skill-authoring · notivn — Claude Code skill: purpose and installation
skill-authoring is a Claude Code skill that sets the rules for creating and revising skills for AI Edit Video. It activates on requests to write a skill or capture a lesson after a video is finished.
MIT ★ 147 updated 2026-11-13
npx skills add notivn/AIEVv2 --skill skill-authoring -a claude-codeWhat skill-authoring does
skill-authoring defines the SKILL.md layout, frontmatter fields, and writing rules. The description must tell the agent when to load a skill, since Claude makes that choice from the description alone. Lessons use a symptom, its cause, and a fix; debugging history without a reusable conclusion does not belong in the file.
A repeatable video format gets its own skill, while a fix to an established workflow goes into that skill’s known-issues section. Advice limited to one project belongs in its NOTES.md. Skill files are written in English. A skill created through the web UI is returned as a draft for approval before the file is written. After a finished video, the skill calls for recording a new lesson or a step repeated more than twice; a topic should be split when a file grows beyond roughly 200 lines.
What it helps with
- create a skill with the required file structure and frontmatter
- specify the situation that triggers skill loading
- record a fix as a symptom, cause, and remedy
- choose between updating a skill and adding a note to
NOTES.md
Example prompts for the agent
- Create a skill for a new repeatable video format.
- Update the skill after this video with the error’s cause and its fix.
- Draft a skill through the Skills page and return it for approval.
How to install skill-authoring
1Skills CLI (Vercel)
npx skills add notivn/AIEVv2 --skill skill-authoring -a claude-code2Manually: put the files in place
~/.claude/skills/skill-authoring/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/skill-authoring/
1Skills CLI (Vercel)
npx skills add notivn/AIEVv2 --skill skill-authoring -a codex2Manually: put the files in place
.agents/skills/skill-authoring/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add notivn/AIEVv2 --skill skill-authoring -a cursor2Manually: put the files in place
.cursor/skills/skill-authoring/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install notivn/AIEVv2 .claude/skills/skill-authoring2Manually: put the files in place
.github/skills/skill-authoring/SKILL.md1Skills CLI (Vercel)
npx skills add notivn/AIEVv2 --skill skill-authoring -a gemini-cli2Platform CLI
gemini skills install https://github.com/notivn/AIEVv2 --path .claude/skills/skill-authoringManually: put the files in place
.devin/skills/skill-authoring/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about skill-authoring
How do I install skill-authoring in Claude Code?
Run npx skills add notivn/AIEVv2 --skill skill-authoring -a claude-code. The skill file is at ~/.claude/skills/skill-authoring/SKILL.md.
What does skill-authoring do?
It sets the structure and writing standards for AI Edit Video skills, and explains when to create a separate skill versus revising an existing one.
When should a lesson from a finished video become a skill update?
Record a lesson when the work reveals a symptom, cause, and fix. A manual step repeated more than twice is another signal to turn it into a skill.
Source text
SKILL.md · MIT
---
name: skill-authoring
description: 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.
---
# 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
```
```markdown
---
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
1. **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.
2. **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.
3. **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: text` clips the diacritics that sit outside the line-box
- **Fix:** add enough `padding-top` + `line-height` to contain the diacritics, then check the first/last frame of the reveal
4. **Specific beats exhaustive.** A runnable command > a general description. Concrete numbers (CRF 28, volume 0.3, stroke 1.5px) > adjectives ("appropriate", "moderate").
5. **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.
6. **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):
1. Read this skill plus the closest existing skill of the same kind as a template.
2. Write a full `SKILL.md` in English, with complete frontmatter, following the rules above.
3. If the skill relates to Vietnamese-language video: inherit the verified fixes (Vietnamese diacritics, ffmpeg PATH) by reference, do not copy them.
4. 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.
© notivn · MIT · notivn/AIEVv2
Similar skills
All skills for Agent setup: memory, context, orchestration →skill-authoring by other authors comes first.