AI & ML

vishalsachdev Skill

Generate learning science-backed feedback templates for Canvas assignments. Use when educators need feedback templates for grading, want to create rubric comments, need encouraging feedback language aligned with Pillar 3 principles (targeted, encouraging, immediate), or want to set up SpeedGrader comment libraries. Works with canvas-mcp for bulk grading.

aelaguiz Bundle

Query logged-in ChatGPT through BrowserOS after applying $browseros and $prompt-authoring. Use for explicit web consultations, data questions, pushed PR reviews, attachments, or exact conversation continuation. Requires @BigQuery for data and @GitHub for GitHub/repo questions, with actual source access; missing or broken access means switch Pro accounts or stop and tell the user, never accept guesses. Defaults to GPT-6 Astra with literal Pro and Extended thinking in Chat, never Extra High, xhigh, Ultra, or Thinking. Discover the already-open Work and Pro profiles, note and use a working account, and continually verify profile/window/page. Missing Pro probably means a temporary limit; try another account in the same-named project with context carried over. Uses one tab, serial prompts, and a heartbeat during waits. Pause blocked consultation when no suitable account works; continue independent work. Not for API work, generic browser automation, automated login, or scripts.

aelaguiz Bundle

Reclaim substantial disk space on Amir's developer Macs by starting with known worktree, build, cache, and log locations and reusing local cleanup inventories. Use for a full disk, accumulated agent worktrees, routine developer cleanup, or a target such as 1 TB free. Protects canonical checkouts, active work, Git commits, and unique local files; verifies actual free space. Use codex-cleanup for a task confined to Codex SQLite/session maintenance, and arch-docs for stale documentation.

aelaguiz Bundle

Use fal.ai MCP tools or direct fal SDK/API calls to discover or recommend models, inspect schemas and pricing, upload files, run/submit/stream inference jobs, poll results, and handle outputs, errors, cost, and retention. Use for fal.ai tasks such as background removal, image/video/audio/3D/vision generation or editing, and schema-aware request building. Prefer an installed fal.ai MCP server when available and fall back to fal_client or raw HTTP. Do not use for non-fal providers, generic media editing that will not call fal, account administration, or installing/configuring the fal MCP server.

aelaguiz Bundle

Run reusable higher-level Herdr operations that compose multiple session, workspace, pane, and agent steps. Use when the user asks to migrate, copy, transfer, or reorganize a workspace between Herdr sessions while preserving its directory, layout, and exact resumable agent continuity when available. Not for ordinary one-session navigation, splitting panes, creating workspaces, or raw CLI control; use $herdr for those primitives.

ninehills Skill

为任意 coding agent 编写高质量任务目标的指南。当用户提到「设定目标」「goal」「任务目标」「持久目标」「完成标准」、或需要为复杂多轮任务（性能优化、调试、迁移、研究复现等）定义可验证的完成条件和约束时触发。

ninehills Bundle

Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, network topology, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Best suited when the diagram needs custom styling, rich shape vocabulary, swimlanes, or exportable images (PNG/SVG/PDF/JPG). Generates .drawio XML and exports locally via the native draw.io desktop CLI.

mcj-coder Bundle

Use for autonomous agent/human pair programming with the agent as primary implementer and human as supervisor. Enables high autonomy between checkpoints with automated review loops before human review.

mcj-coder Bundle

Use when user integrates agents into repository, asks to set up agent guidance/rules/onboarding, or repo missing agent-specific onboarding docs (AGENTS.md). Ensures fresh agent context can apply all repo standards and external skills.

aelaguiz Bundle

Historical local Codex, Claude Code, Pi, or Prime Agent session evidence: retrieve prior prompts, goals, corrections, tool calls, child-agent briefs, and timelines. Supports natural-language history requests with bundled JSONL/SQLite helpers. Not for live agent status, streaming output, or session control; use the runtime's live interface for those. Defaults to the current project/runtime and last 24 hours.

aelaguiz Bundle

Monitor and keep alive a long codex goal-mode session that is already running in a tmux pane, until codex's own goal genuinely completes. Watch the pane for usage limits, stalls, or process death; on a real usage limit rotate the aim account (`aim status` then `aim codex use <label>`), then kill, restart, and `codex resume <session-id>` the SAME session, clear the 'Resume paused goal?' menu, and verify it ACTUALLY resumed work on the new account; check on a ~15-min cadence via a background poll, never a tight loop. Use when the user says monitor/babysit/watch/keep-running my codex, keep it going across rate limits, or restart-and-resume it when limited. Not for spawning a worker to do a task (`agent-delegate`), running your own goal-seeking loop (`goal-loop`), a one-off codex review (`codex-review-yolo`), or purging ~/.codex state (`codex-cleanup`).

