AI & ML

jon-devlapaz Bundle

Scout existing agent skills with evidence before creating one. Use when the user wants the best-supported skill for a workflow, to compare candidates against supplied evidence, or to verify one known skill or repository.

laowang-wy Bundle

Use this skill whenever the user asks to create, build, edit, refine, inspect, or deliver a SketchUp/SU model or architecture scene. It provides managed MCP control, source-based geometry, spatial reasoning, visual review, recovery, and editable SKP delivery.

laowang-wy Bundle

Use this skill whenever the user asks to create, build, edit, refine, inspect, or deliver a SketchUp/SU model or architecture scene. It provides managed MCP control, source-based geometry, spatial reasoning, visual review, recovery, and editable SKP delivery.

babamba2 Bundle

Plugin setup — detect legacy single-profile state (migrate → multi-profile), create or register a SAP connection profile under ~/.sc4sap/profiles/<alias>/, install abap-mcp-adt-powerup MCP server, optionally install DEV-only ZMCP_ADT_UTILS + ZCL_S4SAP_CM_* ALV OOP handlers (tier-gated), register both PreToolUse hooks (blocklist + tier-readonly-guard), optional SPRO / customizations extraction

babamba2 Skill

Guide to install and configure the abap-mcp-adt-powerup MCP server for SAP ADT connectivity

piskie-dev Bundle

Discover, inspect, and safely manage Piskie configuration and capabilities through the stable JSON CLI. Use when a Piskie user wants to read or change persistent settings, inspect models or configuration domains, manage installed Skill/MCP/Plugin capabilities, or install a missing capability that the current task clearly requires.

nowonbun Skill

연결된 SkillPort MCP에서 작업에 맞는 스킬을 검색하고 필요한 본문만 선택적으로 불러올 때 사용한다. 일반 작업이나 MCP 서버가 연결되지 않은 상태에서는 사용하지 않는다.

nowonbun Bundle

SkillPort MCP 사용법

jimmykane Skill

Analyze code quality using ESLint and project-specific patterns

jimmykane Skill

Review Firebase Security Rules and Angular application security patterns

jimmykane Skill

Generate and manage Vitest tests for Angular components, services, and Firebase integrations

jesse-merhi Skill

Transfer the current work to a fresh full agent session, placing related work beside the current session and unrelated asides separately.

babamba2 Bundle

Diagnose SC4SAP plugin health, MCP server connectivity, and SAP system connection (renamed from `doctor` to avoid conflict with Claude Code's built-in `/doctor`)

babamba2 Skill

INTERNAL-ONLY permission bootstrap. Pre-approves Agent dispatch + `.sc4sap/` state-file I/O for the session so parent-skill pipelines run without prompts. SAP MCP handlers are auto-approved by the `permission-approver` PreToolUse hook (except GetTableContents / GetSqlQuery, which stay prompt-gated). MUST be invoked by a parent skill (create-program, setup, team, analyze-*, create-object) — direct user invocation is rejected with a redirect message.

babamba2 Bundle

Direct operational Q&A with a SAP module consultant agent. Auto-routes the question to the matching sap-{module}-consultant and answers against the configured SAP environment (version, industry, country, active modules).

babamba2 Bundle

Read-only, step-by-step root cause analysis for SAP operational errors. Reads the dump summary and failing source via MCP (known-issue web lookup only when the failure is in standard SAP code), widens to transports and where-used only when the clues call for it, narrows hypotheses with minimal user questions, and provides SAP Note search keywords. Never changes code or data.

jimmykane Bundle

Add or materially change a connected fitness-provider integration in Quantified Self. Use for Garmin, Suunto, COROS, Wahoo, or new-provider OAuth, webhooks, activity/history/route/sleep ingestion, delivery, disconnect, provider UI, documentation, and operational coverage.

jimmykane Bundle

Deliver a sports-lib package or parsing-behavior change safely through Quantified Self. Use when a version upgrade, activity or route model change, historical parsing correction, durability input change, or reparse-queue behavior might affect persisted data.

jimmykane Bundle

Compare the user's authorized Quantified Self data across health and fitness domains or relate Timeline notes to recorded trends through read-only MCP tools. Use for sleep versus training, weight versus activity, or Health/Sleep changes around a noted event; use the focused Quantified Self skills for single-domain requests or independent summaries that do not need comparison.

