AI & ML

trpc-group Skill

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

trpc-group Skill

Delegate coding tasks to Codex, Claude Code, or Pi agents via background host sessions. Use when: (1) building or creating new features or apps, (2) reviewing PRs or parallel coding with managed worktree isolation when subagents are available, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat, or any work in ~/clawd workspace (never spawn agents here). Requires OpenClaw host tools with exec_command plus write_stdin.

trpc-group Bundle

Create or update AgentSkills, especially when a user wants the agent to learn a reusable capability, workflow, integration, domain rule, team process, or tool usage pattern for future tasks. Use when designing, structuring, reviewing, validating, packaging, or improving skills with SKILL.md, scripts, references, and assets.

trpc-group Skill

Find a public Agent Skill on GitHub, install it, and load it.

trpc-group Bundle

Connect to a remote streamable HTTP MCP service that exposes announcements and FAQ tools.

tankygranny05 Skill

Clone a repo to ~/temp with unique -cloneN, bump all *_PORT values in clone .env by +100*N, then work only in the clone and never touch the original unless explicitly asked.

tankygranny05 Skill

Prompt template for documenting debugging sessions after successfully fixing bugs. Use this to capture debugging methodology, hypothesis evolution, red herrings, breakthrough moments, and lessons learned for future agents. Trigger keywords - debug knowledge base, document debugging session, debugging methodology, post-mortem analysis, incident report debugging, debug report template, capture debugging process.

tankygranny05 Skill

This skill should be used when MCP stubs or broken control_request flows need to be replaced with ground-truth implementations aligned to extension.js and cli.js, or when MCP-related UI behavior (missing tool outputs, spinner stuck, empty MCP list) needs debugging.

tankygranny05 Skill

Configure Agent HQ Electron crash mitigations + diagnostics via repo .env (added after 2026-01-22 renderer crash).

tankygranny05 Skill

Document how to capture the directional Claude extension/shim traffic so the renamed JSONL streams (`claude_*` and `claude_shim_*`) are always written and can be compared against Codex logs.

tankygranny05 Bundle

Send prompts directly to Google Antigravity (Gemini + Claude) via Python using OAuth refresh tokens, without OpenCode; includes correct headers, model ID normalization, endpoint selection, SSE streaming, and 429 backoff.

tankygranny05 Skill

Convert skills between Claude Code and Codex CLI formats. Use when porting skills from ~/.claude/skills to ~/.codex/skills (or vice versa), converting project-level skills between .claude/skills and .codex/skills directories, or troubleshooting why a copied skill isn't loading. Covers all skill levels (user, project/repo, system, admin) and gotchas like symlinks, hidden dirs, and field length limits.

tankygranny05 Skill

Search past agent conversations, chats, prompt history, and agent data (Codex/Claude). Use when user asks to "search agent chat", "search agent conversation", "find conversation", "agent prompt history", "what did agent X do", "query agent data", or needs to look up past agent activity. PREREQUISITE - Always read dump-agent-data-for-rg skill first.

tankygranny05 Skill

This skill should be used when freezing centralized Codex/Claude sse_lines.jsonl logs and extracting per-round NDJSON files, composing a sessions index, validating outputs, and re-running incrementally for newly appended data using checkpoints.

tankygranny05 Bundle

This skill should be used when building a low-latency, long-lived Codex controller using `codex app-server` (JSON-RPC over stdio) to keep one PID alive across turns while preserving `sse_lines.jsonl` observability.

tankygranny05 Bundle

Patch Claude Code cli.js to enable fine-grained tool streaming (input_json_delta). Use when tool call arguments arrive as a single burst at the end instead of streaming incrementally, when sse_lines.jsonl shows few/no input_json_delta events, or when asked to "enable tool streaming", "fix partial json", or "patch fine-grained streaming".

tankygranny05 Skill

Estimate OpenAI weekly usage limits from SSE logs. Includes billing week extraction (resets 14:47 local), token computation methodology, live pricing fetcher, and limit projection from partial data.

tankygranny05 Bundle

This skill should be used when spawning and managing tmux sessions running Claude Code (cc), reliably detecting Claude session IDs and renaming sessions to tmux-sdk-{uuid7}-sid-{sid}-pid-{pid} without exceeding macOS terminal limits.