aelaguiz Bundle

Run editful Claude, Codex, Cursor Agent, Grok, or Kimi workers as explicit external processes or resumable sessions with exact model/profile resolution and structured receipts. Use when external transport provides a concrete benefit, such as a different provider, a load-bearing exact model/profile, durable exact-session continuation, process isolation, automation, or captured event/final-output artifacts; these are examples, not a closed gate. Route ordinary same-host work directly to the active host's native children when they can satisfy the role. Use exact handles to resume the same external worker. Not for read-only reviews (`fresh-consult`), Codex `-p yolo` reviews, two-model convergence, ordered orchestration, or detached/background delegation.

aelaguiz Skill

Explicit-invocation fleet debrief, fired only when the user invokes it by name ("check my agents") or directly asks what their running or overnight agent sessions actually accomplished and what is ready or stalled; never self-select it to monitor agents inside other work. Verifies every active or recently finished agent lane from artifacts only (commits, changed files, PR state, CI, worktrees, session transcripts), never from agent self-reports, and returns exactly two lists: merge-ready work with receipts (PR, one-line summary, verdicts, CI state, head SHA) and blocked or stalled lanes with the artifact evidence and the one question or action each needs. A claimed "done" without a diff, test run, or PR is reported as claimed-but-unproven. At most one nudge to a stalled worker, then report; this is a debrief, not a daemon, babysitter, or scheduler. Not for single-session archaeology (agent-history) or monitoring inside an actively conducted fleet (conductor owns its own workers).

ninehills Bundle

生成符合中国专利法规范的专利交底书。接收 Markdown 格式的技术描述作为输入，通过多阶段流水线（标题生成、专利检索、发明目的撰写、发明内容撰写、图表生成、报告合并）自动生成完整的专利交底书。

ninehills Bundle

Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG. Trigger on: "画图" "帮我画" "生成图" "做个图" "架构图" "流程图" "可视化一下" "出图" "generate diagram" "draw diagram" "visualize" or any system/flow description the user wants illustrated.

aelaguiz Bundle

Explicitly selected dialogue between two model participants that independently reason, critique, and converge on a bounded question. Use when the user chooses $model-consensus or binding task instructions require it. Ordinary analysis, review, and a single second opinion do not select multi-model dialogue.

aelaguiz Bundle

Write, edit, refactor, or audit prompt-first agent skills so they stay simple by default, self-contained, anti-heuristic, and distinct from nearby peers. Use when a Codex, OpenClaw, OpenAI, Anthropic, or repo-local skill needs stronger intent, trigger boundaries, packaging, references, runtime metadata, or validation before shipping.

aelaguiz Bundle

Write, edit, refactor, or audit prompts and reusable prompt contracts, including Markdown-backed Codex goal prompt files and paste-sized /goal prompts, so they match the user's intent, evidence needs, constraints, completion rules, and output expectations without becoming brittle or overbuilt. Use for casual prompt-writing asks, system/agent/reviewer prompts, prompt repair, anti-heuristic refactors, and findings-first prompt audits; use $skill-authoring for skill packages.

aelaguiz Skill

Transcribe recorded audio or video speech into a saved plain-text file with the user's OpenAI API access. Use for local M4A, MP3, WAV, MP4, or similar media, especially when the user asks for the latest OpenAI transcription model, long-recording chunking, or explicit parallel processing. Discover the newest eligible model live and adapt to its supported API instead of choosing an older upload model for convenience. Do not use for speech generation, audio editing, summary-only requests, subtitle timing, or live microphone captioning.

aelaguiz Bundle

Invoke the local Codex CLI with the exact external `yolo` profile (gpt-6-astra xhigh, fast tier) and captured receipts for an independent review of a substantial artifact or completion state. Use when the user explicitly asks for `codex -p yolo`, an external Codex review, or the profile's exact model/effort/receipt contract. Ordinary same-host Codex reviews should use a clean native child instead. Review-only; requires a concrete artifact or completion target.

aelaguiz Bundle

Install the early-stage startup operating frame when invoked: reality-check the current plan, answer, or behavior away from proof-maximizing, receipt-building, scope expansion, and decision avoidance, and toward the smallest useful move, decisions at 50-70% of desired information, and rigor spent only where wrongness is expensive. Use when the user invokes startup pragmatism, says the agent is overbuilding, over-proving, being pedantic, or perfection-maximizing, or wants a plan, recommendation, or in-flight work re-checked through the early-stage lens. Output is subtraction and a forced decision: name what gets cut, what gets decided now at current information, and where rigor is still owed. Not for code-defect review, plan-readiness audit, intent drift policing, or genuinely irreversible high-blast-radius moves (prod data mutation, external sends, money, app-store releases), which keep full rigor.

aelaguiz Bundle

Write, edit, refactor, or audit `AGENTS.md` files for coding projects so they stay concise, repo-present, plain-English, command-first, scope-aware, and non-inferable. Use when a repo needs a new root or path-local `AGENTS.md`, an `AGENTS.override.md`, a compressed docs index, or a findings-first review of existing agent instructions.

