81,390 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Every skrrt skill in one bundle for the skills.sh CLI: git shipping workflow, structured markdown authoring with auto-fixed lint-clean output, subagent orchestration, design principles, testing discipline, self-documenting code, UI design, and a Claude Code status line. Claude Code installs per bucket instead; see…
★not rated 3
changed 19d agoA
tokens not measured
originalMIT
Reverse-infer OpenSpec specs from this repo's code + git history + local docs (and Jira/Confluence/URLs if available via MCP or host WebFetch). Triggered by /inferspec-scan.
AI-native product development framework. 51 active skills covering the full product lifecycle. FDD+SDD hybrid: 4 living registers, JIT design per feature, atomic commit protocol. Three playbooks: Greenfield, Feature Implementation, Rebuild. From zero to launch.
★not rated 3
changed 1mo agoA
tokens not measured
originalMIT
Fine-tune LLMs using Red Hat training-hub library with SFT, LoRA, and OSFT algorithms. Use when preparing JSONL datasets, running training jobs, configuring hardware, scaling to clusters, evaluating models, or deploying with vLLM.
A communication coach based on Nonviolent Communication, a method for discussing difficult situations by separating observable facts, feelings, needs, and specific requests. It helps turn blame or judgment into clearer, more respectful wording.
A workflow for turning teaching videos and textbooks into a private Markdown textbook, organized by lesson section. It combines source material while preserving only information found in those sources.
Audit a repository or prepare it for an open-source release. Audit mode reports whether the README matches the code and whether stated rules are actually enforced; launch mode walks a repo to release-ready with opt-in checklist packs and README templates. Use when asked to "audit this repo," "is this repo ready to go…
Automatic post-commit code review using OpenAI Codex CLI. After every git commit, Codex reviews the changes and provides a PASS/FAIL verdict. On FAIL, Claude fixes issues and re-commits. On PASS, prompts to push to GitHub.
★not rated 3 3mo agoA
tokens not measured
originalMIT
Create or upgrade an agent skill with SkillsCake. Use when the user wants to improve a skill using SkillsCake, create a skill based on a completed workflow, or says "use SkillsCake".
Initializes a project's SDD (Specification-Driven Development) structure. On an EXISTING project, runs a phased deep analysis with chunking and generates /docs/sdd/ (00-overview to 08-glossary), CONSTITUTION.md and the review rules guide. On an EMPTY project (greenfield), conducts a guided interview about…
A set of rules for how Lume learns lasting preferences and keeps its workspace and conversation files organized. Lume is the application whose configuration and memory it manages.
Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first writing, CVSS 3.1 scoring, title formula, impact statement formula, severity decision guide, downgrade counters, pre-submit checklist. Use after validating a finding and before submitting. Never use…
A set of tools for researching Chinese A-share stocks, including data retrieval, natural-language stock screening, holding analysis, and daily after-market routines. It is described as research software rather than financial advice.
★not rated 3 28d agoA
tokens not measured
originalMIT
Pull the user's live brokerage portfolio (taxable + IRA + crypto) via SnapTrade or Interactive Brokers and produce a deep, position-by-position analysis with an interactive dashboard. Use when asked to analyze "my portfolio", "my positions", "my options", check P/L, review allocation/risk, or get forward guidance on…
A Chinese stock-market review tool that summarizes the day’s market conditions, the strength of a tracked investment theme, and possible breaches of your own holding rules.
★not rated 3
changed 28d agoA
tokens not measured
originalMIT
Validate whether a demand is real before you build it. Frame a falsifiable hypothesis, fan out parallel agents across two pillars (top-down: industry reports / market size / capital signals; bottom-up: Hacker News / App Store reviews / search & social), enforce a 7-axis demand scorecard with ≥2-source triangulation…
Reviews a pull request against its feature doc, ADRs, and domain vocabulary — including terminology drift — and returns findings classed blocker / suggestion / nit / question. Use when asked to review someone else's PR, a Builder's round in tdd-rounds, or your own branch as a last self-check after prod-ready.…
Autonomous software delivery for Claude Code — 8 lifecycle phase skills (auto-spec → auto-ship) plus the loop/verify/checkpoint/budget primitives, with deterministic enforcement hooks and runnable Workflow templates.
AI-Native CLI design spec. Use when building CLI tools, designing command-line interfaces, or scaffolding new CLI projects. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description. Includes an audit protocol for verifying CLI compliance.
Reference skill for Apple WWDC developer sessions (WWDC18–WWDC25). Covers Swift, SwiftUI, SwiftData, Swift Concurrency, UIKit, ARKit, RealityKit, visionOS, Xcode, and all Apple frameworks. Use when asked about Apple APIs, iOS/macOS/visionOS development, WWDC session content, API migration, or any Apple developer…
A command-line tool for checking Taiwanese parcel deliveries by tracking number. It supports several Taiwanese courier services and can show current status, pending parcels, and lookup history.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: