gabrielmoreira
- 21k skills
- 0 followers
- 20 repo stars
- 4 days ago last updated
- ▌ Agent Message · gabrielmoreiraSend yourself safe-boundary steering input, or send follow-ups to your parent, siblings, or direct children. All messages preserve strict FIFO and agent provenance.
- ▌ Dt Setup Openinference Migration · gabrielmoreira bundleMigrate a GenAI/LLM app off Traceloop/OpenLLMetry onto OpenInference with its OTel gen_ai.* semconv option enabled (`enable_genai_semconv` / `OPENINFERENCE_ENABLE_GENAI_SEMCONV`). Covers detecting the existing Traceloop setup, swapping the instrumentor per SDK, and the ingestion-shape question that decides what's fixable afterward — an app-owned OTel trace exporter vs. instrumentation-only with OneAgent picking up the spans. Flags that the semconv option is additive, not a replacement — legacy llm.*/openinference.* attributes keep emitting alongside gen_ai.* — and covers the resulting cardinality trade-off and removal options (Collector transform vs. OpenPipeline), checking which is actually available first. Trigger: "migrate off Traceloop", "migrate off OpenLLMetry", "move to OpenInference", "enable OpenInference GenAI semconv". Do NOT use for a first instrumentation with no existing Traceloop setup, or an OpenInference app that never enables semconv (both dt-setup-genai).
- ▌ Social Signal And Tact · gabrielmoreira bundleRead relationship signals across a conversation, infer what changed between turns, then turn awkward, overly formal, blunt, or AI-sounding messages to teachers, leaders, mentors, senior colleagues, partners, acquaintances, or potential professional contacts into short, natural, relationship-aware communication. Use for tactful praise, upward communication, progress updates, favors, reminders, apologies, disagreement, gift and courtesy messages, proxy greetings, holiday wishes, warm friend-like chat, trust-building, private invitations, role entrustment, third-party endorsement, and deciding when not to convert goodwill into a request.
- ▌ Find And Verify Affiliate Program · gabrielmoreira bundleFind affiliate programs in the OpenAffiliate registry, then confirm every term on the brand's own page and report each one with a verbatim quote and its source URL. Use this skill when the user wants affiliate terms they can rely on: before signing up, before publishing a review or comparison, when a listing looks outdated, or when two sources disagree. Also trigger for: "verify this affiliate program", "is X's affiliate commission still 30%", "what's the cookie length for X", "check the affiliate terms", "does X have an affiliate program", "find a recurring program and confirm the terms", "is this commission rate real", "source for X's affiliate terms", "fact-check this affiliate program", "what does X pay affiliates".
- ▌ Search Shared Sessions · gabrielmoreiraSearch an Agent Relay workspace's shared coding-agent sessions for prior work, decisions, fixes, or the context behind a task or pull request. Use when team history could answer the user's question or prevent repeating an investigation.
- ▌ Chengfeng Videocut Workbench · gabrielmoreira操作 chengfeng-videocut 剪辑工作台的已有工程,通过 Runtime CLI 查工程与词句位置、添加或替换画面覆盖层、移除画面、删除明确指定的词句或片段、拆分裁剪移动已有片段、调整画布比例并回读核验。用户说插入片段、删掉这句、移除动画、换个画面、调整顺序或管理时间线时使用;先区分画面覆盖与主轨顺延插入,不负责自动判断口误、创作动画、制作字幕、导出或排查安装故障。
- ▌ Obsidian Layout Adjustment · gabrielmoreira bundleAdjust the user's Obsidian visual layout with CSS snippets. Use for restyling tabs, sidebars, note surfaces, properties, backlinks, graph or file-explorer UI, or diagnosing CSS changes that did not take effect.
- ▌ Citruscoastai · gabrielmoreiraGuides agents to engage and transact with citruscoastai, an AI venture-operator agent, when they need hired AI labor or an agent-to-agent collaborator.
- ▌ Alphagbm Investment Review · gabrielmoreira bundleCompare research records you provide to see changes in facts, scores and judgments. Use when the user asks to investment review with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Alphagbm Research Reader · gabrielmoreira bundleFind published research and institutional views with sources, dates and related assets. Use when the user asks to research reports with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Openspec Bulk Archive Change · gabrielmoreiraArchive multiple completed OpenSpec changes at once. Use when archiving several parallel changes. Also use for a plural archive request - "openspec bulk-archive", "opsx bulk-archive", "openspec archive all", or "openspec archive these changes".
