AI & ML

aethrox Bundle

Discipline for release classification, version bumps, and changelogs, Conventional Commits classify the release range, SemVer computes the version from those commits, Keep a Changelog renders the result. Use when the user asks to cut a release, bump a version, write a changelog, decide if a change is a major/minor/patch, or choose a branching model for versioned releases.

aethrox Bundle

Classify and structure content going into a document an agent reads (a skill, AGENTS.md, CLAUDE.md, a linked doc) so procedure, facts, and rationale don't get tangled together. Use when creating or editing a skill, or writing/editing AGENTS.md or CLAUDE.md.

chris-mcnulty Skill

How the [YOUR_FIRM] sales harness reads from and writes to Outlook via the Copilot MCP. Composer uses it to save drafts. Cadence uses it to detect sends, detect replies, and queue templated follow-ups. Use when the harness needs to draft a new email, draft a threaded reply, search sent items for a send, scan inbox for a reply, or propose meeting times.

chris-mcnulty Bundle

The canonical list of kill switches every [YOUR_FIRM] sales-harness agent checks at the top of every loop tick and immediately before every send. Use when running the Prospector, Composer, or Cadence skills, or any time before drafting/sending outbound — to confirm no global pause, opt-out, send-cap, or reply-rate floor is active.

phanghonghao Bundle

读取和分析本地图片文件，零 MCP 额度。3级自动降级：Read+PIL增强 → GLM-4V-Flash(免费API) → PaddleOCR(离线)。Use when user mentions: 看图, 读图, 分析图片, 识别图片, img, image, 看一下图片, 图片内容, 截图, screenshot, 照片, photo, 读取图片, image analysis, 明细表, BOM, OCR.

phanghonghao Bundle

Discover trending GitHub repositories across all AI/tech domains. Supports domain-specific browsing: robotics, VLA, agents, MCP, CV, LLM, autonomous driving, 3D, audio, RL, and more. Bilingual output (Chinese + English).

phanghonghao Skill

Local zero-MCP web search & URL reader. Use as the automatic fallback whenever MCP web_search / webReader tools hit rate limits (429 errors, quota exhausted), or proactively for academic/GitHub queries. Routes queries to: arXiv API, GitHub API (gh CLI / curl), Semantic Scholar API, and direct curl page fetch. Trigger when: user mentions 搜论文/查论文/find papers/arxiv/github search, OR when you see "MCP error -429" / "Weekly/Monthly Limit Exhausted" / "webReader_result_summary" with error text.

xmuhameed Bundle

Step-by-step workflow to create a new NestJS backend feature module: Prisma model, DTOs, controller, service, file uploads, auth guards, pagination, soft delete, app.module registration. Use when adding products, categories, coupons, or any new backend resource/module.

jbdamask Bundle

Write a session pass-along document to .pass-along/<YYYY-MM-DD-HHMM>-PASS-ALONG.md capturing operational state — what moved, what is half-done, which loops are still open, and the traps that wasted time — with frontmatter metadata (model, repo, branch, HEAD sha, issue tracker, issues, beads) for the agent that picks the work up. Use when the user says "write a pass-along", "/pass-along", "write a handoff", "hand this off", "I'm wrapping up", "save state for next session", "end of session notes", or is about to stop work, switch machines, or hand a branch to someone else. Also offer one proactively after a significant milestone or when context is about to compact. Companion to the session-recap skill, which reads these.

jbdamask Bundle

Help users evaluate whether an MCP (Model Context Protocol) tool is safe and right for them before installing it. Use when a user wants to check, scan, review, or assess a third-party MCP server from GitHub, npm, or any repository URL. Provides plain-language assessments that anyone can understand, with technical details available on request.

