Agent Skill
Serenity Skill skill
serenity-skillmuxuuu/serenity-skillSKILL.md
Research technology and advanced-manufacturing investments using Serenity-inspired supply-chain bottleneck analysis. Use for theme scans, company thesis challenges, candidate comparisons, or learning this method. Prioritize A-shares unless another market is requested. Return research priorities, dated evidence, profit implications, and conditions that would change the judgment.
always on
68 tokname + description
once used
1,252 tokSKILL.md body
bundled files
141 scripts
repo stars
4.1kGitHub
Install the Serenity Skill skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/muxuuu/serenity-skill --skill serenity-skill
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/muxuuu/serenity-skill.git /tmp/serenity-skill mkdir -p ~/.claude/skills cp -R /tmp/serenity-skill ~/.claude/skills/serenity-skill
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 68 tok |
| When the agent uses it | The SKILL.md instructions | 1,252 tok |
| Only if opened | 14 bundled files (42 KB) | varies |
Until it is used, serenity-skill costs about 20× less than the median MCP server we measured (1,363 tokens on every turn). Skills vs MCP study
Checks
- Ships scripts the agent can run. Read them before installing.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Serenity.skill
- Choose the research task
- Work from current evidence
- Follow the investment logic
- Finish with a usable judgment
- Answer in the user's language
- Examples