Context & AI engineering
25,841 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
Kaelio/ktx/packages/cli/src/skills/wiki_capture Skill
1,540★ repoktx's knowledge base - wiki pages for durable, reusable business knowledge. Covers capture workflow for user preferences, metric definitions, organizational conventions, and cross-references between wiki pages and semantic-layer sources. Loaded by the post-turn memory-agent only. The research agent reads wiki via `wiki_read`/`wiki_search` but does not write it.
evo-hq/evo/plugins/evo/npm/skills/subagent Skill
1,503★ repoProtocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior.
The same file is in 1 other repository
evo-hq/evo/plugins/evo/skills/subagent Skill
1,503★ repoProtocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior.
The same file is in 1 other repository
alibaba/skill-up/e2e/testdata/mcp-case-overrides Skill
1,475★ repoPer-case mocked MCP override smoke skill used by skill-up e2e tests.
alibaba/skill-up/e2e/testdata/mcp-mocked-marker Skill
1,475★ repoMCP mocked marker smoke skill used by skill-up e2e tests.
alibaba/skill-up/e2e/testdata/mcp-stdio-marker Skill
1,475★ repoMCP stdio marker smoke skill used by skill-up e2e tests.
alibaba/skill-up/e2e/testdata/sandbox-mcp Skill
1,475★ repoVerify Sandbox MCP can be installed and called from skill-up.
Prat011/awesome-llm-skills/mcp-builder Skill
no license1,470★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 18 other repositories
Prat011/awesome-llm-skills/skill-creator Skill
no license1,470★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
The same file is in 16 other repositories
rohitg00/skillkit/packages/core/src/methodology/packs/collaboration/handoff-protocols Skill
1,458★ repoManages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or agent; brief a colleague taking over; prepare a shift change summary; or onboard someone mid-task. Produces ready-to-use handoff documents covering current status, next steps, known issues, technical context, and communication templates for both planned and unplanned transfers.
rohitg00/skillkit/packages/core/src/methodology/packs/meta/skill-authoring Skill
1,458★ repoCreates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or define a skill template for Claude Code agents.
silverstein/minutes/.agents/skills/minutes/minutes-copilot Skill
1,445★ repoStart 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.
The same file is in 1 other repository
silverstein/minutes/.agents/skills/minutes/minutes-live-sidekick Skill
1,445★ repoAct as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.
The same file is in 1 other repository
silverstein/minutes/.opencode/skills/minutes-copilot Skill
1,445★ repoStart 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.
The same file is in 1 other repository
silverstein/minutes/.opencode/skills/minutes-live-sidekick Skill
1,445★ repoAct as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.
The same file is in 1 other repository
Zag ausnahmen limited network commercial agent
Klotzkette/claude-fuer-deutsches-recht/bank-rechtsabteilung/skills/zag-ausnahmen-limited-network-commercial-agent Skill
1,443★ repoWenn es um ZAG-Ausnahmen in Bank-Rechtsabteilung geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten Schritt; liefert ein direkt nutzbares Arbeitsprodukt mit Prüfpunkten, Risiken und nächstem Schritt.
Brki rag bro grundlagen cloud act
Klotzkette/claude-fuer-deutsches-recht/berufsrecht-ki-vertragspruefung/skills/brki-rag-bro-grundlagen-cloud-act Skill
1,443★ repoWenn es um BRKI: RAG-Vertraulichkeit in diesem Spezialbereich geht: ordnet Akteninhalt, Belege, Lücken und Nachforderungen; liefert eine Schnittstellenkarte mit Kollisions-, Zuständigkeits- und Nachweisfragen Stichwort für die Auswahl: Brki Rag Bro Grundlagen Cloud Act.
Brki rag vertraulichkeit spezial
Klotzkette/claude-fuer-deutsches-recht/berufsrecht-ki-vertragspruefung/skills/brki-rag-vertraulichkeit-spezial Skill
1,443★ repoWenn es um BRKI: RAG-Vertraulichkeit in diesem Spezialbereich geht: ordnet Akteninhalt, Belege, Lücken und Nachforderungen; liefert eine Schnittstellenkarte mit Kollisions-, Zuständigkeits- und Nachweisfragen Stichwort für die Auswahl: Brki Rag Vertraulichkeit Spezial.