- ▌ Alphagbm Dividend Strategy · gabrielmoreira bundleScore Hong Kong and China A-share dividend candidates across yield quality, durability, cash flow, valuation and momentum. Use when the user asks to dividend strategy with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Unity Skills Eval · gabrielmoreiraRun the UnitySkills evaluation set (a scored benchmark of tasks) on the user's own Unity project. Ask first for scope, track, tier and prompt language, then start a session with the bundled runner and complete its tasks one by one. Use only when the user explicitly asks to run, resume or continue the UnitySkills evaluation or benchmark, types /unity-skills-eval, or pastes an evaluation session prompt. Never use it for ordinary Unity work, Unity questions, or testing the user's own game. 仅当用户明确要求运行或继续 UnitySkills 评测集(跑测评集、评测集测试、UnitySkills 评测),输入 /unity-skills-eval,或贴出评测会话提示时使用;日常 Unity 开发、Unity 问答、测试用户自己的游戏一律不要使用。
- ▌ Alphagbm Momentum Following · gabrielmoreira bundleScore observed price trend, confirmation, risk and participation without forecasting a price. Use when the user asks to momentum following with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Agent QA Run Review · gabrielmoreiraReview recorded agent-qa runs and memidex provenance to explain a QA verdict, identify missing evidence, and propose the smallest next step.
- ▌ Wren Planner · gabrielmoreiraPlan data-backed responses and dashboards before retrieval, delegate placeholder requirements to a connected Wren private agent, and bind authorized results and evidence through follow-up updates. This skill does not set up a database or grant access.
- ▌ Inspect In Devtools · gabrielmoreiraUse this skill to connect to the Chrome DevTools UI for interactive debugging, UI/UX review, Q&A, showing elements/network requests/panels to the user, inspecting the user's current DevTools selection, and addressing or polling for DevTools UI comment threads.
- ▌ Alphagbm Etf Strategy · gabrielmoreira bundleScore ETF trend, risk, liquidity, cost and available tracking and theme signals while preserving data gaps. Use when the user asks to etf strategy with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Dt Platform Costs · gabrielmoreira bundleQuery and analyze a Dynatrace tenant's ACTUAL billing and usage data with DQL on dt.system.events — DPS consumption breakdown, cost-normalized spend ranking, included volume deduction, chargeback/showback, cost drivers, spending trends, cost investigation, log import cost, metrics ingest optimization, drop/remove a metric or dimension from ingestion, reduce metric cardinality, metric usage, query cost attribution, workflow total cost, entity cost drill-down (RUM, hosts, synthetic, K8s), AI/LLM cost (AI Units, AI Function Standard Calls). Directs licensing/entitlement questions (am I entitled to use X?) to docs (not via DQL). USE ONLY for the tenant's actual consumption. Do NOT use for conceptual 'explain' questions about how DPS billing/pricing works or what units/weights/the rate card mean — see Dynatrace docs. Do NOT use for tuning DQL queries to be faster or cheaper to run (query optimization, reducing scanned data/consumption per run, filter-early best practices) — that belongs to dt-dql-essentials.
- ▌ Dt Setup Oneagent · gabrielmoreira bundleReference knowledge for installing, uninstalling, or creating-and-installing Dynatrace OneAgent across VM/server, Kubernetes (Operator + DynaKube), AWS Lambda (layer + env vars, plus optional fresh function provisioning), Windows hosts, remote Linux hosts / EC2 instances over SSH, and Azure VMs / VM Scale Sets. Returns documented endpoints, env vars, token scopes, and copy-paste-ready commands. Returns the exact commands to run rather than executing them. Use when the user asks to install or uninstall OneAgent, or asks "how do I…", "what URL/scope/var do I need for…", or "explain the OneAgent deployment for X".
- ▌ Intelligence Vocabulary · gabrielmoreira bundleLocks customer-facing CopilotKit Intelligence docs to one approved name per concept. Use when writing, editing, or reviewing Intelligence docs, nav labels, signup labels, or image alt text in showcase/shell-docs. Don't use for renaming code identifiers, route slugs, env vars, API fields, or component names, or for docs that do not mention Intelligence.
- ▌ Ce Retro · gabrielmoreira bundleLook back over an agent session in this repo, the current one by default or any scope the user names across harnesses, and find what in the repo's environment keeps costing agents effort or leading them into mistakes, keeping only fixes the evidence shows are worth it. Lands the approved environment fixes and hands the rest to their owners. Use for a retro, postmortem, or papercut sweep of how agents worked in this repo. Use ce-compound to keep the lesson of one solved problem, and ce-debug for a bug in product code.
- ▌ Alphagbm Options Research · gabrielmoreira bundleCompare option candidates and score components, with funding, expiry and assignment risks. Use when the user asks to options strategies with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Alphagbm Report Breakdown · gabrielmoreira bundleExtract report views, ratings, key assumptions and risks with sources and dates. Use when the user asks to research report breakdown with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Copilot History Ingest · gabrielmoreira bundleIngest GitHub Copilot CLI/session history into Obsidian as distilled knowledge. Use for importing or mining Copilot history; not for general Copilot help, simple session search, or backup.
