Org Skills
Why instructions

Your coding standards, applied to every line the AI writes

Instructions are short, always-on rules for a type of file — React components, C# services, Apex classes. The assistant applies them automatically, even to quick "vibe coding" requests, so code follows your standards without anyone having to ask.

The problem

Standards only work if someone remembers them

Casual prompts, generic code

Quick requests like "add a page that lists orders" get the most common pattern online, not your team's — especially in fast, exploratory vibe coding.

The same review comments, again

Reviewers repeat "use the repository pattern", "no secrets in config", "parameterise that query" on pull request after pull request.

One huge instruction file

Teams cram every rule for every stack into one file. The assistant reads all of it on every request and the important rules get lost.

How it works

Short rules, scoped to the files they apply to

Each instructions file declares which files it covers (for example **/*.tsx). The assistant loads it only when it works on matching files — nothing to invoke, nothing to remember.

  1. 1You edit or create a file

    For example a React component, a .NET controller or an Apex trigger.

  2. 2Matching rules load automatically

    Copilot uses applyTo; Claude Code uses the same globs as rule paths. Other stacks' rules stay out of the way.

  3. 3Code follows your standards

    The assistant writes to the rules — and points to the full skill when a task needs more depth.

Benefits

What teams get

Nothing to invoke

Rules apply automatically to matching files. Developers get the standard without knowing it exists.

Safe for vibe coding

Quick, casual prompts still produce code that follows team conventions, security rules and patterns.

Fewer repeat review comments

The things reviewers say every week are written down once and applied before the pull request is opened.

Security baseline everywhere

The secure-coding rules cover every file: no secrets in code, parameterised queries, authorisation checks, no PII in logs.

Right rules for the right files

React rules for components, .NET rules for C#, Apex rules for triggers — scoped, so the context stays small and relevant.

Same rules in Copilot and Claude Code

One source file; the Claude Code rule is generated from it, so teams on either tool follow the same standards.

Consistent across teams

Every repository that installs the instructions follows the same baseline, which makes code easier to move between.

Evolve with your stack

When a framework or standard changes, one pull request updates the rules for every team.

Example

Same request, with and without instructions

Prompt: Add an endpoint that returns a customer by ID.

Without

  • Builds SQL with string concatenation
  • No authorisation check on who may read the customer
  • Logs the full customer record, including personal data
  • Returns stack traces to the caller on errors
  • A reviewer has to catch all of it

With .NET + Secure coding instructions

  • Uses parameterised queries through the data layer
  • Checks the caller may access that customer
  • Logs identifiers only, never personal data
  • Returns a standard problem response without internals
  • Follows the project structure the team agreed

Illustrative example based on the .NET and secure coding instructions. Results depend on the tool, the model and the codebase.

When to use what

Instructions, skills or agents?

UseWhenExample
InstructionsRules that should apply every time a file type is touchedNaming, patterns, security basics for C# files
SkillsA deeper playbook for a specific task, loaded when relevantDesigning a .NET architecture, writing a test strategy
AgentsA repeatable workflow with its own tools and output formatPlanning a work item, reviewing a pull request
Impact

How to show it's working

Measure a baseline before rollout, then compare after a few sprints. These are the signals that move first — track them per team, not per person.

MeasureWhy it matters
Repeated review comments per PRThe clearest sign the rules are being applied.
Security findings in AI-assisted changesThe secure-coding baseline should reduce routine findings.
Lint and type errors in first commitsStandards applied at write-time mean fewer fix-up commits.
Repositories with instructions installedCoverage across teams — the baseline only helps where it is installed.
Who benefits

Useful at every level of the team

Developers

Write to the standard without memorising it — including during quick prototyping.

Reviewers

Stop repeating the same comments and focus on logic and design.

Security & architecture

A baseline that reaches every repository and every assistant.

Teams switching stacks

The right rules load automatically for whichever code they touch.

Get started

Pick the instructions your team needs

Each item in the catalog has copy buttons and install steps for GitHub Copilot and Claude Code.