New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Per Concept Documentation

by MicrosoftDocs in MicrosoftDocs/semantic-kernel-docs

Required when reviewing, updating, auditing, or creating any concept documentation page.

OfficialMITAuto-check passedAI & LLM Engineering

Install Per Concept Documentation

skills CLI
$ npx skills add MicrosoftDocs/semantic-kernel-docs --skill per-concept-documentation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MicrosoftDocs/semantic-kernel-docs per-concept-documentation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MicrosoftDocs/semantic-kernel-docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/per-concept-documentation .claude/skills/per-concept-documentation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
per-concept-documentation
GitHub stars
264
Token cost
~1k tokens
SKILL.md length
506 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Required when reviewing, updating, auditing, or creating any concept documentation page.

  • Works in 11 steps: Identify the concept for which the user… → Gather information about the concept.… → If the concept is already documented,… → …
  • AI & LLM Engineering work in your project
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Per Concept Documentation is an agent skill from MicrosoftDocs/semantic-kernel-docs, published by the product's own GitHub organization. Required when reviewing, updating, auditing, or creating any concept documentation page. Covers code accuracy checks against source repos, language parity across zone pivots, parity table comments, and structural consistency.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering. It works with GitHub. The repository describes itself as: Semantic Kernel (SK) is a lightweight SDK enabling integration of AI Large Language Models (LLMs) with conventional programming languages. The licence is MIT.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “/per-concept-documentation”

Requirements

  • Python 3

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. Identify the concept for which the user is seeking new or updated documentation. This could be a feature, function, class, or any other…
  2. Gather information about the concept. Ask the following questions if they are not already answered
  3. If the concept is already documented, review the existing documentation to identify any gaps or areas that need updating. If the concept…
  4. Documentation follows the format of the existing documentation in the project. Ensure that the new or updated documentation is consistent…
  5. If code snippets are needed, refer to the "code-snippets" skill for guidance on how to create code snippets in the documentation.
  6. Verify code accuracy against source. For each language zone, compare the documented APIs (class names, method signatures, imports…
  7. Check language parity. If the documentation covers multiple languages via zone pivots, compare the sections side by side to ensure each…
  8. Add a parity comment. Insert an HTML comment immediately after the YAML frontmatter containing the language parity table. This table…
  9. Resolve parity gaps. For each missing section identified in the parity table, determine whether it should be added (the concept exists in…
  10. Treat each language zone as an isolated document. Do not compare or contrast one language's implementation with another within the zone…
  11. Update the date. After making changes, update the ms.date field in the YAML frontmatter to the current date.

What it can do on your machine

Read from SKILL.md and the folder at commit 6997e10. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are html).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Per Concept Documentation loads about 1k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 506 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from MicrosoftDocs/semantic-kernel-docs at commit 6997e10, republished under its MIT licence (© MicrosoftDocs). 506 words, ~1,018 tokens.

Download SKILL.mdSave it as .claude/skills/per-concept-documentation/SKILL.md (or your agent's skills folder).
name
per-concept-documentation
description
Required when reviewing, updating, auditing, or creating any concept documentation page. Covers code accuracy checks against source repos, language parity across zone pivots, parity table comments, and structural consistency.

To create or update documentation for a specific concept in the project, follow this process:

  1. Identify the concept for which the user is seeking new or updated documentation. This could be a feature, function, class, or any other relevant topic within the project. The project can be either Agent Framework or Semantic Kernel.

  2. Gather information about the concept. Ask the following questions if they are not already answered:

    • What is the concept?
    • What language does it pertain to (e.g., Python, .NET, or both)?
    • The code path to the concept (this is usually a link to the source code in GitHub).
    • Samples of how to use the concept, if applicable.

  3. If the concept is already documented, review the existing documentation to identify any gaps or areas that need updating. If the concept is not yet documented, proceed to create new documentation (ask the location where the documentation should be created if not already defined).

  4. Documentation follows the format of the existing documentation in the project. Ensure that the new or updated documentation is consistent with the style and structure of the existing documentation.

  5. If code snippets are needed, refer to the "code-snippets" skill for guidance on how to create code snippets in the documentation.

  6. Verify code accuracy against source. For each language zone, compare the documented APIs (class names, method signatures, imports, parameters) against the current source code in the corresponding GitHub repository. Use GitHub search and file retrieval tools to check the actual source files, not just samples.

  7. Check language parity. If the documentation covers multiple languages via zone pivots, compare the sections side by side to ensure each language covers the same set of concepts. Build a parity table listing each section and whether it is present for each language. Identify:

    • Sections present in one language but missing in another.
    • Language-specific features that are intentionally only in one zone (mark these explicitly).
    • Differences in depth or structure for the same concept across languages.

  8. Add a parity comment. Insert an HTML comment immediately after the YAML frontmatter containing the language parity table. This table should be maintained as sections are added or removed. Use ✅ for included concepts, ❌ for excluded concepts, and add a notes column for explanations (e.g., "Python-specific"). Example:

    html
    <!--
  Language parity table – keep in sync when adding/removing sections.

  | Section                    | C# | Python | Notes           |
  |----------------------------|:--:|:------:|-----------------|
  | Basic Structure            | ✅ |   ✅   |                 |
  | Function-Based             | ✅ |   ✅   |                 |
  | Explicit Type Parameters   | ❌ |   ✅   | Python-specific |
  | The Context Object         | ✅ |   ✅   |                 |
-->

  9. Resolve parity gaps. For each missing section identified in the parity table, determine whether it should be added (the concept exists in the other language's SDK) or marked as language-specific. Add equivalent sections where appropriate, mirroring the structure and depth of the existing language zone.

  10. Treat each language zone as an isolated document. Do not compare or contrast one language's implementation with another within the zone content itself. For example, avoid phrases like "Unlike C#, Python does not use a RequestPort" or "the same guessing game workflow." Each zone pivot should read as a standalone document that makes sense without any knowledge of the other language's zone.

  11. Update the date. After making changes, update the ms.date field in the YAML frontmatter to the current date.

© MicrosoftDocs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/per-concept-documentation of MicrosoftDocs/semantic-kernel-docs.

Open the folder on GitHubat commit 6997e10

Compare with similar skills

Per Concept Documentation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Per Concept Documentation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Per Concept Documentation this skillMicrosoftDocs/semantic-kernel-docs264—~1kAutomated safety check: PassMIT
TriageTalAter/annyang6.8k—~810Automated safety check: NotesMIT
Esmfold2JimLiu/science-skills2274 repos~2.5kAutomated safety check: PassApache-2.0
Create Simple Promptpnp/copilot-prompts891—~2.6kAutomated safety check: PassMIT
Issue Workflow Guardrailkxn/codex-remote-feishu328—~1.3kAutomated safety check: PassNone
Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel1.3k—~1.1kAutomated safety check: PassCustom licence

Similar skills

  • Triage

    TalAter/annyang

    Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.

    6.8k GitHub stars~810 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    227 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Create Simple Prompt

    pnp/copilot-prompts

    This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…

    891 GitHub stars~2.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Issue Workflow Guardrail

    kxn/codex-remote-feishu

    A skill your agent uses when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots…

    328 GitHub stars~1.3k tokensUpdated 6 days ago
    AI & LLM EngineeringAuto-check passed

  • Gptqmodel Tokenizer Normalization

    ModelCloud/GPTQModel

    Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.

    1.3k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Token Meter Communication

    splunk/token-meter

    A skill your agent uses when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication.

    110 GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from MicrosoftDocs/semantic-kernel-docs

  • Breadcrumbs

    MicrosoftDocs/semantic-kernel-docs

    Official

    How breadcrumbs work on Microsoft Learn: structure, creation, configuration in docfx.json, and best practices for documentation repos.

    264 GitHub stars~1.7k tokensUpdated 5 days ago
    Auto-check passed

  • Code Snippets

    MicrosoftDocs/semantic-kernel-docs

    Official

    How to reference code from sample repos in Agent Framework docs pages using :::code directives, snippet tags, zone pivots, and highlight attributes.

    264 GitHub stars~1.4k tokensUpdated 5 days ago
    Auto-check passed

  • Cross Repository References

    MicrosoftDocs/semantic-kernel-docs

    Official

    How to configure cross-repository references (CRR) and create API class links for Microsoft Learn docs in this repository.

    264 GitHub stars~1k tokensUpdated 5 days ago
    Auto-check passed

  • Redirection

    MicrosoftDocs/semantic-kernel-docs

    Official

    How to delete, rename, or move articles on Microsoft Learn while preserving Platform IDs, preventing broken links, and managing redirects.

    264 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed

  • Sample Structure

    MicrosoftDocs/semantic-kernel-docs

    Official

    Conceptual organization of Agent Framework documentation and samples.

    264 GitHub stars~1.4k tokensUpdated 5 days ago
    Auto-check passed

  • Toc

    MicrosoftDocs/semantic-kernel-docs

    Official

    How to create, structure, and configure table of contents (TOC) files for Microsoft Learn documentation using toc.yml and docfx.json.

    264 GitHub stars~2.2k tokensUpdated 5 days ago
    Auto-check passed

Works with

Categories

Questions about Per Concept Documentation

What does Per Concept Documentation do?

Required when reviewing, updating, auditing, or creating any concept documentation page. Per Concept Documentation is an agent skill from MicrosoftDocs/semantic-kernel-docs, published by the product's own GitHub organization. Required when reviewing, updating, auditing, or creating any concept documentation page.

When should I use Per Concept Documentation?

Per Concept Documentation fits situations like: AI & LLM Engineering work in your project.

How do I install Per Concept Documentation in Claude Code?

Run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill per-concept-documentation -a claude-code`. Or copy the skill folder (.github/skills/per-concept-documentation in MicrosoftDocs/semantic-kernel-docs) into .claude/skills/per-concept-documentation in your project. Claude Code loads it when a task matches its description.

How do I install Per Concept Documentation in Codex?

Run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill per-concept-documentation -a codex`. Or copy the skill folder (.github/skills/per-concept-documentation in MicrosoftDocs/semantic-kernel-docs) into .agents/skills/per-concept-documentation in your project. Codex loads it when a task matches its description.

Can I use Per Concept Documentation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill per-concept-documentation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/per-concept-documentation, .gemini/skills/per-concept-documentation, .github/skills/per-concept-documentation and .opencode/skills/per-concept-documentation in your project.

What does Per Concept Documentation need to run?

SKILL.md names no scripts, command-line tools or credentials: Per Concept Documentation is instructions for the agent only. Our summary lists: Python 3.

Does Per Concept Documentation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Per Concept Documentation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Per Concept Documentation use?

Per Concept Documentation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Per Concept Documentation use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Per Concept Documentation?

Skills that share tags, products or a category with Per Concept Documentation: Triage (TalAter/annyang, 6.8k stars), Esmfold2 (JimLiu/science-skills, 227 stars), Create Simple Prompt (pnp/copilot-prompts, 891 stars) and Issue Workflow Guardrail (kxn/codex-remote-feishu, 328 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Per Concept Documentation?

MicrosoftDocs (a GitHub organization, an official publisher) maintains it in MicrosoftDocs/semantic-kernel-docs, which has 264 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 2, 2026.

Source: MicrosoftDocs/semantic-kernel-docs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.