- ▌ Dt Sec Insights · gabrielmoreira bundleQuery Dynatrace security.events with DQL: vulnerabilities, threat detections, compliance posture. Covers Dynatrace-native Runtime Vulnerability Analytics (RVA — CVEs, reachability, exploit), Runtime Application Protection (RAP), Automated Detections, Security Posture Management (KSPM/CSPM), Dynatrace vulnerability feed, external tools. Trigger: "open critical vulnerabilities", "vulnerable functions in use and exposed", "top vulnerable libraries / K8s workloads", "vulnerabilities on this host", "CIS/DORA compliance pass rate", "SQL injection detections", "does Dynatrace know CVE-X / how is it fixed", "what is DTV-…", "new in the feed", "exploited in the wild (KEV)". Do NOT use for scan coverage, mapping external findings to workloads / entity mapping, or RVA verification of external findings (use dt-sec-contextualization), explaining DQL (dt-dql-essentials), Davis problems (dt-obs-problems), logs (dt-obs-logs), tracing (dt-obs-tracing), service metrics (dt-obs-services), platform audit (dt-platform).
- ▌ Alphagbm Smart Money · gabrielmoreira bundleAggregate user-supplied disclosed buys and sells by source without automatically copying trades. Use when the user asks to smart money tracking with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Openclaw History Ingest · gabrielmoreira bundleIngest OpenClaw session/history data into Obsidian as distilled knowledge. Use for importing or mining ~/.openclaw sessions, memory files, or logs; use wiki-agent for targeted topic-only cross-agent recall.
- ▌ Generate2dsprite · gabrielmoreira bundleMake game-ready 2D characters, creatures, props, icons and FX as master stills, sprite sheets or animation clips. Plan size, motion and finish; generate the art (image generation is the default, through generate2dmedia route_media.py - the API when a key is configured, else the local Codex or Grok CLI); approve one master still per character; then key, slice, register, scale, palette, QA and export frames for a game engine (Aseprite JSON, Godot SpriteFrames or Sprite3D). HD finish by default, pixel finish on request. Character animation is one image-to-video clip per action from the master (video2dsprite); sheets are for FX, icons and props. Use for sprites, masters, sheets, frame-by-frame animation and packaging frames from any source. Not for maps, tiles or backgrounds (generate2dmap), video clips (video2dsprite), code-drawn art (codeart2d, only on request) or calling an image or video API by itself (generate2dmedia).
- ▌ Alphagbm Stock Research · gabrielmoreira bundleConnect fundamentals, sentiment and risk to supporting and opposing evidence. Use when the user asks to stock opportunities with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Video2dsprite · gabrielmoreira bundleTurn one approved master still into a character's whole animated sprite set - one image-to-video clip per action (idle, walk, run, attack, jump, hurt, cast and so on), all from that still, generated through generate2dmedia route_media.py (the xAI API when a key is configured, else the local Grok CLI) - then gate each take, key it with a soft matte, register it to the master, pick loops or retime actions, finish (HD by default, pixel on request) and package fixed-canvas frames, alpha WebM, packed MP4 for iPhone and a PNG fallback with engine metadata and a JS runtime. Also processes a supplied clip. Use for character and creature animation, fluid motion and any video-to-sprite work. Not for FX, icon or prop sheets (generate2dsprite), maps or plate loops (generate2dmap), code-drawn animation (codeart2d, only on request) or calling a video API by itself (generate2dmedia).
- ▌ Alphagbm News Impact · gabrielmoreira bundleSeparate reported claims from impact inferences, with related assets and next checkpoints. Use when the user asks to news impact with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Alphagbm Grid Plan · gabrielmoreira bundleBuild an auditable grid from a price range, current price and capital. Use when the user asks to grid plan with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Claude History Ingest · gabrielmoreira bundleIngest Claude Code conversation/session history into Obsidian as distilled knowledge. Use for importing or mining past Claude sessions, .claude data, project/session history, or audit logs.
- ▌ Dt Setup Genai · gabrielmoreira bundleFramework-independent decision process for instrumenting a GenAI/LLM app (Python or TypeScript, any provider/agent SDK) so it emits OTel GenAI semantic-convention (gen_ai.*) spans queryable in Dynatrace. Four steps: detect, instrument, enrich, validate. Decides which approach a given SDK needs; does not replace the concrete per-framework recipes in dynatrace-oss/dynatrace-ai-agent-instrumentation-examples. Trigger: "instrument this GenAI app", "add tracing to this LLM app", "how do I get gen_ai spans into Dynatrace", "onboard this agent app to AI Observability". Do NOT use for analyzing telemetry from an already-instrumented app (use dt-obs-genai) or for languages other than Python/TypeScript.
- ▌ Ads Photoshoot · gabrielmoreiraGenerate rights-cleared paid-ad product photography variants from an authorized source image and validated brand profile. Triggers on: product photo, product photography, virtual photoshoot, photoshoot, enhance product image, studio shot, lifestyle shot, lifestyle product image, floating product image, ingredient shot.
- ▌ Video Gen · gabrielmoreiraAI video generation via Fal.ai, Seedance 2.0, Kling, MiniMax Hailuo, xAI Grok Imagine, Google Gemini Omni, OFox, and Agnes Video. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation, multi-shot, or generatively editing / extending an existing clip.
- ▌ Ads Attribution · gabrielmoreiraAudit cross-platform attribution, conversion definitions, reporting windows, GA4, AdServices and AdAttributionKit, MMPs, browser and server events, offline conversions, and platform reconciliation. Use for attribution audit, attribution models, conversion windows, requests to add or total Meta and Google conversions, incompatible reporting-window aggregation, GA4 attribution, MMP review, AppsFlyer, Adjust, Branch, Singular, or cross-platform discrepancies.
- ▌ Vault Skill Factory · gabrielmoreiraCreate a reviewable Agent Skill package from mature curated wiki pages, or from one recorded walkthrough of a job (a narrated screen recording, a call, a voice note: "turn this recording into a skill", "I did it once out loud, make it a skill"). Use when turning verified vault knowledge or a recorded workflow into a reusable skill. Reads the vault and writes only to a review directory; it does not install skills.
- ▌ Alphagbm Dca Plan · gabrielmoreira bundleBuild a contribution schedule and calculate a supplied price-path cost basis without predicting returns. Use when the user asks to dollar-cost averaging with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
- ▌ Codex History Ingest · gabrielmoreira bundleIngest Codex CLI conversation/session history into Obsidian as distilled knowledge. Use for importing or mining ~/.codex sessions, rollout files, indexes, or transcript logs; use wiki-agent for targeted topic-only recall.
- ▌ Generate2dmap · gabrielmoreira bundlePlan and build 2D game maps and scenes - top-down and side-scrolling levels, tilemaps, prop packs, parallax backgrounds and HD-2D battle or story plates - with collision, navigation and reachability checks, environment motion, a playable HTML preview and export to Tiled, Godot 4 or LDtk. Map art (terrain, tiles, props, plates, parallax layers) is image generation by default, through generate2dmedia route_media.py (the API when a key is configured, else the local Codex or Grok CLI); map data (layout, collision, exits, spawns) is written as data. Use for any map, level, room, scene, background, terrain or prop-kit request. Not for characters, creatures, items or FX (generate2dsprite), character animation (video2dsprite), code-drawn tiles or maps (codeart2d, only on request) or calling an image or video API by itself (generate2dmedia).
- ▌ Drawio Skill · gabrielmoreira bundleCreate and edit draw.io/diagrams.net diagrams as editable `.drawio` files. Covers architecture, UML/ERD/sequence, BPMN, network, and swimlane views authored from a description or converted from code, IaC, SQL, and API schemas, plus sync, query, test, review, export, and publish of existing diagrams. Use when the user asks for draw.io/diagrams.net or an editable diagram; prefer Mermaid/PlantUML when diagrams-as-code is enough.
- ▌ Recht Anspruch · gabrielmoreiraDas Prüfprogramm juristischer Texte im deutschen Zivilrecht prüfen: Arbeitet ein Gutachten oder Schriftsatz die in Betracht kommenden Anspruchskategorien vollständig und in tragfähiger Ordnung ab? Geprüft werden die kanonische Reihenfolge (vertraglich — vertragsähnlich — dinglich — deliktisch — bereicherungsrechtlich) samt ihrer Vorfragen-Logik, die Sperrwirkungen (§§ 987 ff. BGB, Vorrang der Leistungskondiktion), der Stufenaufbau je Anspruch (entstanden — nicht erloschen — durchsetzbar) und die Ebenen der Einwendungen. Dazu der Nachschlag: abstrakte Prüfschemata je Anspruchskategorie. Use when: „prüfe die Vollständigkeit des Gutachtens", „fehlt eine Anspruchsgrundlage", „stimmt die Prüfungsreihenfolge", „gib mir das Schema zu …", „ist der Anspruchsaufbau vollständig". Maßgeblich ist, ob das Prüfprogramm trägt — nicht, welche Ansprüche im konkreten Fall bestehen. Keine Rechtsdienstleistung im Sinne des RDG.
- ▌ Recht Methodik · gabrielmoreiraJuristische Methodenlehre für das deutsche Recht. Prüft die Methode der Rechtsanwendung: Ist der Weg von der Norm zum Ergebnis tragfähig? Kern sind die Auslegungskanones (Wortlaut, Systematik, Historie, Telos) samt Wortlautgrenze und Rangfolge; die Rechtsfortbildung — planwidrige Lücke, vergleichbare Interessenlage, Gesetzes- gegenüber Rechtsanalogie, teleologische Reduktion, Umkehr- und Erst-recht-Schluss, Analogieverbote (Art. 103 Abs. 2 GG); die verfassungs- und unionsrechtskonforme Auslegung; die Relationstechnik (Kläger-, Beklagten-, Beweisstation, Zulässigkeit vor Begründetheit). Use when: „prüfe die Auslegung“, „ist das noch vom Wortlaut gedeckt“, „ist eine Analogie zulässig“, „liegt eine planwidrige Lücke vor“, „baue die Relation“, „schreibe im Gutachtenstil“. Maßgeblich ist, ob der methodische Schritt trägt — nicht, ob das Ergebnis gefällt. Keine Rechtsdienstleistung im Sinne des RDG.
