AI & ML

pproenca Bundle

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.

1055373165 Bundle

Full-lifecycle autonomous development agent. User provides a requirement or refactoring plan, and the agent drives the entire flow: requirement locking → architecture design → tech spikes → task decomposition → MDU execution → review → delivery. Use when asked to "autopilot this", "build this feature end-to-end", "run the full dev workflow", "autonomous development", or when a user provides a requirement and wants hands-off execution. Proactively suggest when the user describes a multi-step feature, refactoring plan, or says "I want this built automatically".

delorenj Bundle

Operate the Skillex registry at ~/code/skillex: curate all-skills/ and sets/, author/verify sealed packs, and resolve global or project .agents/skills.json manifests. Use for skillex vendor or pack commands, packs[] versus skills[] precedence, pack.toml, SHA256SUMS, inherit_global, provision-packs.py, sync-skills.py, and pj skills.project-manifest failures. Do NOT use for fan-out engine mechanics (agent-config-fanout), SKILL.md content (skill-creator), repository ignore/index parity (gitignore-maintenance), PJangler implementation (project-jangler), project bootstrap (33god-projects), or the Hermes runtime skill overlay (agent-fleet-operations).

langchain-ai Bundle

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: create a skill, make a skill, build a skill, set up a skill, initialize a skill, scaffold a skill, update or modify an existing skill, validate a skill, learn about skill structure, understand how skills work, or get guidance on skill design patterns.

ledgerhq Skill

Multi-agent code review before opening a PR. Surfaces critical issues, suggestions, and improvements.

mewishu Bundle

Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.

scylladb Bundle

Multi-agent code review for Python projects. Use when reviewing local uncommitted changes, pull request diffs, or when asked to do a code review. Dispatches specialist agents (bug-hunter, security-auditor, test-coverage, code-quality, contracts, historical context) and aggregates results with confidence scoring.

the-vibe-company Bundle

Mega Code Review: independent local code review for any repository. Use when the user asks to review code, validate local changes, run a pre-commit or pre-PR check, inspect uncommitted changes, review a branch against a base branch, review a commit, perform a security/design-quality pass, coordinate isolated sub-agents/sub-reviewers, or decide whether a change should block merge. Defaults to launching an isolated primary review agent with minimal context to avoid polluting the main conversation, then reports read-only, evidence-backed P0-P3 findings plus non-committable local review artifacts.

10k-digital Skill

Provider-neutral project context for Lovable.dev repositories. Use when initializing, inspecting, or modifying a Lovable project, detecting Vite SPA versus TanStack Start, reading `.lovable-agent` configuration, or generating agent instruction shims for Codex, Claude Code, and other agents.

jacbk Bundle

AI assistant framework for building unique, authentic portfolio websites from scratch. Guides agents through research, design, and implementation phases.

krusemediallc Skill

Use when the user wants to reverse-engineer an existing image ad into a reusable prompt template. Validates via KIE.ai — picks gpt-image-2 (`/gpt4o-image/generate`) or Nano Banana (`/jobs/createTask`) at Phase 1. Triggers on "clone this ad as a template", "reverse engineer this ad", "turn this ad into a prompt", "extract a template", "make this ad reusable", "add to my prompt library", "study this ad and make a template". Input is an EXISTING ad image (must be at a public URL); does NOT trigger for fresh generation (use chatgpt-image-ad or nano-banana-image-ad).

mrclrchtr Bundle

Check for available upgrades to the pi coding agent framework by comparing the current `@earendil-works/pi-*` or legacy `@mariozechner/pi-*` version in package.json against releases on `earendil-works/pi`. Use this skill whenever the user asks to upgrade pi, update pi, check pi changelogs/releases, or migrate off the deprecated `@mariozechner/*` packages.

1yihui Bundle

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

jwynia Bundle

Bootstrap, maintain, and evolve context networks across their full lifecycle. Use when starting a new project, when existing documentation feels scattered, or when agent effectiveness degrades due to missing context.

sprngr Bundle

Meta-skill: apply rubber-duck enforcement to any agent session. Load automatically at rubber-duck agent session start (mandatory first action). Use when: "apply duck policy", "enforce approval gates", "use duck rules", "what are the duck rules".

bazylrei Bundle

Hand the current conversation off to a fresh background agent that picks up the work immediately.

architektapx Skill

Extract durable working preferences from recent agent chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.

gentleman-programming Bundle

Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.

jal-co Skill

Git and GitHub CLI mastery for version control operations. Use proactively for commits, branches, PRs, rebases, conflict resolution, and git history management. Covers conventional commits, branching strategies, and GitHub workflows. Examples: - user: "Commit these changes" → stage files, create conventional commit - user: "Create a PR" → push branch, write a short body per <pull-requests>, gh pr create - user: "Rebase on main" → fetch, rebase, handle conflicts - user: "Fix merge conflict" → identify conflicts, resolve, complete merge - user: "Squash my commits" → interactive rebase guidance - user: "What's the git history?" → git log with appropriate flags

purpleailab Skill

Auto-loaded by reentrancy-auditor agent during Phase 2. Provides detection patterns for: CEI violations, cross-function/cross-contract reentrancy, read-only reentrancy, token callback exploits (ERC721/777/1155). Core artifact: State Timeline map.

