sharepoint-ai-skills
CLAUDE.md96 starsChanged 3 months agoMITView on GitHub
Demo scripts live at tools/scripts/<demo-name>/<demo-name>.demo. The [var: KEY = value] declarations inside .demo files are defaults only — never edit a .demo file to set a site URL. Site-specific values go in tools/demo.vars.json under overrides["<demo-name>"]: The runner merges demo.vars.json overrides on top of the script's [var:] defaults at load time, so the .demo file stays as a site-agnostic template with CONFIGURE_ME placeholders. The SharePoint agent site context file must be named SHAREPOINT.md — any other name is ignored. Upload it…
In this repository27 other files it gives its agents.
- authoring-sharepoint-markdownSkill
- autoresearchSkill
- brainstorming-design-docsSkill
- copy-editingSkill
- decision-logSkill
- deck-assemblySkill
- design-directionSkill
- executive-summarySkill
- faq-buildingSkill
- find-expertSkill
- forest-styleSkill
- gap-analysisSkill
- hiring-pipeline-reportSkill
- improve-skillsSkill
- ingest-knowledgeSkill
- kb-admin-reportSkill
- linkedin-post-writingSkill
- list-formattingSkill
- log-knowledge-gapSkill
- meeting-notesSkill
- project-briefSkill
- quarterly-expense-reportSkill
- ralph-loopSkill
- site-analyzerSkill
- style-guidelinesSkill
- uppababy-brand-reviewSkill
- youtube-descriptionSkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 46
Every SKILL.md must include valid YAML frontmatter with at minimum these two fields:
- Distinctive: line 62
Before creating or editing a skill, consult the official authoring guide:
- Very specific: line 66
Keep SKILL.md body under 500 lines
- Distinctive: line 69
Use consistent terminology throughout
- Very specific: line 71
Use gerund form for skill names where possible (copy-editing, not copy-editor)
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md — Project Rules
Repo Structure
| Path | Purpose |
Skills/ | All AI skills live here. See Skills/README.md for the full index. |
Skills/<skill-name>/ | Each skill lives in its own folder. The folder name must exactly match the name field in the skill's frontmatter. Contains SKILL.md and optionally references/, scripts/, and assets/ subdirectories per the agentskills.io spec. |
Skills/<skill-name>/SKILL.md | The skill definition file. Required YAML frontmatter (name, description) followed by skill instructions in Markdown. |
demos/ | End-to-end demo setups. Each demo lives in its own subfolder and may include video recordings, scripts, and supporting assets. Not intended for direct reuse — reference and walkthrough material. |
branding.md | Quick-reference brand cheat sheet for the forest-style brand system. Human-readable; not a skill. For the AI-instructional version see Skills/forest-style/SKILL.md. |
Demo Scripts
Demo scripts live at tools/scripts/<demo-name>/<demo-name>.demo. The [var: KEY = value] declarations inside .demo files are defaults only — never edit a .demo file to set a site URL. Site-specific values go in tools/demo.vars.json under overrides["<demo-name>"]:
"overrides": {
"21-knowledge-base": {
"SITE": "https://microsoft.sharepoint-df.com/sites/KnowledgeBaseDemo/"
}
}The runner merges demo.vars.json overrides on top of the script's [var:] defaults at load time, so the .demo file stays as a site-agnostic template with CONFIGURE_ME placeholders.
The SharePoint agent site context file must be named SHAREPOINT.md — any other name is ignored. Upload it to the AgentAssets library root (not inside Skills/).
Skills
Follow the agentskills.io specification
Skills follow the agentskills.io specification. Each skill is a directory inside Skills/ containing a SKILL.md file:
Skills/
└── skill-name/
└── SKILL.md # RequiredThe directory name must exactly match the name field in the frontmatter. For example, a skill with name: copy-editing must live at Skills/copy-editing/SKILL.md.
SharePoint skills cannot write code
Skills in this repo run in SharePoint, which does not support code execution. Skills must be written entirely in prose and Markdown — no code blocks containing executable code, no scripts, no shell commands, no pseudocode intended for execution.
Required frontmatter
Every SKILL.md must include valid YAML frontmatter with at minimum these two fields:
---
name: skill-name-here
description: Third-person description of what the skill does and when to use it.
---Frontmatter rules (enforced by the platform):
name: must match the parent directory name exactly. Lowercase letters, numbers, and hyphens only — no spaces, no uppercase, no consecutive hyphens, max 64 characters. Must not start or end with a hyphen.description: non-empty, max 1024 characters, written in third person ("Processes..." not "I can..." or "You can use this to..."), no XML tags. Include both what the skill does and the trigger conditions that should activate it.
Optional frontmatter fields: license, compatibility, metadata, allowed-tools — see the spec for details.
Follow the official best practices guide
Before creating or editing a skill, consult the official authoring guide: https://agentskills.io/specification
Key points:
- Keep
SKILL.mdbody under 500 lines - Descriptions must include what the skill does AND when to use it
- Be concise — only add context Claude doesn't already have
- Use consistent terminology throughout
- Avoid time-sensitive information
- Use gerund form for skill names where possible (
copy-editing, notcopy-editor)
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.