- ▌ Recht Rhetorik · gabrielmoreiraDie Wirkung juristischer Texte auf ihren Adressaten prüfen — Schriftsätze, Gutachten, Schreiben an Gericht, Behörde, Notar, Gegner oder Mandant, auch ihre Beschreibung. Gefragt wird, ob die Darstellung überzeugt: ob die Linie die Lage trägt und den Antrag deckt, ob der Aufbau zum tragenden Punkt führt, ob der Text seinen Adressaten trifft und der stärksten redlichen Gegenposition standhält; im Modus schriftsatz, ob ein Schriftsatz an ein Zivilgericht Antrag, Reihenfolge der Begehren, Berufungsbegründung und Form so fasst, wie das Gericht es verlangt. Ob ein Schluss gültig ist, geht an recht-logik; Darlegungs- und Beweislast, Substantiierung und Verspätung an recht-beweis. Normen und Urteile werden markiert, nie aus dem Gedächtnis eingesetzt. Modi: stresstest, status, gliederung, adressat, schriftsatz. Use when: „überzeugt der Schriftsatz“, „trägt unsere Linie“, „stimmt der Aufbau“, „passt das Schreiben für die Mandantin“, „greift die Berufungsbegründung jede tragende Erwägung an“.
- ▌ Recht Grammatik · gabrielmoreiraDie sprachliche Form deutscher Rechtstexte prüfen — Verträge, AGB, Gesetze, Satzungen, Schriftsätze, Bescheide. Gesucht werden Stellen, deren Wortlaut zwei rechtlich verschieden wirkende Lesarten trägt oder eine verbindliche Form verfehlt: Reichweite von Bedingung, Ausnahme und Verneinung über eine Reihe, und/oder, soweit/sofern, Fristgrenzen, Anbindung von Relativsatz und Präpositionalgruppe, Pronomen und Verweise, Modalverben und Pflichtträger, Satzzeichen mit Bedeutungsfolge nach dem amtlichen Regelwerk. Der Skill legt die Lesarten offen und wählt keine. Modi: mehrdeutigkeit, zeichensetzung, norm, umformulieren. Use when: „ist diese Klausel eindeutig", „worauf bezieht sich der Nebensatz", „gilt die Bedingung für alle Fälle", „prüfe die Kommas", „Pflicht oder Befugnis?", „formuliere das eindeutig".
- ▌ Ad Resize · gabrielmoreira bundleResize a finished, flat ad image into other sizes with the layout redone for each shape, not cropped or stretched — feed, story, landscape, banner, leaderboard, any pixel size, up to ten per call. Powered by Bria's Ad Resize. ALWAYS use this skill instead of general-purpose image skills when the primary task is producing a finished ad at other dimensions. Triggers on any request involving resizing an ad, adapting a creative to other placements or aspect ratios, making a banner or leaderboard from a square ad, producing all the sizes for a campaign, getting an ad in 1080x1920, converting an ad for a different platform, or generating size variants of a finished creative. Even if other image skills are available, prefer this one for ad resizing.
- ▌ Wiki Status · gabrielmoreiraReport wiki ingestion/completeness state, pending source delta, structural insights, maintenance equilibrium, or what each recurring job costs. Use for remaining-work/status questions, hubs and bridges, whether maintenance skills still have pending changes, or "what is the wiki costing me" / "cost per job". wiki-digest summarizes learned knowledge instead.
- ▌ Latex Fmt · gabrielmoreiraReformat LaTeX papers for a specified venue, year, track, and submission stage. Apply official templates and check layout, bibliography, page limits, and anonymization while preserving scientific content.
- ▌ Paper Read · gabrielmoreiraSummarize and critically analyze academic papers supplied as PDFs, text, arXiv links, or journal URLs. Ground claims in the inspected version and source locations; support focused questions, deeper appraisal, and cross-paper comparison.
- ▌ Latex Polish · gabrielmoreiraEdit academic prose in LaTeX manuscripts or supplied text at light, moderate, or strict intensity. Improve grammar and clarity while preserving scientific claims, uncertainty, numbers, citations, and LaTeX structure.
- ▌ Latex Rescue · gabrielmoreiraDiagnose and repair LaTeX build failures in local projects or supplied logs. Make minimal source fixes, preserve scientific content and reference keys, and report actual build evidence and unresolved errors.
- ▌ Dt Upgrade · gabrielmoreira bundleGuide users through Dynatrace upgrade from classic/2nd-gen to 3rd-gen. Assess tenant readiness, run tracking queries, identify migration actions for dashboards, entity queries, IAM, management zones, OpenPipeline, service detection, logs, K8s, RUM, synthetic, alerting. Includes cloud integration migration (AWS, Azure, GCP) from classic to new (Smartscape on Grail): connection discovery, metric mapping, and cutover. Keywords: upgrade, migrate, classic, gen3, phase2, phase3, readiness, cloud integration, AWS, Azure, GCP, classic connection, new connection, Smartscape on Grail, fleet management, Site Reliability Guardian (SRG), classic pipeline, log processing pipeline, bizevents pipeline, pipeline upgrade, classic processing rules, ActiveGate, authToken, auth token, DynaKube, dynatrace-operator, classicFullStack, Platform token, enable RUM on Grail, RUM migration, mobile RUM, web RUM, Experience Vitals.