tai-ch0802 Skill

使用 Claude API / Anthropic SDK 建構、除錯和最佳化應用程式。使用此技能建構的應用程式應包含提示快取 (prompt caching)。也處理在 Claude 模型版本之間遷移現有 Claude API 程式碼（4.5 → 4.6，4.6 → 4.7，替換已退役模型）。觸發時機：程式碼匯入 anthropic/@anthropic-ai/sdk；使用者要求使用 Claude API、Anthropic SDKs 或 Managed Agents (/v1/agents, /v1/sessions, /v1/environments)；使用者在檔案中新增/修改/調整 Claude 功能（快取、思考、壓縮、工具使用、批次、檔案、引用、記憶）或模型（Opus/Sonnet/Haiku）；關於 Anthropic SDK 專案中提示快取/快取命中率的問題。不觸發：檔案匯入 `openai`/其他提供者 SDK，檔案名稱類似 `*-openai.py`/`*-generic.py`，與提供者無關的程式碼，一般程式設計/機器學習。

tai-ch0802 Skill

建立高質量 MCP (Model Context Protocol) 伺服器的指南，使 LLM 能透過精心設計的工具與外部服務互動。當需要建構 MCP 伺服器以整合外部 API 或服務時使用，無論是使用 Python (FastMCP) 或 Node/TypeScript (MCP SDK)。

elihuvillaraus Skill

Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM pitfalls. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. Universal — applies to all agents and all AI tools. Triggers on "karpathy", "think before coding", "don't assume", "simplify", "surgical changes", "success criteria".

elihuvillaraus Skill

Guía definitiva sobre cuándo usar un SKILL vs un AGENTE en GitHub Copilot CLI. Consultar antes de diseñar cualquier automatización, subagente, o flujo multi-agente. Trigger: 'qué uso skill o agente', 'cuándo usar agente', 'skill vs agent', 'cómo estructura mis agentes', 'when to use agent', 'agent architecture'.

brite-nites Bundle

Apex test execution and coverage discipline (Brite edition) with 120-point scoring. TRIGGER when user runs Apex tests, checks coverage, fixes failing tests, touches *Test.cls / *_Test.cls files, works in brite-salesforce, asks about 100% class coverage targets, @TestSetup static-state trap, Queueables inside Test.stopTest() re-entering handlers, @TestVisible + Test.isRunningTest() escape-hatch gating, Bypass_Validation_Rules honoring in tests, LWC Jest pre-commit, or scratch-org-per-PR validation. DO NOT TRIGGER when writing Apex production code (use sf-apex), Agentforce agent testing (use sf-ai-agentforce-testing), or Jest/LWC tests (use sf-lwc).

brite-nites Skill

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

brite-nites Skill

Refines a v1 project plan into agent-ready tasks with clear context, implementation steps, and validation criteria. Use after /plan-project has produced a v1 plan.

tankygranny05 Skill

Create or tune a Rust SQLite ingestor that ingests huge JSONL logs fast in historical mode and stays under a strict RSS budget in live mode using byte-scan parsing, mode-specific SQLite PRAGMAs, exec-based live restart, and a minimal index set.

tankygranny05 Skill

Verify RAM consumption of processes by measuring system memory before/after killing them. Uses htop in a tmux session for accurate measurement.

tankygranny05 Skill

Adds project root directories to sys.path for proper imports, with try/except to handle REPL environments (PyCharm, ipython, Jupyter) where __file__ is undefined. Use when writing Python scripts that need to import from parent/grandparent directories and should also work in interactive environments.

tankygranny05 Bundle

Ultra-fast token+cost computation for Codex + Claude SSE logs (Rust) plus Python anchor/fast comparisons; includes build+run+benchmark guide.

tankygranny05 Skill

Configuration philosophy requiring centralized, transparent .env files with no hidden variables, silent fallbacks, or defaults. Use when dealing with config, configuration, env variables, background variables, fallbacks, or dev philosophy. All configuration must be explicit in .env with .env.example as ground truth.

tankygranny05 Skill

Generate interleaved multi-agent conversation reports organized by theme. Use when user asks for "interleaved conversation", "conversation by theme", "multi agent conversation timeline", or wants to see chronological prompts across agents grouped by user intention.

tankygranny05 Skill

Use this skill when implementing agent spawning in tmux or subprocess, building stream-json SDK integrations, debugging agent startup or resume issues, or understanding centralized logging configuration for Claude Code agents managed by AMS.

tankygranny05 Bundle

Configure OpenCode + opencode-antigravity-auth plugin to use Google OAuth (Antigravity) for free Gemini/Claude usage; includes auth-store gotchas, verified workaround, and troubleshooting with logs.

tankygranny05 Skill

Customize VS Code AI extensions (Claude Code, OpenAI Codex) by replacing bundled binaries with custom versions, configuring executable paths, and enabling multi-instance panels. Use when patching extensions after updates, switching to custom-built binaries, or enabling multiple Codex editor tabs.

tankygranny05 Skill

Safe incremental deployment and updates for the agentic ecosystem after initial setup. Focuses on config preservation, safe service restarts, verification, and optional testing. Use after agentic-ecosystem-remote-deployment has completed at least once.

tankygranny05 Skill

This skill should be used when ensuring Codex emits centralized observability logs (sse_lines.jsonl) while running in app-server mode, especially when used by the VS Code extension.