Loading...
Loading...
Found 977 Skills
MITRE ATT&CK mapping discipline and technique reference for OpenTide TVM, DOM, and MDR objects — technique vs sub-technique selection, tactic assignment, multi-technique chaining, version pinning, revocation handling, coverage gap analysis, platform matrix awareness, and a locally searchable technique index. Use when populating threat.att&ck fields in TVMs, mapping DOM signals to techniques, tagging MDR rules, assessing detection coverage against the ATT&CK matrix, or looking up technique IDs and descriptions.
Draft PR titles and descriptions from local git history.
Publish confirmed final-cut videos to platforms such as YouTube, Douyin, WeChat Channels, and Xiaohongshu. Used when users say “publish the video, sync publishing, upload to YouTube, post to Douyin/WeChat Channels/Xiaohongshu, schedule publication,” etc. Verify the video version, cover, subtitles, title and description, and AI/copyright declarations for each platform, then generate a per-platform publishing package. Only after the user grants authorization for each platform may the video be uploaded through a runtime-available official API, form-filling assistant, or upload tool as private, a draft, or scheduled. It never mass-publishes with one click. When upload capability is unavailable, deliver a manual publishing package.
Draft, edit, review, and refine all human-facing writing, from short-form copy to connected prose. Use it whenever readers must follow ideas, context, reasoning, narrative, or tone. Use it across technical surfaces such as package and repository descriptions, README and technical document content or information architecture, CLI wording, JSDoc and docstrings, explanatory source comments, runtime messages, test titles, labels, and repository collaboration through issues, pull requests, and Discussions. Do not use for LICENSE text, formatting-only work, or tasks that neither evaluate nor change wording or information architecture. Agent responses are not a trigger on their own.
Use this skill to write package release notes, changelog entries, and hosted release descriptions from supplied drafts or verified changes, or to review release copy for completeness, consistency, and wording. The work can cover a commit, commit range, pull request, branch, tag, diff, or every change since the latest release. Do not use it for ordinary commit summaries unless they are intended for use in release notes or a changelog.
Audits and fixes both halves of being found — classic search and AI answers. Search side: rankings, site structure, page speed, titles and descriptions, and content that answers what customers search for. AI side: whether assistant crawlers can reach the site, pages render without JavaScript, an llms.txt file, schema.org data, and presence in the directories assistants read. For online stores it also runs a bulk catalog cleanup, rewriting product titles, descriptions, alt text, and SEO fields in approved batches. Works on any public website with no connector. Use this whenever the owner talks about being found online, including "nobody finds us on Google," "how do I show up in ChatGPT," "make my website AI friendly," "SEO audit," "GEO," "AEO," "AI search visibility," "my competitor ranks above me," "fix my product listings," or "I asked an AI about my industry and we weren't in the answer."
Index of all COSS UI particle examples. Use when implementing UI features to find copy-paste-ready component patterns built on coss primitives. Each particle has a description and a JSON URL for easy installation.
Use this skill when users want to report, collect, organize, classify, or standardize issues encountered while using AI tools. It applies to any scenario, including coding Agents, chat assistants, office assistants, search, writing, data analysis, and internal AI systems. The skill converts free-form descriptions into structured feedback reports with clear issue categories, tags, severity, scenarios, impacts, and suggestions for additional information.
Documentation knowledge correctness validation. Inspect whether the technical descriptions in OpenHarmony API documentation are consistent with authoritative standards and specifications (W3C, CSS, etc.), mathematical definitions, or industry facts. When a knowledge issue is found, further compare it against the implementation code to distinguish a "documentation error," a "code implementation error," or an inconsistency across all three. Trigger phrases: documentation description validation, documentation knowledge correctness, whether a description is accurate, parameter description validation, documentation correction, and documentation-to-code comparison.
Prepare Roblox games for publishing and discovery. Use for icon, thumbnail, name, description, store copy, launch positioning, genre fit, CTR improvement, first impression review, and pre-launch page readiness.
Writes short product copy: headlines, titles, meta and store descriptions, buttons, empty states, error messages, subject lines, CTAs. Use when asked for such copy.
Helps the user make their own Claude Code skill for editing videos, step by step. Interviews them briefly (what the skill does, an example video, what good looks like), runs the task once without a skill to see what goes wrong, writes three test scenarios, drafts the SKILL.md to the skill-authoring guide (clear name, a description that says what and when, a checklist, a check-and-fix loop, one example), saves it to their skills folder, tests it against the scenarios in a fresh agent, and improves it with them. Skills made here plug into cooked. (the edit folder, the review page, the safe zone) and can run as a style. Use when the user says "make a skill", "create a skill", "turn this into a skill", "help me write a skill" or "build my own editing skill". Not for adding rules to a skill that exists from a video's notes (skill-improver), and not for copying a creator's style from their videos (creator-teardown).