Socratic deep interview with mathematical ambiguity gating before autonomous execution
Score 80/100
Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks, distributing workload, or orchestrating multi-agent workflows.
Score 80/100
DeliveryManager — Commit + push + PR con convenciones Intrale en un solo comando
Score 80/100
Render and deploy documents to output directory for hosting. Supports Quarto slides and Typst PDFs.
Score 80/100
Продуктовое описание в 1 абзац: что было сделано или что предстоит сделать. Без технических деталей — понятно менеджеру, заказчику, стейкхолдеру.
Score 80/100
Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML…
Score 80/100
Proposes a database schema (SQL or NoSQL) for a given domain. Use when the user asks to "design a database", "model data for X", "build an ER", pick SQL vs NoSQL, or invokes…
Score 80/100
Analyze and iteratively refine website design until it meets professional standards
Score 80/100
Determine whether a specific pattern, entity, or condition exists in the given data. Use when searching for patterns, checking existence, validating presence, or finding signals.
Score 80/100
Analyze text to detect if it was written by AI. Returns a score from 0-100 with detailed metrics. Use when checking content before publishing or submitting.
Score 80/100
Use when adding a new UI component to an existing module - handles templates, inputs, and test scaffolding.
Score 80/100
Use when adding server state management or shared logic - creates an auto-imported composable with useFetch/useAsyncData.
Score 80/100
Use when adding a signal-based store or utility service - creates injectable with inject() and Angular Signals.
Score 80/100
Use when creating a new feature module with all layers - service, adapter, types, state, components, and tests.
Score 80/100
Use when adding API integration to a module - creates types, contracts, adapter, and service layer.
Score 80/100
Use when a module needs test coverage - creates tests for adapters, services, and components.
Score 80/100
Generate dev server lifecycle scripts (start/stop/status/ports) from detected project structure
Score 80/100
Generate a daily or weekly digest of activity across all connected sources. Use when catching up after time away, starting the day and wanting a summary of mentions and action…
Score 80/100
Build a rigorous world model with state, dynamics, uncertainty, and provenance. Use when creating digital twins, constructing system representations, building simulation…
Score 80/100
Run the digital twin sync loop to synchronize real-world signals with a digital model. Use when updating digital twins, detecting drift, managing real-time state synchronization,…
Score 80/100
Adaptive design interview — spawns design-discussant to gather decisions via one-question-at-a-time questioning. Writes D-XX decisions to STATE.md block.
Score 80/100
Use this skill when gathering phase context through adaptive questioning before planning, clarifying implementation decisions, or exploring gray areas for a phase.
Score 80/100
Step 8 of the forge workflow when the approved plan has ≥ 2 steps marked `Parallel-friendly: yes`. Dispatches one `forge-implementer` subagent per such step, each in an isolated…
Score 80/100
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
Score 80/100
Use when executing a plan document to ship a feature. Triggered by 'build this', 'execute the plan', 'implement the plan', or any request to run/ship a plan.
Score 80/100
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
Score 80/100
Use when sending a spoken debrief to a Telegram chat. Collects context, drafts a 30-second executive brief, synthesizes it via TTS, and delivers it as a native voice message.
Score 80/100
Use when deploying merged changes to production across all bridge machines. Triggered by 'deploy to prod', 'ship it', 'push to prod', or 'do-deploy'.
Score 80/100
Discover happy paths on a target site using agent-browser, producing structured trace JSON for deterministic test generation.
Score 80/100
Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection, quality-focused prompting, and meta-judge → LLM-as-a-judge…
Score 80/100
Execute complex tasks through sequential sub-agent orchestration with intelligent model selection, meta-judge → LLM-as-a-judge verification
Score 80/100
Audit how well a named feature is integrated into its host project. Checks for orphan code, dead wiring, missing tests, undocumented entry points, config gaps, and partial…
Score 80/100
Use when reviewing a plan before build. Spawns parallel war-room critics (Skeptic, Operator, Archaeologist, Adversary, Simplifier, User) plus automated structural checks.
Score 80/100
Audit all Claude Code skills for compliance with canonical template standards. Use when checking skill quality, validating skill structure, linting SKILL.md files, verifying…
Score 80/100
Code documentation agent — write/update docs with /docs write, check status with /docs check. Minimal code blocks, reference pointer based.
Score 80/100
Use when onboarding onto a module and need a quick summary of its structure, patterns, and key files.
Score 80/100
Create E2E tests with screenshots and build step-by-step documentation for the public website
Score 80/100
Summarize the current agent session, create an Obsidian note for it, and link it from today's daily note.
Score 80/100
Draft an offer letter with comp details and terms. Use when a candidate is ready for an offer, assembling a total comp package (base, equity, signing bonus), writing the offer…
Score 80/100
Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering…
Score 80/100
Nightly memory consolidation — prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md index.
Score 80/100
Управление вайб-код проектами. Протокол .drift/ для трекинга статуса, прогресса, заметок и целей по всем проектам.
Score 80/100
Internal development tool that tests whether skill descriptions trigger correctly for different user inputs.
Score 80/100
This skill should be used when the user asks to "compose DSPy modules", "use Ensemble optimizer", "combine multiple programs", "use dspy.MultiChainComparison", mentions "ensemble…
Score 80/100
This skill should be used when the user asks to "bootstrap few-shot examples", "generate demonstrations", "use BootstrapFewShot", "optimize with limited data", "create training…
Score 80/100
This skill should be used when the user asks to "evaluate a DSPy program", "test my DSPy module", "measure performance", "create evaluation metrics", "use answer_exact_match or…
Score 80/100
This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inference…
Score 80/100
This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mentions "GEPA…
Score 80/100
This skill should be used when the user asks to "integrate DSPy with Haystack", "optimize Haystack prompts using DSPy", "use DSPy to improve Haystack pipeline", mentions "Haystack…
Score 80/100
This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimization",…
Score 80/100
This skill should be used when the user asks to "refine DSPy outputs", "enforce constraints", "use dspy.Refine", "select best output", "use dspy.BestOfN", mentions "output…
Score 80/100
This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions…
Score 80/100
This skill should be used when the user asks to "create a DSPy signature", "define inputs and outputs", "design a signature", "use InputField or OutputField", "add type hints to…
Score 80/100
Calculate customs duties, taxes, MPF, HMF, and landed cost for imports using AskRosetta. Use when a user needs duty rates, tariff calculations, or total landed cost.
Score 80/100
Migrate existing repositories to use Personal GitHub Ecosystem templates and patterns. USE THIS SKILL when user says "migrate to ecosystem", "adopt templates", "convert workflow",…
Score 80/100
Run line-level editing across chapters. Catches spelling, grammar, awkward phrasing, and word echoes.
Score 80/100
Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD.
Score 80/100
Write detailed embodiment descriptions for patent specifications. Use when user says \"撰写实施例\", \"write embodiment\", \"实施例描述\", \"detailed description\", or wants to describe how…
Score 80/100
Manage participant relationships - thank-yous, updates, re-engagement, and advocacy asks
Score 80/100
Instant lead enrichment. Drop a name, company, LinkedIn URL, or email and get the full contact card with email, phone, title, company intel, and next actions.
Score 80/100