AI & ML

block65 Bundle

Wrap up the current session into a complete handover prompt a fresh agent can run with, save it to a file, and copy it to the clipboard so the user can /clear and paste. Use this skill whenever the user says "handover", "hand over to a new agent", "let's handover", "prepare a handoff", "wrap this up for a new session", "I'm going to clear", or otherwise wants to continue this work in a fresh context without losing progress, even if they don't use the word "handover". Accepts an optional steering instruction after the trigger (like /compact takes one), e.g. "handover — just the dragon-hatchery work" or "handover, have the next agent start with the potion tests".

block65 Bundle

Rate the comments and check the changed lines in a diff against the recurring failure modes in agent-written code: narration comments, JSDoc used as an internal note, defensive defaults, sentinels, negated state predicates, magic numbers. Use this skill when the user says 'check my comments', 'rate these comments', 'are these comments any good', 'check the diff', 'diff check', 'did I narrate', 'review my changes before I commit', 'check what I just wrote', or asks whether a comment earns its place. Also use it before reporting a change complete, and when the user complains about comment spam, JSDoc blocks on internal code, or comments explaining code that is no longer there. Pass file paths as args to rate the comments already in those files instead of a diff.

mlops-courses Skill

Structure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free scikit-learn pipelines. Use when exploring a dataset, training a first model, or preparing a notebook for promotion.

mlops-courses Skill

Make an ML system a glass box with reproducible runs, MLflow dataset lineage, drift monitoring, alerting, and SHAP explanations. Use when a deployed model needs traceability, monitoring, alerting, or explanation.

mnemox-ai Bundle

AI trading memory with outcome-weighted recall and autonomous strategy evolution. 17 MCP tools, 1,233 tests, works with any trading platform.

zemloai-ctrl Bundle

Real-time electricity prices and cheapest hours in 40+ countries and regions. Without this, AI agents guess electricity prices. Provides three MCP tools: spot_price, cheapest_hours, best_energy_contract.

oimiragieo Bundle

Use when the user wants to use Claude (Claude Code CLI) for analysis, codebases, or brainstorming from another agent. Uses headless Claude Code CLI scripts (no MCP). Triggers on "use Claude", "analyze with Claude", "ask Claude", "brainstorm with Claude".

mufeedvh Bundle

Explore codebases efficiently with code2prompt, using sem-backed entity maps and grouped source reads to reduce agent round trips. Use when understanding an unfamiliar repository, locating implementations, gathering context for changes or reviews, or installing code2prompt.

snowflake-labs-snowflake-ai-kit Bundle

Auto-routing skill loaded by the prompt filter hook. Routes Snowflake-related operations to Cortex Code CLI. Not for direct invocation — use $cortex-run instead.

syz51 Bundle

PRIMARY tool for fetching library/framework documentation. PROACTIVELY use instead of WebFetch/WebSearch when user requests docs, API references, setup guides, or code examples for any programming library or framework. Use this skill immediately when detecting queries like "show me X docs", "how do I use Y", "get Z documentation", etc. Token-efficient alternative to MCP servers.

demo112 Skill

Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, and deployment.

demo112 Skill

Build AI-powered agents for Solana blockchain — trading bots, DeFi strategies, token analysis, and on-chain automation with TypeScript.

demo112 Skill

Master Cursor IDE with optimal configurations, custom rules, MCP integrations, and workflow patterns that 10x developer productivity.

dotnet Bundle

Generate and maintain .NET release notes from `features.json`. Uses `generate-changes` for authoritative shipped-change data, `generate-features` for scoring/triage, `update-existing-branch` for incremental reruns on populated branches, `editorial-scoring` for the shared rubric, `api-diff` to generate API diff reports and `api-diff-validation` for API verification, and a multi-model `review-release-notes` pass for final editorial QA.

zhizhunbao Bundle

English code comment standards for Python and TypeScript. Use when (1) adding comments to code, (2) standardizing comment format, (3) TypeScript/TSX file header comments, (4) Python module docstrings

yu-iskw-github-project-skills Skill

Synchronizes the list of Agent Skills in the root README.md with the actual skills present in the codebase.

contrast-security-oss Skill

Orchestrate a full release of mcp-contrast end to end, changelog-first. Preflight, deferred-landing changelog draft, version gate, release ticket and branch, smoke test, Gradle Release dispatch and monitoring, artifact verification, release-notes sync, tracker sweep, and Slack announcement. Run when a human asks to cut, make, or ship a release. Human gates at changelog approval, version choice, changelog PR merge, go/no-go, tracker sweep, and the Slack post.

contrast-security-oss Bundle

Pre-release exploratory test of the Contrast stdio MCP server. Builds the jar fresh, wires it into a separate headless Claude instance, and has that instance spawn one subagent per discovered tool to test it against a live org. Run on demand only, before a release or when a human explicitly asks, not during routine feature development. Asks which mode to run if not specified.

rnett Bundle

Using Gradle MCP tools to inspect and run existing builds, including projects, tasks, properties, dependencies, and build results. Activate for Gradle build operation and diagnosis; use authoring-gradle-builds when the build definition itself must change.

rnett Bundle

Ingests a Gradle wrapper upgrade for this repository: reads the release notes, upgrade guides, and linked documentation for the version upgraded to, then updates this repo's own code/tooling and the shipped Gradle MCP skills (src/main/skills/*) so everything stays accurate for that version. ## Positive Triggers (when to activate) - The Gradle wrapper of this repo was just bumped in `gradle/wrapper/gradle-wrapper.properties` (or the bump is in flight) and the new version's implications must be ingested. - Asked to "ingest the Gradle upgrade", "sync the repo/skills with Gradle <version>", or "update our skills/docs for the new Gradle version". - Auditing whether shipped skills, the generated best-practices corpus, or version-sensitive repo code are still accurate after a wrapper upgrade. ## Negative Triggers (when NOT to activate) - Performing the wrapper bump itself (make the upgrade, then come here to ingest it). - Version-sensitive edits to some other project's build (that is the shipped `authoring-gradle-bu

vivalalova Bundle

Use Agent IDE CLI for TypeScript/JavaScript and registered parser-extension code intelligence, dependency analysis, symbol disambiguation, and safe refactoring. Trigger when Codex needs to inspect TS/JS projects, analyze cycles or impact, search symbols, find references with --at, trace call hierarchy with --at, rename safely, move files/directories/members, update imports, change function signatures and call sites, add parameters with distinct call-site values via --call-site-value, detect dead code or remove dead code with --apply, check CLI usage/help, manage index cache with --no-cache/--cache-dir, or verify parser language extension behavior. Matches agent-ide, cycles, impact, search, find-references, call-hierarchy, rename, move, change-signature, deadcode.

vivalalova Bundle

Manual verification workflow for the agent-ide CLI against tests/fixtures. Use when asked to manually test CLI behavior, repeatedly mutate fixture projects, inspect git diff, restore fixtures between cases, cover multiple TS/JS cases, and fix any bug found during fixture-based CLI testing.

incomestreamsurfer Skill

Guide for creating, managing, and using Claude Code Agent Skills. Use when the user asks about Skills, wants to create a new Skill, or needs help with SKILL.md files.

sdi2200262 Skill

Guides an AI agent through customizing APM templates, building releases, and managing a custom APM repository.

sdi2200262 Bundle

Agent communication standards and file-based Message Bus protocol for structured inter-agent messaging.

haibarakiku Bundle

Generate an Abaqus FEA training dataset for surrogate / ML models. Latin Hypercube Sampling (or sparse-pattern sampling) over a parameterized design vector, one case folder per sample, batch-submit Abaqus jobs via subprocess, recover from crashes, and write a unified dataset index. Use when the user wants to "build a training set for a surrogate model", "sweep design parameters in Abaqus", "run N FEA simulations", or "sample a design space".

captkernel Bundle

Use when the user mentions a skill/plugin by name, asks "should I install X", asks for skill recommendations, wants a security check on a skill, asks about duplicates or conflicts, wants to create a new skill, or wants to migrate skills across agent platforms (Cursor, Codex, Gemini, etc.).

captkernel Skill

The intelligence layer for Claude skills — without Python. Maintains a trust-rated catalog (curated entries + live GitHub topic search via curl), identifies what fits your project (stack, deps, CLAUDE.md), recommends with pros/cons and per-project customization advice, persists every decision, and migrates across 55 supported agent platforms. Same model as the full version, no engine — the agent does the work via Bash, Read, Glob, Grep, Write. Use when the user mentions a skill, asks "should I install X", asks to evaluate / recommend / audit / check a skill, asks "what skills fit this project", asks for a list of supported platforms, or wants to migrate skills to another agent. Choose this over the full version when you don't have Python, want zero dependencies, or prefer transparent agent reasoning.

yu-iskw-github-project-skills Skill

Expert triage agent. Use proactively to categorize, label, and assign new issues.

yu-iskw-github-project-skills Bundle

Sets the active GitHub project and repository context by writing a repo-level config file at .github/project-config.json. Run once per repository to eliminate repeated context verification prompts and share the context with all team members via git. All subsequent agent sessions will auto-verify silently against this config.

yu-iskw-github-project-skills Skill

Technical project manager agent. Use proactively to synchronize repository work with GitHub Project boards.

yu-iskw-github-project-skills Bundle

Implements new Agent Skills for the project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI), ensures specification compliance, and provides specialized templates. Use when creating, authoring, or adding a new skill, or when the user asks about Agent Skills format or SKILL.md.

yu-iskw-github-project-skills Bundle

Comprehensive testing suite for GitHub agent skills and subagents. Executes 17 workflows and generates a detailed report.

applied-artificial-intelligence Skill

LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systematic evaluation, or measuring LLM performance.

applied-artificial-intelligence Skill

Comprehensive guide to implementing RAG systems including vector database selection, chunking strategies, embedding models, and retrieval optimization. Use when building RAG systems, implementing semantic search, optimizing retrieval quality, or debugging RAG performance issues.

applied-artificial-intelligence Skill

Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs, implementing NLP tasks, or optimizing transformer inference.