81,493 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.
Use when working against a test suite, spec, or graded harness you do not own - especially inside an automated loop scored on how many tests pass - and tempted to change the tests, weaken assertions, hardcode expected outputs, special-case inputs, or overfit the visible examples to turn things green.
A universal skill for Claude Code, Minimax Code, and any AI coding agent that accepts markdown skill files. Combines the Fable Brain behavioral prompt (8 modules that fix how a model responds), Karpathy's agent-orchestration mindset and workflow (program.md, AutoResearch, parallel tracks), and 50 production-ready…
A structured way to guide an AI through difficult problems one step at a time, while keeping the problem bounded and allowing earlier judgments to change.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.…
Verified, resumable engineering loops for Claude Code — audit a codebase into an acceptance-gated backlog, route each item to the right model, execute one verified commit at a time.
★not rated 6 4mo agoA
tokens not measured
originalMIT
Evidence-driven acceptance gate for AI-generated software changes. Reviews PRs, migrations, and repos with adaptive scope and issues a PASS / CONDITIONALPASS / FAIL / INCONCLUSIVE verdict backed by verifiable evidence.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Use this skill when the user wants to share, install, inspect, publish, claim, or troubleshoot agent skills with Skilo links, refs, bundles, or tool-native skill directories.
Use when preparing a clean 15-20 min academic talk (journal club, group meeting, seminar, conference talk) from 1-2 source papers, with LaTeX Beamer slides that prioritize white space, sparse text, readable figures, and defensible source attribution. Also use when incorporating recorded talks, videos with captions…
Draft a clean client approval request, set a 48h SLA with a 72h escalation, and track revision rounds so the third billable revision never slips through unbilled.
Write the concept for a demo, guide, walkthrough or site-tour video of an app or any public website — the two documents that get approved BEFORE anything is recorded: PLAN.md (the shape: purpose, audience, beat list, spotlight targets, privacy flags, what is out of scope) and SCRIPT.md (every word in playing order…
Generic multi-domain research framework with domain-aware scheduling. Model-agnostic and domain-agnostic - perform comprehensive research on any topic.
A bilingual English-and-Russian editor and checker for text that sounds machine-generated. It identifies common AI writing patterns and can rewrite them into more natural prose while preserving the meaning.
Collect and download Douyin videos, cover images, direct music audio, and user-page video lists using a local Node.js CLI and SQLite. Use this skill when the user wants to parse a Douyin share link, inspect video quality or cover candidates, download MP4 video, download direct Douyin music audio, collect public…
A report-only audit of a project’s design, files, skills, and progress. It checks whether these parts still agree and runs read-only verification such as builds or commands.
Run vivadicta commands against the user's VivaDicta for Mac history from the shell. Use when picking a subcommand, flag combo, or output format for the vivadicta CLI.
★not rated 6 6mo agoA48 tokens
originalMIT
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: