Use when relay fragment composition, data masking, colocation, and container patterns for React applications.
Pressure relief system design skill for PSV sizing, flare header analysis, and overpressure protection
Browse entities in the Remnic knowledge graph and surface their facts and relationships. Trigger phrases include "tell me about the entity", "look up", "what do we know about".
Shared memory workflow for Claude Code agents connected to Remnic — recall before acting, observe during work, remember at the end.
Search Remnic memories by natural-language query. Trigger phrases include "what do you remember about", "recall anything on", "have we discussed".
Store a durable memory in Remnic so every connected agent can recall it. Trigger phrases include "remember this", "save this for later", "add a note that".
Run a deep full-text search across every Remnic memory. Trigger phrases include "search memories for", "find anything about", "deep search".
Remove metadata from one or multiple PDFs by uploading them to the Solutions API, polling until completion, then returning download URL(s) for the cleaned PDF(s) (or a ZIP if…
Removes a pinned audit reference from this repository. Use when the user explicitly asks to remove, delete, or retire an audit reference.
Remove a GSD workspace and clean up worktrees — from general/general-misc
Rename a loop and update all references in YAMLs, tests, and docs.
Expert skill for building interactive REPLs with rich editing and evaluation features
Analyze external repositories for adoptable ideas and patterns.
The question isn't whether we CAN simulate people. It's how we do it with dignity.
Specialized skill for analyzing and scoring requirements quality against BABOK and IEEE 29148 standards
Design control traceability skill for managing user needs, design inputs, design outputs, and verification/validation linkages
Batch-resize images for web (WebP at 1920/1200/400px), social (center-cropped WebP at Instagram square/portrait, Twitter/X, LinkedIn), slides (center-cropped JPEG at 1024×768 and…
Systematic ambiguity resolution through tiered information gathering. Use when facing unclear requirements, unknown context, uncertain implementation choices, or any situation…
Optimize resource allocation to eliminate overallocation while minimizing schedule impact
Resource scheduling and assignment optimization skill for personnel and equipment allocation
Generate responsive image sets with srcset, WebP/AVIF conversion, and art direction
Responsive design with Container Queries, fluid typography, cqi/cqb units, subgrid, intrinsic layouts, foldable devices, and mobile-first patterns for React applications.
Intelligent resume parsing and candidate screening with bias-reduction capabilities
Reconstruct working context at the start of a new session. Reads STATE.md + HANDOFF.md (if present) + latest 3 T##-SUMMARY.md files and synthesizes a 'where we are' briefing.
Expert-level retail systems, POS, inventory management, e-commerce, customer analytics, and omnichannel retail
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking.
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking.
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking.
Retrospectiva semanal dos projetos Luna. Analisa commits, jobs agendados, servicos ativos, e pendencias de todos os projetos do Rogerio. Responde em portugues (pt-BR).
Automated return authorization and routing skill optimizing return paths and customer experience
AI-powered returns inspection and disposition decision skill maximizing value recovery
ASC 606 five-step model implementation skill for revenue recognition analysis and documentation
Review PR for release note quality and doc impact. Gates communication before merge.
Review phase of the review-fix loop. Runs vibe:review and normalizes findings into the review-fix ledger.
Runs vibe:work for review-fix tasks until the current batch is complete, then syncs .plan/TASKS.md status back to the review-fix ledger.
Analyze audio files to extract musical features (BPM, key, chords, timbre, dynamics) and generate structured reviews with HMT taxonomy mapping for Horus persona.
Reviewer para Axé Hub — audita backend, frontend e specs contra os padrões do projeto
Reviews AWS cost optimization findings for accuracy, validates recommendations, and filters false positives using confidence-based scoring.
Probability distribution fitting skill for calibrating uncertainty models from historical data or expert judgment
Build and maintain project and change risk registers with scoring, mitigation strategies, and tracking
Risk register management skill for systematic risk identification, assessment, and tracking
A unified interface for annotating single-cell RNA-seq data using Marker Genes, Deep Learning (CellTypist), or LLMs.
AI-powered RNA velocity analysis for predicting cellular state transitions, differentiation trajectories, and dynamic gene regulation from single-cell RNA sequencing data.
Constructive critique via 5 HackerNews personas with claim validation.
Durchleuchtet eine Android-App systematisch wie ein Roentgengeraet — extrahiert ALLE Funktionen, Bildschirme, Klick-Pfade, Paywall-Stufen und Hidden Features aus dem Quellcode,…
Mudar para papel especialista. Ativa com "mudar papel", "como especialista em segurança", "como arquiteto".
Debate multi-rol para explorar compromisos. Se activa con "debatir entre roles", "explorar compromisos".
Adversarial review coach for root cause analysis. Reviews reports with fresh eyes, runs verification commands to spot-check evidence claims, pushes hard on depth and rigor.
Use when running /rune:appraise or /rune:audit, when spawning multiple review agents, when TOME aggregation fails or produces malformed output, or when a TeammateIdle hook fires…
Analyze an enriched note and route to the best vault destination. Stage 3 of the processing pipeline.
Pick the right LLM for CONTRACT DRAFTING — generating, redlining, or rewriting contract language from instructions.
Pick the right LLM for CONTRACT REVIEW — reviewing an existing agreement for risk, deviations from standard, missing protections, and internal contradictions, and proposing…
Pick the right LLM for LEGAL INFO EXTRACTION — pulling facts, clauses, dates, parties, obligations, and structured fields out of contracts and legal documents.
AI-powered route planning and optimization skill using advanced algorithms (VRP, TSP) to minimize transportation costs, reduce delivery times, and maximize vehicle utilization
Classify a non-Reflex request and select which workflow handles it — the sole workflow classifier. Selects by judgment, never a keyword table; emits selected | ambiguous |…
失敗した週次収集回の原因を調べ、小さく直せるものだけを直す手順。GitHub Actions の self-hosted runner から claude -p の引数として起動される。直せないときは診断だけを書いて終える。
Triage complet RTK : exécute issue-triage + pr-triage en parallèle, puis croise les données pour détecter doubles couvertures, trous sécurité, P0 sans PR, et conflits internes.
Iterative rubric-based evaluation and self-improvement loop. Builds a scoring rubric interactively, evaluates an artifact with multiple models in parallel (Codex, Gemini, Claude),…
Execute plan tasks via fresh-context subagents (swarm mode)
Use when agents need to read or write project memory, when persisting learnings from reviews or audits, when managing echo lifecycle (prune, reset), when a user wants to remember…