skill-authoring
Skill136 starsChanged 16 days agoMITView on GitHub
The standard for writing new skills for the AI Edit Video system - file structure, frontmatter, tone of voice, and how to accumulate production lessons into skills. Read when the user asks to create a new skill (via chat or from the Skills page in the web UI) or when updating a skill after finishing a video.
89 other projects use a version of this.
Adopted by
Most recently taken up by
- neuroborus/agent-runnertheir own version, first seen Nov 8, 2026
- juninmd/skillstheir own version, first seen Nov 8, 2026
- TrueImmortal82/open-code-skillstheir own version, first seen Nov 8, 2026
- patrykmurzyn/skillstheir own version, first seen Nov 8, 2026
- frnkgns/Overgeared-Skillstheir own version, first seen Nov 8, 2026
- github/plugin-marketplace-startertheir own version, first seen Nov 8, 2026
Used with
Projects with it also use cloud-api-recipe-authoring, codebuddy-ide-mcp-upgrade and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TencentCloudBaseSkillcloud-api-recipe-authoring
Author or revise a cloud-api-operations recipe (config/source/skills/cloud-api-operations/references/recipes/). Encodes why the long tail of control-plane capabilities is deliberately NOT wrapped as MCP/CLI tools, the API-first admission test for whether a capability deserves a recipe, the negative and positive lists, the fixed recipe structure, the writing rules distilled from writing-for-agents, the user-facing copy red lines, and the product regeneration/verification pipeline. Also routes contributors (and their agents) to the contribution flow and the pre-PR self-test protocol in references/contributing.md. Use when adding a recipe, judging whether a scenario belongs in the recipe set, updating the recipes index, re-checking existing recipes against the admission test, or onboarding someone who wants to submit one.
Also in 3 projects that use this
TencentCloudBaseSkillcodebuddy-ide-mcp-upgrade
升级 CodeBuddy IDE(genie 扩展)内置的 CloudBase MCP,以及 MCP 发版时同步 IDE 侧白名单。当用户提到「更新 IDE 里的 MCP」「内置 MCP 版本太老」「IDE 集成的 CloudBase 功能不足」「改工具白名单 toolWhiteList」「把新 bundle 打进 CodeBuddy」「白名单漂移」「MCP 发版要同步什么」时使用。覆盖:解包定位内置 bundle 与内嵌配置、重新构建 mcp bundle、生成新的工具白名单与系统提示词、安全注入 IDE 并备份、用 MCP 协议验证工具清单、人工端到端验收、一键回滚。
Also in 3 projects that use this
DIL8654Skillapi-contract-review
Review ASP.NET Core Web API contracts for HTTP semantics, versioning, backward compatibility, and response consistency. Use when the user asks to review an API, check endpoints, validate REST behavior, or before releasing contract changes.
Also in 5 projects that use this
zaxbysauceSkillpr-review-fix
Codex adapter for addressing pull request review feedback in opencode-swarm. Use when the user asks to fix PR review comments, requested changes, reviewer findings, CI-review notes, or a pasted review summary with low false-positive tolerance.
Also in 3 projects that use this
albertdobmeyerSkillgit-workflows
Advanced git operations beyond add/commit/push. Use when rebasing, bisecting bugs, using worktrees for parallel development, recovering with reflog, managing subtrees/submodules, resolving merge conflicts, cherry-picking across branches, or working with monorepos.
Also in 3 projects that use this
rogue-dev-studioSkillfrontend-engineering
Expert frontend application engineering: accessible UI structure, state and data-fetching discipline, form/validation UX, responsive layouts, performance budgets, and integration with API contracts. Use when building or refining SPA/web screens, design-system consumption, client-side routing, or fixing UI reliability (loading, empty, and error states).
Also in 3 projects that use this
- +6 more from TencentCloudBase
Other versions89 projects use a version of this.
Word for word · 1
- notivn/AIEV★ 132100% same
Edited · 0
None found.
Wrote their own version · 88
- nyldn/claude-octopus★ 4.4ksame name
- endurain-project/endurain★ 2.4ksame name
- joaovitoriasilva/endurain★ 2.4ksame name
- theopenco/llmgateway★ 1.7ksame name
- TencentCloudBase/CloudBase-AI-ToolKit★ 1.2ksame name
- TencentCloudBase/CloudBase-MCP★ 1.2ksame name
- TencentCloudBase/CloudBase-AI-Toolkit★ 1.2ksame name
- pockebot/openpocket★ 847same name
- QuixiAI/agi-memory★ 623same name
- QuixiAI/Hexis★ 623same name
78 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-illustrationsSkill
- auto-cutSkill
- background-musicSkill
- color-gradingSkill
- gsapSkill
- hyperframes-cliSkill
- hyperframes-registrySkill
- hyperframesSkill
- key-layoutSkill
- make-a-videoSkill
- noti-tiktok-full-textSkill
- noti-tiktok-vnSkill
- noti-youtube-editSkill
- offline-voiceSkill
- remotion-assembleSkill
- short-form-videoSkill
- video-pipelineSkill
- website-to-hyperframesSkill
- webui-designSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 79 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Write for the next use, not as a souvenir: Every section must answer "what do I do differently next time".
- Very specific: line 35
Fix: add enough padding-top + line-height to contain the diacritics, then check the first/last frame of the reveal
- Distinctive: line 51
When the user creates a skill through the Skills page (describing it in their own words, often in Vietnamese):
- Distinctive: line 52
Read this skill plus the closest existing skill of the same kind as a template.
- Very specific: line 53
Write a full SKILL.md in English, with complete frontmatter, following the rules above.
- Distinctive: line 54
If the skill relates to Vietnamese-language video: inherit the verified fixes (Vietnamese diacritics, ffmpeg PATH) by reference, do not …
- Distinctive: line 59
Ask yourself: is there a new symptom -> cause -> fix?
“Common” is measured: kept by at least 6 in 10 of the 79 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Authoring - writing skills the right way
Skills are where production know-how accumulates. A good skill makes the next video automatically better than the last one without having to repeat anything in chat.
Required structure
.claude/skills/<name-kebab-case>/
└── SKILL.md---
name: <matches the folder name, kebab-case>
description: <1-2 sentences: what the skill does + WHEN to use it. Claude decides whether to load the skill from this line alone - be specific, include keywords>
---
# Title
<skill body>Writing rules
- The description decides everything. Claude only sees the description when choosing a skill - it must spell out the trigger situation: "Read when...", "Use when the user provides...". A vague description = a skill that never gets used.
- Write for the next use, not as a souvenir. Every section must answer "what do I do differently next time". Do not transcribe debugging history - keep only the conclusion + how to apply it.
- Every fix needs its recognition condition. The standard template for a lesson:
- Symptom: Vietnamese gradient text loses its diacritics on the reveal frame
- Cause:
background-clip: textclips the diacritics that sit outside the line-box - Fix: add enough
padding-top+line-heightto contain the diacritics, then check the first/last frame of the reveal
- Specific beats exhaustive. A runnable command > a general description. Concrete numbers (CRF 28, volume 0.3, stroke 1.5px) > adjectives ("appropriate", "moderate").
- Write skills in English; keep code/commands/technical names as-is. Do not translate technical terms (frame, render, timeline...). Vietnamese strings that are literal data (sample captions, UI labels, on-screen text) stay verbatim.
- One skill, one topic. Split a skill once it grows past ~200 lines. Reference other skills by name (
see the remotion-assemble skill) instead of copying content across files.
When to CREATE a new skill vs UPDATE an existing one
| Situation | What to do |
| A new repeatable video format (e.g. product comparison video) | Create a new skill, cloned from the closest existing one |
| Fixing a bug in a workflow that already has a skill | Update that skill, in its "Known issues" section |
| A new aesthetic/brand rule | Update webui-design (UI) or the relevant video format skill (video) |
| Knowledge that only applies to one specific video | DO NOT put it in a skill - write it in that project's NOTES.md |
Creating a skill from the web UI
When the user creates a skill through the Skills page (describing it in their own words, often in Vietnamese):
- Read this skill plus the closest existing skill of the same kind as a template.
- Write a full
SKILL.mdin English, with complete frontmatter, following the rules above. - If the skill relates to Vietnamese-language video: inherit the verified fixes (Vietnamese diacritics, ffmpeg PATH) by reference, do not copy them.
- Return it to the UI as a draft for the user to approve before writing the file.
After every finished video
Ask yourself: is there a new symptom -> cause -> fix? Was there a step done manually more than twice (the sign it should become a skill)? If so, update the skill in that same session - do not defer it to the next one.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