purpleailab Skill

Auto-loaded by access-control-auditor agent during Phase 2. Provides detection patterns for: missing modifiers, privilege escalation, tx.origin phishing, OR/AND logic errors, missing two-step transfer. Core artifact: Permission Matrix.

datadog-labs Skill

Diagnose and fix Single Step Instrumentation (SSI) issues on Linux hosts — SSI automatically instruments applications for APM without code changes. Only use if the agent and SSI are configured but traces are missing or instrumentation is not working.

datadog-labs Skill

Generate a live Single Step Instrumentation (SSI) onboarding confirmation report for Linux hosts — verifies APM instrumentation is working end-to-end with deep links into the Datadog UI. Only use after agent-install and enable-ssi have both completed.

nanocoai Skill

Install and initialize OneCLI Agent Vault. Migrates existing .env credentials to the vault. Use after /update-nanoclaw brings in OneCLI as a breaking change, or for first-time OneCLI setup.

nanocoai Bundle

Use OpenCode as an agent provider. OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per group via `ncl groups config update --provider opencode`; host passes OPENCODE_* and XDG mount when spawning containers.

ravnhq Bundle

Detect bundled dev work — multiple implementation tasks in one prompt — and dispatch each as an isolated agent (own session, own cwd, scoped tools, awaited), classifying dependencies so independent tasks fan out in parallel and dependent ones run in order. Use when a prompt bundles two or more dev tasks like "generate test cases and create the PR", "bug report and test plan", "do X and Y in parallel", or explicit /orchestrate. Opt into worktree mode via "--worktree" (or "in a worktree", "isolated branch", "auto-merge to main") to provision an integration branch off the protected base (develop/dev preferred; else newer main/master tip), spawn one worktree per task off that branch (parallel for independent, waves for soft-sequenced, merged-into-one for hard-chained), and hand off to agent-pr-creator for the protected-base PR. Resolves issue-tracker tickets (Linear, Jira, GitHub Issues, Notion) via MCP and uses the ticket id as the integration branch name. Skip for single-task asks, questions, or info requests.

hkuds Skill

Deep research framework for pre-IPO / private companies (Ant Group, SpaceX, Stripe, ByteDance...). Six analyst lenses — business model, financial forensics, competitive landscape, risk & governance, tech & IP, alternative-data signals — run in parallel via run_swarm, then cross-validated for signal consistency before any verdict. Built around the core challenge of private-company work: information is scarce, so every data point carries a confidence label (high / medium / low), inference is shown separately from fact, and 'I don't know' is a valid output. Outputs a fair-value range, exit-path analysis, and an information-gap map. Use for any unlisted company where you need to judge what the business is actually worth.

modu-ai Skill

Test pyramid strategy, coverage targets, test patterns, and quality metrics reference. Agent-extending skill that amplifies manager-develop test-creation and quality-validation work with production-grade testing patterns. NOT for: production code implementation, architecture design, DevOps, security audits.

rivet-dev Bundle

agentOS: A computer for every agent.

nvidia Bundle

Set up NeMo Curator for data curation (text, image, video, audio)

do1e Bundle

Agent Skill

getzep Skill

Use when deciding whether to search Zep memory for user preferences.

spikesubingrui-design Bundle

把 Obsidian 变成 OpenClaw memory + gbrain 知识图谱的可视化 GUI：单 vault、wikilink 图谱、 memory 日记软链、DB 页面物化导出，编辑仍回灌 sync/embed；可选升华候选队列把日记里反复出现的 话题提议成图谱页面；v1.2 附策展宪法（给写图谱的 agent 的系统提示词：收录三问／分类 rubric／ 页面密度标准／重铸模板／问答回流）；v1.3 附检索流水线（关键词+向量双引擎 RRF 融合／时间衰减／ MMR 去冗／一跳图扩展，配评测集把召回从 0/10 修到 10/10）。触发词：obsidian脑库 / 第二大脑可视化 / gbrain obsidian / memory图谱 / 连点成面 / second brain vault / 知识策展 / 图谱堆积 / 召回 / 检索融合 / RRF

sprintberlin Bundle

Use Zoho CRM via MCP; run safe record workflows, COQL, select Actions, and report reproducible skill defects to GitHub.

starhui-dev Bundle

Use this skill when the user wants to inspect or change Huly data from the terminal using huly-cli through npx, including projects, issues, statuses, labels, fulltext search, or raw huly-mcp tool calls. Use for Huly task triage, issue updates, project lookup, and agent-safe Huly automation.

stijnswapped Bundle

Run an authorized, local-first application security assessment on the current project using this agent's own reasoning. Use when the user invokes Myrqen, asks to security-test or pentest the app they are building, asks whether their app has real vulnerabilities before shipping, wants a Myrqen finding validated, or wants a Myrqen remediation applied and retested.