4.2K skills · sorted by relevance
Create knowledge references from URLs, documents, or files for use by AI agents. Fetch, process, and store structured references in the configured references directory (default: .ai-factory/references/).
The English summary is being prepared. Showing the original description.
Create knowledge references from URLs, documents, or files for use by AI agents. Fetch, process, and store structured references in the configured references directory (default: .ai-factory/references/).
The English summary is being prepared. Showing the original description.
Use when the user asks to "build a win-back campaign", "re-engage lapsed subscribers", "run a re-permission / re-consent sweep", or "sunset my dead list"; produces a closed-loop reactivation program — a lapsed-cohort definition, a staged offer ladder, a re-consent (re-permission) capture step, and a sunset-confirm / suppression rule. Owns none of the SEND-N sub-item notes: engagement-decay / sunset is email-sequence-designer's and preference-center / frequency options is preference-frequency-manager's — this skill references those notes, it does not re-emit them. Not for the general lifecycle flows (welcome/cart/post-purchase) — use email-sequence-designer; not for the preference-center / opt-down ladder — use preference-frequency-manager; not for the consent record itself — use consent-registry; not for computing EQS or the N1 veto — use email-quality-auditor. 流失召回/重新授权/沉默用户清理
The English summary is being prepared. Showing the original description.
Add GitHub permalinks with fixed SHA/commit references to research documentation containing code snippets. Use when writing technical docs with code examples, creating investigation/research docs that reference source files, user asks to "add permalinks" or "add GitHub links", documenting code research findings with file:line references, or creating audit trails needing permanent code references. Triggers on "add github links", "add permalinks", "link to source", "make code references permanent".
The English summary is being prepared. Showing the original description.
Add a standard GNOME preferences dialog (AdwPreferencesDialog) with Ctrl+comma shortcut, PreferencesPage/Group rows, and GSettings bindings. Use when adding settings or preferences UI to a GNOME app.
The English summary is being prepared. Showing the original description.
既存スキルの references / samples / scripts が公式ドキュメントの最新版に追従しているか確認し更新するワークフロー。 reference-updater Agent で差分検出し、必要なファイルを更新して CLAUDE.md まで反映する。 「<library> のスキルを最新化して」「リファレンスを更新して」などで使用。
The English summary is being prepared. Showing the original description.
Repair and verify cross-references between SKILL.md files after a skill is created, renamed, removed, or restructured. Ensures every skill that calls another skill references the correct name, and every skill that is called has accurate "Called by" context. Load after universal-skill-creator creates a skill, after improve-skills completes a cycle, after a skill is renamed or removed, or when the user asks to fix cross-references, sync skill links, repair broken skill references, update skill cross-links, check skill references, or "are cross-links correct".
The English summary is being prepared. Showing the original description.
Requires OFOX_API_KEY — create one at https://app.ofox.ai, plus a publicly reachable reference video the user is authorized to use. Use when a user has a rough 3D white-model, clay, wireframe, blockout, previs, or animatic clip and wants a finished visual treatment that preserves its shot order, cut timing, camera framing, spatial layout, and motion directions. Distinguishes that structure-preserving job from a continuation beginning at the reference's final state. Do not use for two still endpoints (keyframe-animation), for appending and locally joining a new ending (video-extend-edit), or when still-image references must be combined with the video in one request — first/last-frame anchors conflict with video references in the shipped core, while mixed image/video references are untested.
The English summary is being prepared. Showing the original description.
Review deployment evidence and recovery conditions when assessing a release. The skill directs the agent to consult the accompanying restore reference and include a timestamp in its decision, providing a narrowly defined release review procedure.
Create and edit images or generate short videos with xAI Grok. The skill explains how to write prompts, combine source images, assign reference images to video roles, and check generation progress before downloading results.
Work with Zotero desktop through a command-line interface to inspect references and collections, generate citations and bibliographies, add notes, and assemble structured information for further AI analysis.
Control a running iTerm2 workspace from the command line. Inspect processes and directories across panes, send commands, read terminal history, arrange windows and tabs, and manage preferences or tmux integration.
Combine laboratory animal welfare measurements into reference-relative RELSA severity scores. Analyze individual trajectories, explore forecasts for specified observation times, and derive candidate score zones, with explicit checks on normalization, reference selection, prediction intervals, and evaluation limits.
Prepare genomic interval data for machine learning by checking BED files, reference genome consistency, and model compatibility. Plan Region2Vec or scEmbed workflows and assess shared reference regions using local validation and planning helpers.
Find animation, short-video, and motion-effect references on 1human, including items saved in a shared human-agent library. Review sources and licenses to guide creative work, and publish creations only within the owner's explicit permission.
Turn recurring procedures and specialized knowledge into reusable agent skills. It guides the design of SKILL.md, scripts, reference documents, and output assets, then validates the structure and packages the files for distribution.
Connect ViewModels, objects that manage screen state and actions, through messages without direct references. The skill covers event broadcasts, requests for values, window-specific channels, and recipient registration and cleanup using CommunityToolkit.Mvvm.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Create academic Word documents with APA, Chicago, IEEE, or MLA citation formatting. Organize abstracts, equations, figure and table references, footnotes, and bibliographies, with support for two-column journal layouts in a single .docx file.
Extract references between imported documents and classify how they relate, such as relying on, extending, or refuting another work. Store these relationships as typed links so explicit graph queries can trace connections through the collection.
Create or improve a company-specific data analysis skill by gathering analysts’ knowledge and examining database structures. Document business terms, metric formulas, table relationships, and common query patterns in reusable reference files.
Create, update, validate, and reorganize Agent Skills stored in a repository. It covers SKILL.md metadata, reference files, compatibility links, and validation scripts, supporting maintenance of skill folders, categories, and instructions for agents.
Turn repeated workflows into reusable Picoclaw skills, or update and review existing ones. Organize SKILL.md instructions, scripts, reference documents, and output assets, then check the structure and test representative tasks.
Produce videos in Hypit by interpreting briefs and references, generating images, video, and audio, and combining them with supplied material. The workflow covers composition, caption timing, review in Studio, export, and service setup.