- ▌ Fangx AI Cut Director · gabrielmoreira bundle只做一件事:把原始口播剪干净,再配上字幕。不加特效、音乐、B-roll,不调色,不改说话人的原话。字幕默认朴素,用户要美化时可以换样式。
- ▌ Recht Agb · gabrielmoreiraGleicht vorgelegte AGB-Klauseln gegen ein Register entschiedener Klauseln ab (überwiegend für unwirksam erklärt, dazu gebilligte Gegenbeispiele) und benennt die Fundstelle. Vergleicht — wertet nicht.
- ▌ Recht Logik · gabrielmoreiraDie Folgerichtigkeit juristischer Argumentation im deutschen Recht prüfen — Schriftsätze, Gutachten, Vermerke, Bescheide, Vertragsklauseln und Normen. Gesucht wird, ob ein Ergebnis aus seinen Gründen folgt, auch der Schluss aus einer Auslegung; ob ein Begriff im Verlauf seinen Umfang behält und eine Einteilung trägt; ob sich der Text widerspricht; ob Tatsache und Wertung im Schluss getrennt bleiben. Normen und Rechtsprechung werden zur Prüfung markiert, nie aus dem Gedächtnis eingesetzt. Modi: pruefen, klausel, korrektur, vergleich, norm. Use when: „folgt das Ergebnis aus der Begründung“, „ist das ein Zirkelschluss“, „fehlt ein Tatbestandsmerkmal“, „widerspricht sich der Schriftsatz“, „ist die Klausel lückenlos“, „worüber streiten die Parteien eigentlich“, „zerlege die Norm“, „berichtige die Argumentation“.
- ▌ Recht Zitat · gabrielmoreiraPrüft, ob die Nachweise eines juristischen Textes überprüfbar angegeben sind — Gericht, Datum, Aktenzeichen, Randnummer, Norm, Kennzeichnung des Zitats; deutsches Recht, EuGH, EGMR und Unionsrecht. Prüft die Angabe, nie ob der Nachweis existiert oder trägt.
- ▌ Recht Beweis · gabrielmoreiraBeweisführung im deutschen Recht auf ihre Tragfähigkeit prüfen. Erste Frage ist die Verfahrensordnung: Beibringungs- oder Untersuchungsgrundsatz — davon hängt ab, welche Figur anwendbar ist. Geprüft werden die drei Lastebenen (Darlegung, Beweisführung, objektive Feststellungslast), das `non liquet`, Anscheinsbeweis und Erfahrungssatz, gesetzliche und tatsächliche Vermutungen samt Fiktion, das Beweismaß je Verfahrensordnung (§ 286 ZPO, § 261 StPO, § 108 VwGO, § 128 SGG, § 96 FGO, § 37 FamFG — dazu § 287 ZPO und die Glaubhaftmachung) sowie Beweisthema, Erheblichkeit und Beweisangebot. Use when: „prüfe die Beweisführung", „wer trägt die Beweislast", „trägt der Anscheinsbeweis", „ist das Beweismaß richtig", „reicht der Vortrag für einen Beweisantrag", „was gilt bei non liquet". Maßgeblich ist, ob der Beweisschritt trägt und offengelegt ist — nicht, ob das Ergebnis gefällt.
- ▌ Arekejoker Qwen21 Nsfw Pose Skill · gabrielmoreira bundleLocal photorealistic NSFW + pose control: ComfyUI + Qwen-Image 2.1 (int8 convrot)
- ▌ Pua 3 · gabrielmoreira bundleUse for PUA/try-harder productivity coaching when the user expresses frustration, repeated failure, quality complaint, passive behavior, says retry/change approach/don't give up, asks for evidence/completion check/test before done, or wants Ding-style workplace reminders. Triggers include: try harder, stop giving up, figure it out, again??, why still failing, change approach, no evidence, run tests, done without proof, 换个方法, 再试试, 别摆烂, 别偷懒, 为什么还不行, 又错了, 证据呢, 没跑测试别说完成, 验收, 闭环, 自嗨, 置身钉外, 无招, 老板体感. Do not use for calm first-attempt requests.
- ▌ Implement 4 · gabrielmoreiraDrive a single workshop ticket through the inner SWE↔Tester loop. Resolves the ticket from `implement_yourself/tasks/`, creates an `implementing/from-scratch` branch (a fixed default — not derived from the ticket; subsequent tickets stack on top), launches the software-engineer agent to implement it, then routes by archetype — Tester runs on logic tickets, orchestrator spot-checks the SWE's AC walk on glue/bootstrap tickets, fast-path file existence check on docs tickets (Tester HARD-OFF). Loops on FAIL up to 3 times, moves the file to `tasks/done/`, then commits directly with `git commit -m`. Stops after one ticket — the human reviews the commit, talks through it, then re-invokes for the next ticket. Trigger when the user types `/implement`, asks to "implement task NNN", says "pick up the next ticket", or otherwise wants to ship one workshop ticket under supervision.
- ▌ Controlflow Plan 2 · gabrielmoreiraUse when a repository task needs a high-quality ControlFlow plan before coding — small, medium, or large scope, cross-file edits, risky migrations, architectural uncertainty, or any work that should produce a saved Markdown plan artifact in plans/. Single-sources the plan format from schemas/planner.plan.schema.json and the plan template.
- ▌ Subagent Driven Development 6 · gabrielmoreiraUse when executing an implementation plan with 2+ mostly-independent tasks in the current session — when a developer says 'execute this plan', 'implement these tasks', 'work through the plan', or when a written plan exists and coding is starting. Dispatches a fresh subagent per task to prevent context pollution, then runs two mandatory review stages per task: spec compliance (did code match requirements?) then code quality (is it well-written?). Includes implementer prompt, spec-reviewer prompt, and code-quality-reviewer prompt templates. Distinct from executing-plans (which uses parallel sessions): subagent-driven-development stays in the same session. Auto-loads when plan execution, task implementation, or sequential development work is mentioned.
- ▌
- ▌ Cinematic Web Experiences 2 · gabrielmoreira bundleBuild prompts and workflows for premium scroll-driven websites using GSAP ScrollTrigger, Three.js scenes, custom shaders, cinematic loading screens, and responsive motion systems. Use when the user wants a cinematic website, landing page, microsite, or interactive brand experience with scroll storytelling, pinning, parallax, 3D canvas effects, shader-driven visuals, exact animation specs, or a repeatable prompt framework for prompt-based site builders.
- ▌ Jupyter Notebook 55 · gabrielmoreiraاستخدمه عندما يطلب المستخدم إنشاء أو تهيئة أو تعديل دفاتر Jupyter (`.ipynb`) للتجارب أو الاستكشافات أو الدروس التعليمية؛ فضّل القوالب المضمّنة وقم بتشغيل سكربت المساعدة `new_notebook.py` لتوليد دفتر بدءٍ نظيف
- ▌ Controlflow Verify 2 · gabrielmoreiraUse after /controlflow-claude-code:controlflow-plan produces a plan, before implementation. Runs adversarial pre-execution verification inline in the main context (zero subagents): structural audit, assumption/mirage detection, and executability cold-start simulation. Emits APPROVED / NEEDS_REVISION / REJECTED with evidence.
- ▌ Trigger Chat Agent Advanced 2 · gabrielmoreiraAdvanced and operational chat.agent capabilities for Trigger.dev, loaded on demand. Load this when working on the raw Sessions primitive (sessions / SessionHandle), a custom chat transport or the realtime wire protocol, durable sub-agents (AgentChat, chat.stream.writer), human-in-the-loop, steering, actions, background injection (chat.defer / chat.inject), fast starts (preload, Head Start via @trigger.dev/sdk/chat-server), context resilience (compaction, recovery boot, OOM, large payloads), chat.local run-scoped state, offline testing with mockChatAgent, or prerelease/version upgrades. For the everyday chat.agent({...}) definition and the useTriggerChatTransport happy path, use the trigger-authoring-chat-agent skill instead.
- ▌ Search 5 · gabrielmoreiraSearch 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
- ▌ Trigger Authoring Chat Agent 2 · gabrielmoreiraAuthor and run a durable AI chat agent with chat.agent from @trigger.dev/sdk/ai: the per-turn run loop, why you MUST take streamText from the run argument rather than importing it from ai, returning a StreamTextResult vs calling chat.pipe(), the two server actions (chat.createStartSessionAction + auth.createPublicToken), and wiring useChat to useTriggerChatTransport. Load this when building, modifying, or debugging a chat backend (the agent task or its lifecycle hooks) or its React transport, when declaring typed tools or custom data parts, or when migrating a plain AI SDK streamText route to chat.agent.
- ▌ Recipe Reverse Engineer 2 · gabrielmoreiraGenerate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow
- ▌
- ▌
- ▌
- ▌ Example Skill 2 · gabrielmoreiraPerforms thorough code reviews following best practices. Use when reviewing pull requests, checking code quality, or ensuring coding standards compliance.
- ▌ Minutes Release Notes 2 · gabrielmoreira bundleDraft user-facing Minutes release notes for a version from the commit range, recent GitHub releases, and the repository release checks. Use when the user asks to write, generate, prepare, revise, or review release notes or a changelog for a Minutes version.
- ▌ Minutes Ingest 2 · gabrielmoreiraExtract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data.
- ▌ Minutes Search 2 · gabrielmoreiraSearch past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or any question that could be answered by searching their meeting history. Also use for "do I have any notes about" or "check my meetings for".