jimmykane Bundle

Analyze the user's authorized Quantified Self sleep data through its read-only MCP tools. Use for sleep sessions, duration, stages, efficiency, naps, bedtime or wake-time patterns, HRV, sleep heart rate, blood oxygen, respiration, and sleep-oriented recovery trends; use the cross-domain Quantified Self skill when comparing sleep with training, measurements, or activities.

jimmykane Bundle

Analyze authorized recorded all-day Quantified Self Health metrics through read-only MCP tools. Use for daily or intraday heart rate, HRV, stress, resources or Body Battery, movement, energy, blood pressure and fitness trends; use the Sleep skill for overnight session vitals and the measurements skill for weigh-ins or body composition.

jimmykane Bundle

Explore the user's authorized Quantified Self saved routes through its read-only MCP tools. Use for route summaries, activity types, route geometry, bounds, segments, waypoints, or finding saved routes near a place or coordinate; do not use saved-route access to answer nearby activity-history questions.

jimmykane Bundle

Analyze one or more authorized Quantified Self activities through its read-only MCP tools. Use for individual workouts, activity tags, activity descriptions, activity summaries, canonical metrics, laps, MTB jumps, swim lengths, pace or power charts, detailed workout samples, interval analysis, breadcrumb traces, or finding activities near a place; use the training skill for aggregate trends across many activities.

jimmykane Bundle

Analyze the user's authorized Quantified Self body measurements through its read-only MCP tools. Use for weight, body mass, weigh-ins, recorded measurement history, rates of change, plateaus, or other discoverable personal measurement trends; do not substitute a current Training-derived snapshot for historical measurements.

rayminliu Bundle

The Chinese formal document compiler — Reference/Spec → Deterministic Document → Evidence. Renders Markdown into properly typeset Chinese formal documents (docx + PDF) with unified validation: 9 automated checks (package integrity, image embedding, TOC fields, page numbering, blank pages, Word acceptance, visual drift), structured report (report.json), and evidence package (screenshots + signature). Use when generating tenders, bids, grant applications, final reports, white papers from Markdown with explicit design contracts (profile.json or ref.docx). Also supports targeted edits to existing docx without re-typesetting. Should not be used for tracked changes, comments, watermarks, theses, or English documents.

jesse-merhi Skill

Audit agent skills: loaded roots, duplicate skills, unused skills, prompt-budget costs, compact descriptions.

tifandotme Skill

Provides the local command contract for HADL database credentials and tunnels. Use when an agent needs to inspect, traverse, or query HADL, Aquasense, Backoffice, staging, production, or windmill databases.

tifandotme Skill

Creates and reviews Agent Skills, including SKILL.md files, frontmatter, references, and scripts. Use when creating or updating an Agent Skill.

tifandotme Skill

Creates and maintains compact AGENTS.md files for repository-specific agent instructions. Use when creating, updating, trimming, refactoring, or auditing AGENTS.md files.

thecolliery Bundle

Verify version-sensitive facts against live authoritative sources before asserting them in code or answers. Triggers on: "/source-grounding", "source-grounding", "sourcing". Standing rule — always active via CLAUDE.md. Invoke for deep verification work (API signatures, CVEs, model IDs, auth flows, deprecated patterns, security advisories).

jesse-merhi Skill

Evidence-backed user corrections or self-detected mistakes revealing reusable agent failures: delegate one systemic-fix recommendation, get approval, then implement it.

jesse-merhi Skill

Write agent-facing skills, AGENTS.md, CLAUDE.md, and linked docs with precise behavioral instructions.

jesse-merhi Skill

Select model-specific writing guidance for another skill, including exact coverage checks, same-family fallback, and one task-wide stale-coverage notice.

jesse-merhi Skill

Query Jira, JPD, and Confluence through local Rovo Dev MCP, including site IDs, JQL, CQL, and boards.

bo2bot-messaging Bundle

Load when the human mentions Bo2bot, a bot inbox, sending a message to another bot or agent, greeting hello@bo2bot.com, or the Bo2bot BBS. Handles login, buckets, mandatory feedback, reply, send, and logout. Do not load for email, Slack, or Perplexity connectors.

repoprompt Bundle

Draft, deduplicate, review, refine, or file maintainer-friendly GitHub issues for RepoPrompt CE from rough notes, investigation findings, or agent context. Use when a user or agent needs a clear RepoPrompt CE issue draft or explicitly requests issue filing.