AI & ML

elevanaltd-hestai-mcp Bundle

===SKILL:AGENT_CREATION===

elevanaltd-hestai-mcp Skill

OCTAVE on the wire — read and emit OCTAVE in agent-to-agent messages without authoring files. Syntax kernel, operator table, and the OCTAVE_WIRE primer v1.3 (provenance, hedges, verbatim IDs). For agents outside the workbench matrix.

elevanaltd-hestai-mcp Skill

===SKILL:AGENT_INTERVIEW===

elevanaltd-hestai-mcp Skill

LLM-native structured communication format. Teaches OCTAVE syntax rules, canonical forms, and warning prevention for zero-error .oct.md authoring.

elevanaltd-hestai-mcp Skill

===SKILL:V9_AGENT_CREATION===

elevanaltd-hestai-mcp Bundle

Supabase operational knowledge for migrations, RLS optimization, MCP tool benchmarks, and ADR-003 compliance. Use when validating database migrations, optimizing Row-Level Security policies, checking MCP tool performance, or ensuring Supabase operational standards. Triggers on: migration validation, RLS patterns, Supabase benchmarks, ADR-003, database state tracking, schema governance.

hashgraph-online-awesome-codex-plugins Bundle

Launch a finished Codex Process Jobs record again as a new detached job using its validated persisted argv, working directory, and execution mode. Use only when the user explicitly asks or approves rerunning a specific completed, failed, or cancelled build, test, benchmark, inference run, data job, or repair.

hashgraph-online-awesome-codex-plugins Skill

Use when setting up Agent Deck, the MCP is disconnected, or the local daemon is down. Guides install/start with read-only checks; the user runs install commands.

hashgraph-online-awesome-codex-plugins Skill

Use at session start in a deck-bound workspace, or when the user asks for the deck status line / which deck is active.

hashgraph-online-awesome-codex-plugins Skill

Look up vehicle data by Year, Make, and Model using the CarsXE YMM API. Use this when a user doesn't have a VIN but knows the year, make, and model of a vehicle and wants specs, trims, or features.

hashgraph-online-awesome-codex-plugins Bundle

River Review のメインエントリポイント。 レビュー依頼の intent classification → 専門 skill 選択 → 実行 → finding verification → feedback classification → fixture / reference / suppression への還元までを束ねる improvement-loop orchestrator。

hashgraph-online-awesome-codex-plugins Bundle

一般コード品質のレビューエージェント。デフォルトのフォールバック先。 可読性、保守性、型安全性、ロギング等の個別スキルへルーティングする。

hashgraph-online-awesome-codex-plugins Bundle

ドキュメント観点のレビューエージェント。 README / docs / AGENTS.md と実装の整合性、API ドキュメントとコードの対応、 usage や例の正確性、i18n（JA/EN）整合性、用語統一を検証する。

hashgraph-online-awesome-codex-plugins Bundle

テスト観点のレビューエージェント。 テスト網羅性、命名規則、フレーキーテスト、カバレッジギャップの個別スキルへルーティングする。

hashgraph-online-awesome-codex-plugins Bundle

セキュリティ観点のレビューエージェント。 基本的なセキュリティチェック、認証・認可設計、プライバシー設計の個別スキルへルーティングする。

hashgraph-online-awesome-codex-plugins Bundle

パフォーマンス観点のレビューエージェント。 N+1クエリ、メモリ効率、キャッシュ戦略、可観測性の観点でコード変更を評価する。

hashgraph-online-awesome-codex-plugins Bundle

設計・アーキテクチャ観点のレビューエージェント。 依存関係、境界設計、データモデル、API設計等の個別スキルへルーティングする。

lev-os Skill

Compatibility route for delegated coding-agent work. Load $coder for current multi-provider, CAAM-aware, Lev-managed worker execution.

lev-os Skill

Claude Code Prompt for Plan Mode

lev-os Skill

RAG Engineer

lev-os Skill

Prompt Engineer

lev-os Bundle

[WHAT] Route prompts + files to GPT-5 Pro, Gemini 3 Pro, Claude Opus 4.1, and more via oracle CLI [HOW] Uses oracle serve (persistent browser daemon on :9473) or API with OPENAI_API_KEY [WHEN] Second opinion, multi-model comparison, browser-only features (image gen, extended thinking) [WHY] Cross-model validation and access to models not available in current context Triggers: "ask gpt", "oracle", "second opinion", "ask chatgpt", "cross-check with gpt", "multi-model", "compare models", "gpt-5", "gemini", "use oracle"

dirtytrii Skill

提议并执行 rubric 或 bucket 升级。两种模式：**完整 rubric bump**（最高风险动作，5 步强制 + 跨模型审核）和 **--bucket-only 轻量重校**（只换 bucket 边界，不动 rubric 公式）。**Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分**——不接受 self-scored fallback。触发词："升级 rubric"/"bump rubric"/"更新公式"/"我想加一个维度"/"调整权重"/"重校桶"/"recalibrate bucket"。

dirtytrii Bundle

INTERNAL sub-agent, not a user-facing skill. Performs context-isolated nine-dimension rubric scoring for cheat-score, cheat-predict, and cheat-bump. Accepts only script and rubric-note paths, returns strict JSON, and refuses post-publish evidence.

specterops Bundle

Use when creating or changing BloodHound OpenGraph extensions, custom node schemas, custom ingestors, edge models, or Cypher patterns that connect non-AD assets to BloodHound CE graph analysis. Use for graph-model design questions such as new node kinds, new relationship kinds, extension schema changes, or custom ingestor behavior. Do not use for routine BloodHound path triage, connection checks, or known OpenHound query adaptation; use $bloodhound-analysis, $bloodhound-query, $openhound-github, $openhound-jamf, or $openhound-okta instead.

specterops Bundle

Use for Ghostwriter operation log entries from Codex, including config guidance, quick notes, evidence-backed entries, and guided oplog capture through the Ghostwriter MCP tools.

specterops Bundle

Develop Mythic translation containers for custom agent wire formats, custom encryption/decryption, and Mythic-to-agent message conversion. Use when a payload type sets translation_container, when mythic_encrypts is false with custom crypto, or when a C2 profile/agent needs non-JSON or binary message formats.

specterops Bundle

Use for reverse engineering and binary analysis with LaurieWired/GhidraMCP. Trigger for Ghidra MCP setup, bridge_mcp_ghidra.py usage, GhidraMCP plugin workflows, decompilation, function/string/import/export/xref analysis, renaming functions/data/variables, setting comments/types/prototypes, or producing Ghidra-backed RE notes.

specterops Bundle

Provides Binary Ninja IL documentation and MCP server usage guidance for binary analysis and reverse engineering

specterops Bundle

Draft believable copy for a credential-harvest landing page. Use when creating target-specific text for a fake login, SSO prompt, meeting join page, or internal portal notice.

ax-llm Skill

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.

ax-llm Skill

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

ax-llm Skill

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for using the generated Ax package, factory functions, package docs, examples, and API reference.

ax-llm Skill

Use when writing C++ code with `axllm` for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.

ax-llm Skill

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

ax-llm Skill

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.