claude-skills
AGENTS.md13 starsChanged 8 months agoMITView on GitHub
Precedence: the closest AGENTS.md to the files you're changing wins. Root holds global defaults only. Pulumi IaC and Flux CD GitOps skills for Claude Code. Eight skills: TypeScript, Go, Python, Neo (AI agent), CLI reference, Flux CLI, Flux Operator CLI, Pulumi Labs export. Distributed via Tessl tile (tile.json) and .claude-plugin/marketplace.json.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository9 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- flux-cliSkill
- flux-operator-cliSkill
- pulumi-cliSkill
- pulumi-goSkill
- pulumi-labs-exportSkill
- pulumi-neoSkill
- pulumi-pythonSkill
- pulumi-typescriptSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
Keep SKILL.md concise — detailed content goes in references/
- Distinctive: line 32
No auxiliary files (README.md, CHANGELOG.md) inside skill folders
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- FOR AI AGENTS - Human readability is a side effect, not a goal --><!-- Managed by agent: keep sections and order; edit content, not structure -->AGENTS.md
Precedence: the closest AGENTS.md to the files you're changing wins. Root holds global defaults only.
Overview
Pulumi IaC and Flux CD GitOps skills for Claude Code. Eight skills: TypeScript, Go, Python, Neo (AI agent), CLI reference, Flux CLI, Flux Operator CLI, Pulumi Labs export.
Distributed via Tessl tile (tile.json) and .claude-plugin/marketplace.json.
File Map
| Path | Purpose |
pulumi-{typescript,go,python}/ | Language-specific Pulumi skills (SKILL.md + references/ + evals/) |
pulumi-neo/ | Pulumi Neo AI agent skill (SKILL.md + references/ + scripts/ + evals/) |
pulumi-cli/ | Pulumi CLI reference (SKILL.md + references/ + evals/) |
flux-cli/ | Flux CD CLI reference (SKILL.md + references/) |
flux-operator-cli/ | Flux Operator CLI reference (SKILL.md + references/) |
pulumi-labs-export/ | Autoregistry provider export to pulumi-labs (SKILL.md + references/ + scripts/ + archetype/ + tests/ + evals/) |
tile.json | Tessl tile config (name, version, skill paths) |
.claude-plugin/marketplace.json | Plugin marketplace manifest |
.github/workflows/publish-tile.yml | Publishes tile on push to main via tesslio/publish |
CLAUDE.md | Project instructions for Claude Code |
Conventions
- Keep
SKILL.mdconcise — detailed content goes inreferences/ - "When to use" belongs in frontmatter
description, not the body - No auxiliary files (README.md, CHANGELOG.md) inside skill folders
- Sync versions across
tile.jsonandmarketplace.json
Boundaries
| Rule | |
| Always | Keep SKILL.md focused; detailed docs in references/ |
| Always | Sync versions in tile.json and marketplace.json |
| Ask first | Adding new skills, changing versions, modifying CI |
| Never | Commit secrets in skill content |
| Never | Add auxiliary files inside skill folders |
| Never | Push directly to main |
When instructions conflict
The nearest AGENTS.md wins. Explicit user prompts override files. See also CLAUDE.md.
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.