sandraschi Bundle

Comprehensive MCP server development guide covering FastMCP 2.14.3 features, Anthropic standards, ecosystem integration, and production deployment across all agentic IDEs

barkleesanders Skill

Control the user's local Claude for Life Sciences ("Claude Science" / operon) app from the Claude Code CLI via the `csci` command. Use when the user wants to drive the science app — ask/continue a research conversation with the OPERON agent, list or read projects, pull artifacts/results, inspect the 33 wired connectors (Google Drive, Gmail, Calendar + 24 bio databases like BioMart/PubMed/ChEMBL/ClinVar), check agents/skills/kernels, or search synced data. Triggers: "csci", "claude science", "the science app", "my life sciences app", "ask OPERON", "science project", "localhost:8765", "operon", "run this on my genomics/DNA data". Not for general bioinformatics Q&A (use the app's own agent for that) — this is the control layer.

aelaguiz Bundle

Write Markdown-backed goal prompt files for ArcStep runs from a user ask plus an optional canonical DOC_PATH, especially `$arch-step auto-plan`, `implement-loop`, `auto-implement`, or `full-auto`. Use when the user wants a durable Codex/Claude goal prompt that references source truth without copying the plan, keeps implementation aligned with plan intent, and catches surface-level completion. Not for executing ArcStep itself or creating harnesses, runners, or controllers.

aelaguiz Bundle

Audit and score an agent-definition markdown such as `AGENTS.md`, `CLAUDE.md`, `SKILL.md`, `SOUL.md`, `.cursorrules`, or a system prompt using a cold-reader rubric for clarity, consistency, context independence, operating-model fit, and coherent agent-dispatch semantics when present. Use when the user asks to review, score, critique, or audit an agent instruction file. Not for evaluating agent outputs, code quality, or rewriting the file itself.

aelaguiz Bundle

Keep the parent responsible for requirements, architecture, integration, and direct review while its subagents implement, test, and repair. Used by issue-to-pr and epic-to-prs for Astra or Fable coordinators, or when the user asks for this executive/worker split on accepted work. Astra delegates to GPT-5.6 Sol high; Fable delegates to Opus 5. All skill authorship stays with the parent. Owns execution responsibilities, not a delivery lifecycle, agent launcher, read-only review, or conductor's full workflow.

jankneumann Bundle

Readiness gate for sync-point operations — inspect validation, rework, and active-agent state before merge

jankneumann Bundle

One front door for Langfuse — combines the Langfuse Agent Skill (best practices + docs), the Langfuse CLI (full API surface via npx), and the Langfuse MCP server (native prompt-management tool calls). Use when instrumenting an app, querying or modifying Langfuse data (traces, prompts, datasets, scores, sessions, evals), looking up Langfuse documentation, or configuring Langfuse for a new repo. Routes between Skill knowledge / CLI / MCP based on intent.

jankneumann Bundle

Remediate findings from bug-scrub report — auto-fixes, agent-assisted fixes, and quality verification

barkleesanders Bundle

Set, pause, resume, complete, or clear a persistent per-directory objective (port of Codex `/goal`). Use when the user types `/goal …` or asks to set/check/pause/clear "the goal", "my goal", "the objective", or to wrap up a focused session of work. While a goal is active, a UserPromptSubmit hook injects an anti-completion-bias steering prompt before every turn, and a beads issue mirrors the goal so it shows up in `bd list`. Also absorbs the former /makegoal skill as `/goal make <task>` — fill a build brief, set the goal, decompose into deliverables, optionally fan out parallel agents, synthesize. Triggers: "/goal", "/makegoal", "set a goal", "what's my goal", "pause the goal", "resume the goal", "clear the goal", "mark the goal complete", "is the goal done", "make a goal", "parallel goals", "parallel agents for this task", "build brief".

barkleesanders Bundle

Generate a working CLI from any API, then wrap it in a Claude Code skill. Point it at API docs, a live URL, or a peek-api capture and get a dual-mode Commander.js CLI (human + agent output) plus a ready-to-use skill folder. Use when user wants to wrap an API in a CLI, generate a CLI from API docs, turn an API into a command-line tool, scaffold a CLI from discovered endpoints, or create a skill for an API.

jankneumann Bundle

Generate throughput and quality reports from coordinator audit data and episodic memory

hairyf Bundle

TRON (java-tron) - account model, DPoS, resources, system contracts, TVM, TRC-10/TRC-20, DEX, APIs, events, TronGrid.

barkleesanders Bundle

This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.

jankneumann Skill

Refine a system design or plan to be maximally agent-intuitive, agent-ergonomic, and agent-accretive — grounded in simulated agent journeys and real friction evidence, measured in tool calls and tokens, with falsifiable acceptance probes