Forensische prompt gutachten erstellen
Klotzkette/claude-fuer-deutsches-recht/berufsrecht-ki-vertragspruefung/skills/forensische-prompt-gutachten-erstellen Skill
1,443★ repoWenn es um Prompt-Injection: Prüfung in diesem Spezialbereich geht: ordnet Akteninhalt, Belege, Lücken und Nachforderungen; liefert eine Tatbestands- oder Anspruchsmatrix mit Gegenargumenten.
Forensische pruefung prompt injection
Klotzkette/claude-fuer-deutsches-recht/berufsrecht-ki-vertragspruefung/skills/forensische-pruefung-prompt-injection Skill
1,443★ repoWenn es um Prompt-Injection: Prüfung in diesem Spezialbereich geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition; liefert eine Tatbestands- oder Anspruchsmatrix mit Gegenargumenten.
Klotzkette/claude-fuer-deutsches-recht/berufsrecht-patentanwaelte/skills/patent-agent-patentportfolio Skill
1,443★ repoWenn es um Patent Agent Patentportfolio in Berufsrecht Patentanwälte geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Patent agent prior art sanktionen
Klotzkette/claude-fuer-deutsches-recht/berufsrecht-patentanwaelte/skills/patent-agent-prior-art-sanktionen Skill
1,443★ repoWenn es um Patent Agent Prior Art Sanktionen in Berufsrecht Patentanwälte geht: klärt Rolle, Ziel, Frist, Unterlagen und den passenden nächsten Fachskill; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Patent agent title und werbung kammerantwort
Klotzkette/claude-fuer-deutsches-recht/berufsrecht-patentanwaelte/skills/patent-agent-title-und-werbung-kammerantwort Skill
1,443★ repoWenn es um Patent Agent Title Und Werbung Kammerantwort in Berufsrecht Patentanwälte geht: ordnet Akteninhalt, Belege, Lücken und Nachforderungen; liefert eine Verhandlungs- oder Eskalationslinie mit Optionen.
Patent agent title und werbung rechtsprechungscheck
Klotzkette/claude-fuer-deutsches-recht/berufsrecht-patentanwaelte/skills/patent-agent-title-und-werbung-rechtsprechungscheck Skill
1,443★ repoWenn es um Patent Agent Title Und Werbung Rechtsprechungscheck in Berufsrecht Patentanwälte geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition; liefert eine Gegenprüfung mit Fehler-, Beweis- und Fristencheck.
Freundlicher copilot gesellschaftsrecht
Klotzkette/claude-fuer-deutsches-recht/corporate-kanzlei/skills/freundlicher-copilot-gesellschaftsrecht Skill
1,443★ repoWenn es um Freundlicher Corporate-Copilot in Corporate-Kanzlei geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten. Auswahlstichwort: Freundlicher Copilot Gesellschaftsrecht; Arbeitsfeld: Corporate-Kanzlei.
Klotzkette/claude-fuer-deutsches-recht/corporate-kanzlei/skills/freundlicher-copilot Skill
1,443★ repoWenn es um Freundlicher Corporate-Copilot in Corporate-Kanzlei geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten. Auswahlstichwort: Freundlicher Copilot; Arbeitsfeld: Corporate-Kanzlei.
Vergabe os master orchestrator
Klotzkette/claude-fuer-deutsches-recht/fachanwalt-vergaberecht/skills/vergabe-os-master-orchestrator Skill
1,443★ repoWenn es um Vergabe Os Master Orchestrator in Fachanwalt Vergaberecht geht: erstellt den passenden Entwurf aus Sachverhalt, Norm, Beweis und Antrag; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Klotzkette/claude-fuer-deutsches-recht/grosskanzlei-corporate-ma/skills/deal-os-orchestrator Skill
1,443★ repoWenn es um Deal Os Orchestrator in Großkanzlei Corporate/M&A geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Klotzkette/claude-fuer-deutsches-recht/grosskanzlei-corporate-ma/skills/freundlicher-copilot Skill
1,443★ repoWenn es um Freundlicher Copilot in Großkanzlei Corporate/M&A geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Klotzkette/claude-fuer-deutsches-recht/internal-investigations-praxis/skills/inv-036-third-party-agent Skill
1,443★ repoWenn es um Internal Investigation: Third Party Agent in Internal Investigations Praxis geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Klotzkette/claude-fuer-deutsches-recht/internationales-handelsrecht-lex-mercatoria/skills/commercial-agent-eu Skill
1,443★ repoWenn es um EU-Handelsvertreterrecht in Internationales Handelsrecht und Lex Mercatoria geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Klotzkette/claude-fuer-deutsches-recht/internationales-handelsrecht-lex-mercatoria/skills/ihl-064-commercial-agent-eu Skill
1,443★ repoWenn es um Commercial Agent EU in Internationales Handelsrecht und Lex Mercatoria geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Klotzkette/claude-fuer-deutsches-recht/kanzlei-allgemein/skills/freundlicher-copilot-kanzlei Skill
1,443★ repoWenn es um Freundlicher Kanzlei-Copilot in Kanzlei-Allgemein geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Delegation supervision deliverable acceptance
Klotzkette/claude-fuer-deutsches-recht/kanzlei-mandant-lifecycle/skills/delegation-supervision-deliverable-acceptance Skill
1,443★ repoWenn es um Delegation und Supervision in Kanzlei-Mandant Lifecycle geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Literatur quellen prompting leitfaden rdg
Klotzkette/claude-fuer-deutsches-recht/ki-richtlinie-kanzleien/skills/literatur-quellen-prompting-leitfaden-rdg Skill
1,443★ repoWenn es um Literatur und Quellen in diesem Spezialbereich geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition; liefert eine Beweislast- und Substantiierungsmatrix.
Klotzkette/claude-fuer-deutsches-recht/ki-richtlinie-kanzleien/skills/prompting-leitfaden Skill
1,443★ repoWenn es um Prompting-Leitfaden in diesem Spezialbereich geht: zerlegt Ergebnis, Frist, Zuständigkeit, Beweislast und Gegenposition; liefert eine Mandantennachricht oder Entscheidungsvorlage.
Rechtsabteilung provider deployer grenze bei custom gpt
Klotzkette/claude-fuer-deutsches-recht/ki-vo-ai-act-pruefer/skills/rechtsabteilung-provider-deployer-grenze-bei-custom-gpt Skill
1,443★ repoWenn es um Rechtsabteilung: Provider-Deployer-Grenze bei Custom GPT in diesem Spezialbereich geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und nächsten Schritt; liefert ein direkt nutzbares Arbeitsprodukt mit Prüfpunkten, Risiken und nächstem Schritt Stichwort für die Auswahl: Rechtsabteilung Provider Deployer Grenze Bei Custom Gpt.
Klotzkette/claude-fuer-deutsches-recht/mittelstand-corporate-ma/skills/freundlicher-copilot Skill
1,443★ repoWenn es um Freundlicher Deal-Copilot in Mittelstands-Corporate/M&A geht: entwickelt Verhandlungsziel, Vergleichskorridor und Eskalationspfad; liefert eine Verhandlungs- oder Eskalationslinie mit Optionen.
Budget roadmap byod policy chatgpt copilot
Klotzkette/claude-fuer-deutsches-recht/nis2-cybersecurity-compliance/skills/budget-roadmap-byod-policy-chatgpt-copilot Skill
1,443★ repoWenn es um Budget Und Roadmap in NIS-2, Cybersecurity und IT-Sicherheits-Compliance geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Klotzkette/claude-fuer-deutsches-recht/nis2-cybersecurity-compliance/skills/chatgpt-copilot-policy Skill
1,443★ repoWenn es um Chatgpt Copilot Policy in NIS-2, Cybersecurity und IT-Sicherheits-Compliance geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Product liability prompt code public
Klotzkette/claude-fuer-deutsches-recht/softwarerecht-de-eu-us/skills/product-liability-prompt-code-public Skill
1,443★ repoWenn es um Produkthaftung für fehlerhafte Software EU in Softwarerecht Deutschland/EU/International/USA geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Klotzkette/claude-fuer-deutsches-recht/softwarerecht-de-eu-us/skills/prompt-code-ownership Skill
1,443★ repoWenn es um Prompt und Code Ownership in Softwarerecht Deutschland/EU/International/USA geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten.
Prompt versionierung paket review
Klotzkette/claude-fuer-deutsches-recht/tabellenreview-3d/skills/prompt-versionierung-paket-review Skill
1,443★ repoWenn es um /tabellenreview-3d:prompt-versionierung in Tabellenreview 3D geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten. Auswahlstichwort: Prompt Versionierung Paket Review; Arbeitsfeld: Tabellenreview 3D.
Klotzkette/claude-fuer-deutsches-recht/tabellenreview-3d/skills/prompt-versionierung Skill
1,443★ repoWenn es um /tabellenreview-3d:prompt-versionierung in Tabellenreview 3D geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine Fristen- und Risikoampel mit Sofortschritten. Auswahlstichwort: Prompt Versionierung; Arbeitsfeld: Tabellenreview 3D.
silverstein/minutes/.claude/plugins/minutes/skills/minutes-copilot Skill
1,426★ repoStart 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.
silverstein/minutes/.claude/plugins/minutes/skills/minutes-live-sidekick Skill
1,426★ repoAct as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.
silverstein/minutes/tooling/skills/goldens/claude/minutes-copilot Skill
1,426★ repoStart 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.
silverstein/minutes/tooling/skills/goldens/claude/minutes-live-sidekick Skill
1,426★ repoAct as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.
silverstein/minutes/tooling/skills/goldens/codex/minutes-copilot Skill
1,426★ repoStart 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.
silverstein/minutes/tooling/skills/goldens/codex/minutes-live-sidekick Skill
1,426★ repoAct as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.
silverstein/minutes/tooling/skills/goldens/opencode/minutes-copilot Skill
1,426★ repoStart 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.
silverstein/minutes/tooling/skills/goldens/opencode/minutes-live-sidekick Skill
1,426★ repoAct as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.
OpenRaiser/NanoResearch/skills/vendor-ai-research/0-autoresearch-skill Skill
1,421★ repoOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
The same file is in 2 other repositories
OpenRaiser/NanoResearch/skills/vendor-ai-research/skypilot Skill
1,421★ repoMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
The same file is in 6 other repositories
brycewang-stanford/Awesome-Journal-Skills/NeurIPS-Skills/skills/neurips-submission Skill
1,416★ repoUse when auditing a NeurIPS main-track submission for current-cycle CFP, OpenReview, formatting, anonymity, track, contribution-type, checklist, code/data, dual-submission, and LLM/agent policy compliance.
first-fluke/oh-my-agent/.agents/skills/oma-db Skill
1,369★ repoDatabase specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning, data standards, anti-pattern review, and compliance-aware database design. Use for database, schema, ERD, table design, document model, vector index design, RAG retrieval architecture, migration, query tuning, glossary, capacity estimation, backup strategy, database anti-pattern remediation work, and ISO 27001, ISO 27002, or ISO 22301-aware database recommendations.
The same file is in 3 other repositories
first-fluke/oh-my-agent/.agents/skills/oma-orchestrator Skill
1,369★ repoAutomated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel execution, and automated multi-agent workflows.
first-fluke/oh-my-agent/.agents/skills/oma-skill-creator Skill
1,369★ repoCreate or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents/skills/{skill-name}/SKILL.md`, converting an existing skill to the standardized Scheduling / Structural Flow / Logical Operations / References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.
first-fluke/oh-my-agent/.agents/skills/oma-voice Skill
1,369★ repoLocal-first text-to-speech and speech-to-text via the Voicebox MCP server. Generates speech from cloned or preset voice profiles for agent notifications, content voiceovers, and audio asset creation, and transcribes audio files for meeting notes or memos. Runs entirely on-device with no cloud, no API keys, no per-call cost. Use for voice generation, TTS, STT, transcription, voiceover, narration, dictation, audio asset work.
first-fluke/oh-my-agent/benchmarks/runs/oma/.agents/skills/oma-db Skill
1,369★ repoDatabase specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning, data standards, anti-pattern review, and compliance-aware database design. Use for database, schema, ERD, table design, document model, vector index design, RAG retrieval architecture, migration, query tuning, glossary, capacity estimation, backup strategy, database anti-pattern remediation work, and ISO 27001, ISO 27002, or ISO 22301-aware database recommendations.