that builds filesystem paths from external input and then reads, creates, mutates, or deletes files under a trusted root.
Apply a criterion to items and keep or drop them. The grep of knowledge work — binary keep/drop decision per item. Different from rank (which reorders but keeps all).
Generate financial statements (income statement, balance sheet, cash flow) with period-over-period comparison and variance analysis.
Finalize orphaned recordings - stop processes, compress, push to orphan branch. TRIGGERS - finalize recording, stop asciinema, orphaned recording, cleanup recording, push…
Generate an income statement with period-over-period comparison and variance analysis
Generate financial statements (income statement, balance sheet, cash flow) with period-over-period comparison and variance analysis.
Resolve an agent name or description to an exact mngr agent name. Used by other skills that target agents.
Search your Microsoft Outlook inbox and cross-reference emails with your contact history — find any email instantly and see full relationship context alongside it via Rarefriend.
Find pages with overfull boxes (content that doesn't fit) in LaTeX presentations. Use when checking for layout issues or content overflow.
Resolve data lake and lakehouse asset references across Glue Data Catalog, S3, S3 Tables, and Redshift.
Use when feature implementation is complete and the branch is ready for final validation, PR creation, or merge.
Archive a completed bugfix or feature workflow by renaming its branch into the archives/ namespace and moving its specs and SQL folders into the archives/ trees.
Analyze the dispatch-log for per-feature spend, cache hit rate, and model routing — surface optimization opportunities
AI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract…
Bulk extract content from an entire website or site section. Use this skill when the user wants to crawl a site, extract all pages from a docs section, bulk-scrape multiple pages…
Download an entire website as local files — markdown, screenshots, or multiple formats per page. Use this skill when the user wants to save a site locally, download documentation…
Discover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site…
Use when a GitHub issue reports a missed, spurious, or wrong-element annotation. Reproduces the failure with debug_annotation.py, diagnoses the root cause, and improves schema…
Use when: planning fixes for a batch of review findings, clustering findings by shared root cause, deciding root-cause versus symptom-level fixes, ordering a fix batch for one…
Use when: assessing what a proposed fix or patch could newly break before it is pushed, tracing fix impact through callers, shared state, and contracts, checking whether a fix…
Read an Obelus compile-error bundle, make the minimal source edits needed to clear the compiler errors, and stop. The desktop re-runs the compiler to verify.
Systematically fix multiple GitHub issues with parallel analysis and sequential TDD fixes. Use for batch bug-fixing sessions.
Fix a random FIXME in the codebase (in the given scope, use "." for the whole codebase)
バグ修正→コンパイル確認→回帰テスト→失敗時 revert の安全修正パイプライン。修正が新たなバグを生まないことを機械的に保証する。USE WHEN 単発バグ修正、影響範囲が見えにくい変更、リファクタの安全確認。SKIP 大規模機能追加は impl-orchestrator、セキュリティ Finding 一括修正は robust-fix、仕様整合性回復は…
Auto-tag tests that flaked >N times in M runs, move them to a quarantine suite, and cap how long they stay there
Generate spaced repetition flashcards from notes or topics. Use when user wants to create flashcards, make review cards, prepare for spaced repetition, or convert notes to quiz…
Analyze any fleet's inventory/devices.json and recommend optimal Ollama models per device based on hardware constraints, inference tier, and current LLM landscape.
Defamiliarization audit for empirical output. Systematically interrogates every feature of a figure, table, or set of results — not just the main finding.
Use when the user wants to manually flush a deferred-commit queue from a prior or interrupted chain. Reads .hyperflow/commits-queue/manifest.json, fast-forwards the staging branch…
Write follow-up emails that re-engage without being annoying. Uses proven psychology for follow-up sequences. 42% of replies come from follow-ups.
Walk a user through what changes when they take ai-brain-starter from a personal vault to a team vault.
Time-series forecast spec (ARIMA / Prophet / ML) with validation strategy, monitoring plan, and retraining triggers.
Hard reset for a specific task type. Deletes playbook, confidence entry, evaluations, and classifier data.
Create or configure a fork workflow with git-town. Preflight checks at every step. TRIGGERS - fork repo, setup fork, git-town fork, create fork, fork workflow, upstream setup.
Справочник паттернов компоновки управляемых форм 1С. Используй как справочник при проектировании форм — архетипы, конвенции, продвинутые приёмы — from general/general-misc
Bidirectional sync between a fork project and Foundation_template using git subtree. Pull canonical skills/agents/lessons into the fork, or push contributions back.
Run FPGA synthesis pipeline from .tri spec to bitstream. Use when working with Verilog, FPGA, or hardware synthesis.
Execute this when the user requests code context for a repository or library using DeepWiki, Context7, Exa, and/or git clone. — from TuYv/ccpm
Create a new Freezed model with JSON serialization. Use when adding new data models.
Design en implementeer frontend UI voor dit project. Volgt het Mariage Bruidsmode design system (kleuren, typografie, componenten).
Convert visual input (screenshots, Figma exports, URLs, inspiration images) into working pages or components.
Tư duy typography frontend dùng chung: hierarchy rõ, chữ ngắn có ích, font scale tinh tế, metadata vừa đủ và mobile không quá to.
Use for landing pages, websites, apps, and UI where visual composition and structure are the primary concern.
Verify a running frontend with explicit visual claims, viewports, and screenshot evidence using the frontend-visualqa MCP server or CLI.
Fully automated end-to-end demo of the team-tile bootstrap pattern — zero user args, runs all 12 steps front-to-back, auto-cleans up at the end.
End-to-end Figma-to-code pipeline. Runs plan-design then build-design in one command with no user interaction. Use when invoking "/full-build".
Run all 36 agents across 9 categories in 4 phases — complete codebase audit with orchestration, Observer Agent, and token management.
Interactief een GitHub issue opstellen volgens een vast 5-secties template (probleem, voorbeelden, bevindingen, potentiële oplossing, tests).
Design the GA4 event catalogue — map events to conversions, define custom dimensions/metrics, and verify via DebugView.
Display project-config.yaml read-only — top-level section TOC (default), a single named section, or the full byte-verbatim file (--full).
Walk through a complete GAIA benchmark→submit flow — from key resolution through HAL-compatible package generation
Scan in-progress and completed story files for development findings and triage each into a new backlog story, an existing story, or dismiss.
Full story validation with factual verification via Val subagent. Dispatches the validator via the main-turn Agent tool and records the outcome via review-gate.sh using canonical…
Understand the online game rules, lobby lifecycle, round boss permissions, card JSON format, variant-specific extensions, and where gameplay copy must stay in sync.
Universal AI game-boost platform. Daily check-ins, BBS forum tasks, gift codes, real-time game state (resin/stamina/battery), and natural-language task planning across 10+ games…
Gap analysis tra documentazione interna (informativa, registro, policy) e requisiti richiesti dall'utente o da nuovo trattamento. Nessuna consulenza legale.
Analyze a Solidity contract for gas optimization opportunities. Identifies savings with specific techniques, gas numbers, and before/after code. Covers L1 and L2 considerations.
Mine Claude Code session logs for bash commands getting incorrect permission decisions. Find read-only commands that return "ask" when they should be "allow", unknown commands…