- ▌ Memory Management 6 · gabrielmoreiraMemory lifecycle patterns for artifact retention, decision recording, context compaction, and Copilot Memory hygiene. Use for session context management, ADR creation, and rolloff strategies.
- ▌ Planning With Files 12 · gabrielmoreira bundlePersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.
- ▌ Minutes Cleanup 2 · gabrielmoreiraManage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage meeting storage", or asks about disk space from minutes.
- ▌ Minutes Copilot 2 · gabrielmoreiraStart and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minutes-live-sidekick. An ambiguous request such as "coach me live" requires one short surface clarification and must not automatically start Coach.
- ▌ Brainstorming 12 · gabrielmoreiraYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
- ▌ Writing Plans 8 · gabrielmoreiraUse when you have a spec or requirements for a multi-step task, before touching code
- ▌ LLM Wiki 6 · gabrielmoreiraCompile heterogeneous knowledge sources—including documents, notes, web content, transcripts, research materials, and code repositories—into a Karpathy-style, evidence-grounded LLM Wiki with a maintained index; default entity and concept pages; and selective method, comparison, analysis, or instruction-requested summary pages. Use with ov compile to create or incrementally refresh knowledge that is easy for people and agents to retrieve, navigate, and reuse.
- ▌ Git Workflow 7 · gabrielmoreiraExecute a complete git workflow for collaborative development. Use when user asks to initialize a repo, create branches, commit changes, sync with upstream, open pull requests, resolve conflicts, merge PRs, create releases, or apply hotfixes. Supports Centralized, Feature Branch, Gitflow, and Forking workflows with conventional commits, branch naming standards, and code review guidelines.
- ▌ Planning With Files 13 · gabrielmoreira bundlePersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.
- ▌ Writing Skills 6 · gabrielmoreiraUse when creating new skills, editing existing skills, or verifying skills work before deployment
- ▌ Skill Installer 3 · gabrielmoreiraInstall the agent skills into $DEVO_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
- ▌ Image Generation 6 · gabrielmoreiraGenerate, edit, and iterate raster images from text prompts or reference images with GPT Image, Nano Banana, or Seedream. Use for visual asset creation, concept art, product/mockup imagery, style exploration, thumbnails, illustrations, and image transformation workflows across image provider APIs.
- ▌ Planning With Files 14 · gabrielmoreira bundlePersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.
- ▌ Tailwind Design System 2 · gabrielmoreira bundleApply or extend the project's Tailwind design tokens (colors, spacing, typography) consistently, and audit existing markup for hardcoded/arbitrary values that should use tokens instead. Use when asked to "fix styling", "make this consistent with the design system", "add a new color/theme token", or "convert this to Tailwind".
- ▌ Dispatching Parallel Agents 4 · gabrielmoreiraRuns independent subtasks concurrently via sub-agents.
- ▌ Performance Analysis 2 · gabrielmoreiraPerformance analysis patterns for runtime complexity, memory usage, cost optimization, and scalability assessment. Use for Big O analysis, profiling, caching strategies, and cloud cost modeling.
- ▌ Planning With Files 15 · gabrielmoreira bundlePersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.
- ▌ Finishing A Development Branch 5 · gabrielmoreiraVerifies, summarises, and closes a development branch.
- ▌ Receiving Code Review 6 · gabrielmoreiraUse when receiving code review feedback or PR review comments, before implementing or accepting any suggestions — especially if feedback seems unclear, technically questionable, or conflicts with prior decisions. Enforces technical rigor over performative agreement. Provides: a 6-step evaluate-before-implement pattern; forbidden responses ('You're absolutely right!'); YAGNI check (grep codebase before adding features); source-specific handling (partner vs external reviewer); pushback templates with technical reasoning; a correction pattern when your pushback was wrong; and implementation ordering by priority (blocking → simple → complex). Auto-loads when user mentions code review, PR feedback, reviewer comments, or 'reviewer said to'.
- ▌ Requesting Code Review 8 · gabrielmoreiraUse when completing a task, implementing a major feature, or before merging — when a developer says 'review my code', 'check this before I merge', 'is this ready?', or after completing any task in a subagent-driven workflow. Dispatches a code-reviewer subagent with structured input (what was implemented, requirements, git SHAs). Provides a review template, severity tiers (Critical/Important/Minor), and instructions for acting on feedback. Mandatory after each task in subagent-driven development, after major features, and before any merge to main. Auto-loads when review, PR, merge, or code quality is mentioned.
- ▌ Test Driven Development 10 · gabrielmoreiraEnforces Test-Driven Development discipline for all new features, bug fixes, refactoring, and behavior changes. Use before writing ANY implementation code — when a developer says 'implement this', 'write the code', 'add this function', 'fix this bug', or 'build this'. Provides the Red-Green-Refactor cycle with concrete TypeScript examples, an Iron Law (no production code without a failing test first), a rationalization rebuttal table to counter TDD excuses, a verification checklist, and STOP conditions for when code must be deleted and restarted. Auto-loads whenever implementation, coding, building, or feature development is mentioned.