jbdamask Skill

Lints writing for AI slop tells, including overused words, cringe phrases, structural patterns, and bro-speak declaratives that are fingerprints of LLM-generated text. Use this skill any time the user asks to check, clean, lint, or review writing for AI tells, AI slop, cringe phrases, or generic LLM-sounding language. Also use it when the user says things like "does this sound AI-written?", "make this sound more human", "remove the AI vibes", "de-slop this", or "clean up my draft". If the user shares a piece of writing and expresses any concern about it sounding robotic, generic, or artificial, use this skill.

jbdamask Skill

Reconstruct where a coding session left off by reading the latest .pass-along document if one exists, then gathering context from git history, planning docs, task trackers, and past agent chat logs from any supported harness (Claude Code, Codex CLI, Amp, opencode, Grok CLI), then summarizing it as recent activity, current state, active tasks, and likely next steps. Use when the user asks "where were we?", "what were we working on?", "recap the session", "catch me up", "what did I do yesterday", or otherwise returns to a project and needs to resume. Also use when a new conversation looks like a continuation of earlier work.

jbdamask Skill

Generate a succinct, factual, up-to-date company research report ('Company Short') in a fixed Markdown format. Use whenever the user asks to research a company, get a company overview/profile/brief, asks 'what does <company> do', wants competitive or market intel on a business, or invokes 'company shorts'/'company short' with a company name or URL. Covers business model, products, financials, partnerships, market position, customers, and recent news.

jbdamask Skill

Spawn an Opus sub-agent in extended-thinking max-effort mode to debate, critique, and pressure-test the primary agent's current thinking through an unbounded multi-turn dialogue, terminating when the agents either reach genuine consensus or cleanly agree to disagree. Supports escalating clarifying questions to the human user mid-debate, and supports the user sending the debate back for another round (jury-room rule). Use when the user invokes "phone a friend", asks for a "second opinion", "sanity check", "debate this with another model", or otherwise signals they want rigorous adversarial review of an approach, plan, design, diagnosis, or decision before proceeding.

i-onlabs Skill

Debate-Weighted Aggregation council for critical multi-agent decisions. Automatically triggers for security, architectural, and high-risk operations requiring expert deliberation.

thiientv Bundle

Creates or improves an Agent Skill by defining a precise trigger boundary, concise procedural instructions, progressive-disclosure references, deterministic helpers, routing evals, and validation evidence. Use when authoring or reviewing SKILL.md, skill metadata, bundled references, or skill packaging. Not for ordinary project documentation or application code.

thiientv Bundle

Designs or reviews relational, document, key-value, graph, or search data models with ownership, invariants, access paths, migrations, consistency, retention, privacy, and recovery behavior. Use for schema changes, new data stores, indexes, migrations, persistence boundaries, or query-driven design. Not for a query-only bug without a model change or for API contract design.

thiientv Bundle

Designs and runs reproducible evaluations for AI agents, prompts, tools, skills, and model-backed workflows using realistic datasets, isolated baselines, objective assertions, rubric grading, trajectory analysis, cost/latency tracking, and regression comparison. Use when measuring agent quality, optimizing skill triggering, comparing prompts or models, or gating an AI feature release. Not for ordinary deterministic unit tests.

thiientv Bundle

Maps an unfamiliar or large codebase before implementation by locating entry points, ownership, execution paths, conventions, tests, dependencies, change hotspots, and unresolved questions. Use when onboarding to a repository, scoping a cross-cutting change, preparing a handoff or reusable CodeTour, explaining a subsystem, or when the agent is guessing where behavior lives. Not for diagnosing one reproduced failure or designing a new architecture before the current system is understood.

thiientv Bundle

Prepares a focused code review request for a branch, commit, pull request, or substantial working-tree diff by defining the review boundary, contract, risk areas, evidence, and questions for an independent reviewer. Use before merge or when another agent needs to review an implementation. Not for processing feedback already received or for claiming runtime correctness.

thiientv Skill

Splits a coding task into independent parallel agent workstreams with disjoint write sets, explicit inputs and outputs, dependency ordering, and a merge/review plan. Use when several subtasks can proceed without shared mutable state. Not for tightly coupled edits, one failing root cause, or parallel changes to the same files.

thiientv Bundle

Executes an approved implementation plan through fresh implementer and reviewer agents for each task, with explicit handoffs, focused tests, and task-by-task integration. Use for multi-task work where independent agent context improves implementation and review quality. Not for a single small edit, an unresolved design, or a failure that still needs root-cause analysis.

vasuag09 Skill

Produce a phased, risk-assessed implementation plan from a spec. Use after /spec and /research, before writing code. Delegates to the harness-claude:planner agent for non-trivial work.

vasuag09 Skill

Review changed code for quality, correctness, and maintainability before merge. Use immediately after implementing or modifying code. Delegates to the harness-claude:code-reviewer agent. First gate of the Verify phase.

vasuag09 Skill

Feedback step that closes the loop from production back into the harness — take a signal you BRING to it (a pasted stack trace, log snippet, error text, or an issue/monitoring URL), triage it into a located, reproducible failure, and route it into the existing /fix lane. Bring-a-signal only — no polling, no credentials, no new MCP. It locates the failing area and shapes a repro SEED; it does NOT write the finished failing test — that is /fix's job. Opt-in; invoked explicitly. Use when production surfaced something and you want it fixed under the harness's gates.

vasuag09 Skill

Make and record an architecture/design decision for non-trivial work — new subsystems, interfaces, data models, or significant refactors. Use when /plan flags a load-bearing decision. Delegates to the harness-claude:architect agent.

vasuag09 Skill

Resolve build failures and type/compile errors fast, with minimal diffs. Use when a build or typecheck fails during implementation. Delegates to the harness-claude:build-error-resolver agent.

vasuag09 Skill

Execute a plan via test-driven development — write tests first, then minimal code, phase by phase. Use after /plan (and /architect if needed) to write the actual feature. Delegates to the harness-claude:tdd-guide agent.

vasuag09 Skill

Adversarially review a plan against its spec before implementation — check that every acceptance criterion is covered, no scope crept in, and parallel tasks have disjoint write-sets. Use after /plan, before /implement. Read-only gate; delegates to the harness-claude:planner agent in a check pass. Non-blocking except on Critical.

vasuag09 Skill

Remove dead code, duplication, and tech debt safely during the Maintain phase. Use after shipping, or when a codebase has accumulated cruft. Delegates to the harness-claude:refactor-cleaner agent. Behavior-preserving only.

vasuag09 Skill

Security scan of changed code before merge — OWASP Top-10, injection, secrets, access control. Use for any change touching auth, input, queries, file I/O, external calls, crypto, or secrets. Delegates to the harness-claude:security-reviewer agent.

vasuag09 Skill

Orchestrate the MAINTAIN phase — understand the codebase (if unfamiliar) then safely remove dead code, duplication, and tech debt. Use after shipping or on an accumulating codebase. Sequences /onboard and /refactor-clean, delegates to the harness-claude:refactor-cleaner agent, and halts before ambiguous deletions.

naubergois Bundle

Gera demo narrada de app web via AutoDemo MCP (demo_create, session, project.json, HyperFrames). Use when the user asks for autodemo, demo de produto web, MP4 a partir de URL, ou gravar um app no browser sem aula didática.

naubergois Skill

Controla mouse e teclado na tela do Mac como um humano via Touchpoint MCP (e fallback cliclick). Use when the user asks to clicar, digitar, mover mouse, controlar Cursor/Finder/apps, screencast sozinho, computer use, ou desktop automation.

naubergois Skill

MCP PleasePrompto/notebooklm-mcp (arquivado). Login Google no Chrome persistente via setup_auth. Use when the user asks NotebookLM MCP, setup_auth, re_auth, or logar no NotebookLM pelo MCP.

naubergois Skill

Alias — use skill clicar-tela. Controla mouse/teclado via Touchpoint MCP no Cursor.