25,000 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.
Sets up and manages Script Wizard presets — the saved configurations that power the per-preset scripting skills. Use this skill to create a new preset, update an existing preset (voice, standards, style, or publication context), list presets, rename, duplicate, or delete. Triggers on: "set up script wizard", "create a…
A Chinese-language workflow for preparing technical bid documents for government projects. It covers reading tender documents, building a scoring matrix, drafting sections, and checking the final response for compliance.
Given an RFP or security questionnaire and a content library of prior responses, classifies every requirement by type, runs explicit keyword-level verification to prevent fabricated matches, flags non-functional submission constraints, drafts first-pass responses for matched items, and produces a gap list with…
Use this skill as the default entry point when creating, editing, reviewing, migrating, or debugging md-quiz repositories and quiz.md files. It routes quiz content and QML syntax work to qml-authoring, and routes repository structure, md-quiz-repo.yaml, quiz paths, assets, and sync contract work to quiz-repo-spec.
Create or update project documentation. Use when creating architecture docs, runtime docs, reference docs, or design documents that explain what the system does.
Use Obsidian's official CLI to work with a running Obsidian app and its configured vaults. Use for live workspace state, indexed search and metadata, daily notes, tasks, links and backlinks, Bases, templates, bookmarks, plugins, themes, Sync status, and developer inspection. Prefer ordinary filesystem tools when the…
Reader-first writing for any deliverable a human reads to understand a result: HTML reports, MD design docs, debate-result summaries, survey dashboards, executive briefs, handoff notes, panel-review syntheses. Writes for a reader who has NOT read the preceding material. NOT for: bug reports, incident reports, status…
Use Substack's unofficial cookie-authenticated API to read posts, create drafts, publish issues, and manage publications on behalf of a logged-in Substack user. Required when the user asks to post to Substack, schedule a Substack send, mirror content to Substack, or extract data from a Substack account.
Comprehensive SEO content writing and optimization skill based on semantic SEO principles. Enforces 71 rules covering featured snippets, entity optimization, sentence structure, content originality, factual writing, truth ranges, and vocabulary richness. Use when writing, editing, reviewing, or optimizing any web…
Meter Claude Code token usage to your self-hosted Ledger ledger. Each turn's usage is metered at session end so you can see your spend and efficiency (API-equivalent value vs. actual cost) on the Ledger dashboard. Sends token metadata only — never transcript content.
★not rated 6 2mo agoA
tokens not measured
originalMIT
A skill for humanizing Russian-language text. Removes signs of AI generation, makes the text feel alive. ALWAYS use this when the user asks to: humanize a text, remove traces of a neural network, make a text lively/natural, rewrite it like a human, humanize in Russian, remove officialese, remove wateriness/filler…
Write technical and agent-facing text in ASD-STE100 Simplified Technical English. Benchmarked: 95.5% fewer STE violations than baseline across 12 models.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Renwei (人味) — book-length Chinese de-AI editor. Use when editing, polishing, or de-AI-ing Chinese manuscripts, chapters, or articles (.md, .txt), or when the user says their text reads like AI, sounds translated, or feels fake. 51 rules across AI tells, Euro-Chinese syntax, grammar defects, chapter rhythm, whole-book…
Analyse de profil GitHub orientée objectif : eval README, détection marqueurs IA, signaux recruteur, conseils keywords et SEO. Né du live TPC GitHub Roast.
Use when generating documentation from a codebase, creating architecture docs, building an Obsidian vault from code, or when someone asks to document or explain a project's structure.
Progressive disclosure terminal workflow using the Go doc-cli tool to query self-docs over the HTTP API. Use doc-cli search to fetch minimal candidate IDs and snippets, then doc-cli get to retrieve exact chunk markdown.
A response style that gives short, direct technical answers with little filler, inspired by the character Rocky from Project Hail Mary.
★not rated 6 6mo agoB175 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: