Agent skill

Add Function

by microbus-io in microbus-io/fabric

TRIGGER when user asks to add, create, or modify an API endpoint, function, or RPC, or a route that accepts typed arguments and returns typed results.

Apache-2.0Auto-check passedBackend & APIs

Install Add Function

skills CLI
$ npx skills add microbus-io/fabric --skill add-function -a claude-code

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

GitHub CLI
$ gh skill install microbus-io/fabric add-function --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/microbus-io/fabric.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/microbus/add-function .claude/skills/add-function && 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
add-function
GitHub stars
172
Token cost
~2.4k tokens
SKILL.md length
1,155 words
Files
1
Skills in repo
32
Repo updated
First seen
Licence
Apache-2.0

At a glance

TRIGGER when user asks to add, create, or modify an API endpoint, function, or RPC, or a route that accepts typed arguments and returns typed results.

  • Works in 11 steps: Read Local CLAUDE.md File → Determine the Signature → Determine the Method and Route → …
  • User asks to add
  • Calls go
  • Modify an API endpoint

What it does

Add Function is an agent skill from microbus-io/fabric. TRIGGER when user asks to add, create, or modify an API endpoint, function, or RPC, or a route that accepts typed arguments and returns typed results.

Its SKILL.md is about 2.4k 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 Backend & APIs, covering REST APIs and Microservices. The repository describes itself as: Microbus is the only fabric where every agentic workflow runs on a true microservice substrate - giving your workflows security, scale, observability, and prompt-driven authoring. The licence is Apache-2.0.

When your agent uses it

  • User asks to add
  • Modify an API endpoint
  • A route that accepts typed arguments and returns typed results

Example prompts

  • “/add-function”

Workflow steps

11 steps, taken from the step headings in SKILL.md.

  1. Read Local CLAUDE.md File
  2. Determine the Signature
  3. Determine the Method and Route
  4. Determine a Description
  5. Determine the Required Claims
  6. Define Complex Types
  7. Declare the Endpoint in definition.go
  8. Generate the Boilerplate
  9. Implement the Logic in service.go
  10. Test the Function
  11. Housekeeping

What it can do on your machine

Read from SKILL.md and the folder at commit fb98098. 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

    Shell commands in SKILL.md call:

    • go

    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

Add Function loads about 2.4k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 1,155 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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 microbus-io/fabric at commit fb98098, republished under its Apache-2.0 licence (© microbus-io). 1,155 words, ~2,389 tokens.

Download SKILL.mdSave it as .claude/skills/add-function/SKILL.md (or your agent's skills folder).
name
add-function
description
TRIGGER when user asks to add, create, or modify an API endpoint, function, or RPC, or a route that accepts typed arguments and returns typed results.

CRITICAL: Do NOT explore or analyze other microservices unless explicitly instructed to do so. The instructions in this skill are self-contained to this microservice.

CRITICAL: A functional endpoint is declared as a define.Function var in myserviceapi/definition.go and implemented as a handler in service.go. Add the declaration and run cmd/genservice.

CRITICAL: Keep the // MARKER: MyFunction comment on the define.Function var and on its In/Out structs. They are waypoints for future edits.

Workflow

Copy this checklist and track your progress:

Creating or modifying a functional endpoint:
- [ ] Step 1: Read local CLAUDE.md file
- [ ] Step 2: Determine the signature
- [ ] Step 3: Determine the method and route
- [ ] Step 4: Determine a description
- [ ] Step 5: Determine the required claims
- [ ] Step 6: Define complex types
- [ ] Step 7: Declare the endpoint in definition.go
- [ ] Step 8: Generate the boilerplate
- [ ] Step 9: Implement the logic in service.go
- [ ] Step 10: Test the function
- [ ] Step 11: Housekeeping
Step 1: Read Local CLAUDE.md File

Read the local CLAUDE.md file in the microservice's directory. It contains microservice-specific instructions that should take precedence over global instructions.

Step 2: Determine the Signature

Determine the Go signature of the functional endpoint.

go
func MyFunction(ctx context.Context, input1 string, input2 ThirdPartyStruct) (output1 map[string]MyStruct, err error)

Constraints:

  • The first input argument must be ctx context.Context
  • The function must return an err error
  • Maps must be keyed by string, e.g. map[string]any
  • Complex types (structs) are allowed by value or by reference, e.g. MyStruct or *MyStruct
  • All input or output arguments must be serializable into JSON, including complex types
  • Arguments must not be named t or svc
  • Argument names must start with a lowercase letter
  • The function name must start with an uppercase letter
  • A return argument named httpStatusCode must be of type int
  • If the return argument httpResponseBody is present, no other return argument other than httpStatusCode and error can be present
  • The magic HTTP argument names httpRequestBody, httpResponseBody and httpStatusCode are documented in the rules file under "Magic HTTP Arguments"
Step 3: Determine the Method and Route

The method of the endpoint determines the HTTP method with which it will be addressable. Unless there's a reason to use a specific method, like for a REST API, use ANY to accept requests with any method.

The route of the endpoint is resolved relative to the hostname of the microservice to determine how it is addressed. The common approach is to use the name of the endpoint in kebab-case as its route, e.g. /my-function.

To set a port other than the default 443, prefix the route with the port, e.g. :1234/my-function.

Encase path arguments with {} , e.g. /section/{section}/page/{page...}.

Prefix the route with // to set a hostname other than that of this microservice, e.g. //another.host.name:1234/on-something

Step 4: Determine a Description

Describe the endpoint starting with its name, in Go doc style: MyFunction does X. This becomes the godoc comment on the define.Function var.

Describe what the endpoint does and the effect it produces, not who is expected to call it. "Charges the card and returns a receipt id" is good; "called by the LLM as a tool" or "used by the checkout page" is not.

Do not write per-argument descriptions in the godoc. Put them in jsonschema_description:"..." tags on the In/Out struct fields (Step 7).

Step 5: Determine the Required Claims

Determine if the endpoint should be restricted to authorized actors only. Compose a boolean expression over the JWT claims associated with the request that if not met will cause the request to be denied. For example: roles.manager && level>2. Default to closed: in a standard ingress configuration an empty requiredClaims on a :443 endpoint (or any port the operator added to AllowedInternalPorts) is reachable by the entire internet. Leave it empty only for an intentionally public endpoint; if the endpoint wields a stored secret or a privileged side effect, it must be gated by requiredClaims and/or an internal port. See the Ports and Authentication sections of .claude/rules/microbus.md.

Step 6: Define Complex Types

Identify the struct types in the signature and define each in the myserviceapi directory following the add-type skill: one file per type, camelCase json tags with omitzero, jsonschema_description tags, optional dv8 validation tags, and an optional pure Validate method for cross-field invariants. A type owned by another microservice is aliased rather than redefined. Skip this step if there are no complex types.

Show full SKILL.md (524 more words)Show less
Step 7: Declare the Endpoint in definition.go

Append the define.Function var and its In/Out structs to myserviceapi/definition.go.

go
/*
MyFunction does X.
*/
var MyFunction = define.Function{ // MARKER: MyFunction
	Host: Hostname, Method: "ANY", Route: "/my-function",
	In: MyFunctionIn{}, Out: MyFunctionOut{},
}

// MyFunctionIn are the input arguments of MyFunction.
type MyFunctionIn struct { // MARKER: MyFunction
	Input1 string           `json:"input1,omitzero" jsonschema_description:"Input1 is X"`
	Input2 ThirdPartyStruct `json:"input2,omitzero" jsonschema_description:"Input2 is X"`
}

// MyFunctionOut are the output arguments of MyFunction.
type MyFunctionOut struct { // MARKER: MyFunction
	Output1 map[string]MyStruct `json:"output1,omitzero" jsonschema_description:"Output1 is X"`
}
  • Host is always Hostname. Method and Route come from Step 3. Set In and Out to the In/Out struct literals (MyFunctionIn{}, MyFunctionOut{})
  • The In struct holds the input arguments excluding ctx; the Out struct holds the output arguments excluding err. Use PascalCase field names and camelCase json tags with omitzero
  • In struct fields may carry dv8 validation tags (see the add-type skill); they are enforced automatically after decoding, rejecting an invalid payload with 400 Bad Request before the handler runs. Tags on Out struct fields are inert
  • For a magic HTTP argument (httpRequestBody, httpResponseBody, httpStatusCode), set the field's json tag to -. A jsonschema_description tag still applies to a body field (HTTPRequestBody/HTTPResponseBody) and describes the whole body payload in the OpenAPI doc, e.g. `json:"-" jsonschema_description:"The object to create"`
  • If an In/Out field's type comes from another package (e.g. a time.Time field needs "time"), add that import to definition.go
  • Add the gating and routing fields only when needed:
    • RequiredClaims: "roles.manager && level>2" for the claims from Step 5 (omit when public)
    • TimeBudget: 30 * time.Second to cap the handler's duration (omit for the default; add the time import if used)
    • LoadBalancing: define.None to multicast to all replicas, or LoadBalancing: "my-queue" for a named queue; omit for the default hostname queue (load-balanced among peers)
Step 8: Generate the Boilerplate

From the microservice's directory, run the generator. It regenerates myserviceapi/client.go, intermediate.go, mock.go, mock_test.go, and manifest.yaml from the updated definition.go. It also scaffolds a placeholder handler in service.go and a placeholder test in service_test.go for any new feature that lacks one, each ready for you to fill in.

shell
go run github.com/microbus-io/fabric/cmd/genservice .

Then verify the microservice compiles with go vet ./... from the project root.

Step 9: Implement the Logic in service.go

The previous step generated a placeholder handler func (svc *Service) MyFunction(...) in service.go, with the signature and godoc projected from definition.go, tagged // MARKER: MyFunction and holding a // TODO: Implement MyFunction body. Replace that body with the handler's logic. Leave the generated signature and godoc as they are: they are the contract from definition.go, so if the signature is wrong, fix definition.go and regenerate rather than editing service.go. Complex types refer to their definition in myserviceapi. Add imports for any packages the body references that are not already imported (e.g. "time" for a time.Time value).

Step 10: Test the Function

Skip this step if instructed to be "quick" or to skip tests.

The boilerplate generator created a placeholder test function TestMyService_MyFunction in service_test.go, tagged with a // MARKER: MyFunction comment and a HINT block. Add one or more test cases at the bottom of that function, following the pattern shown in its HINT comment. Do not remove the HINT comment.

If the feature or microservice cannot or should not be tested - for example, it starts a daemon or requires a resource unavailable in the test environment - do not delete the generated test. The generator keys on the test function's name and would scaffold it again on the next regeneration. Instead, replace the entire body of the test with a t.Skip("reason") explaining why.

Step 11: Housekeeping

Follow the housekeeping skill.

© microbus-io, Apache-2.0. 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 .claude/skills/microbus/add-function of microbus-io/fabric.

Open the folder on GitHubat commit fb98098

Compare with similar skills

Add Function 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.

Add Function compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Add Function this skillmicrobus-io/fabric172—~2.4kAutomated safety check: PassApache-2.0
Nodejs Backend Patternsever-works/ever-works15818 repos~4kAutomated safety check: PassAGPL-3.0
Dr Jskilljdubois/dr-jskill342—~4.6kAutomated safety check: NotesApache-2.0
Hybrid Cloud Test Gengetsentry/sentry46k—~2.6kAutomated safety check: PassCustom licence
API Gatewayitsmostafa/aws-agent-skills1.2k1 repos~2.2kAutomated safety check: PassMIT
Vss Deploy Detection Tracking 2DNVIDIA/skills3.5k1 repos~4.5kAutomated safety check: PassApache-2.0

Similar skills

  • Nodejs Backend Patterns

    ever-works/ever-works

    Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices.

    158 GitHub starsUsed in 18 repos~4k tokens
    Backend & APIsAuto-check passed
  • Dr Jskill

    jdubois/dr-jskill

    Creates Java + Spring Boot projects: Web applications, full-stack apps with Vue.js or Angular or React or vanilla JS, PostgreSQL, REST APIs, and Docker.

    342 GitHub stars~4.6k tokensUpdated 8 days ago
    Backend & APIsAuto-check: notes
  • Hybrid Cloud Test Gen

    getsentry/sentry

    Official

    Generate hybrid cloud tests for the Sentry codebase. An agent skill from getsentry/sentry.

    46k GitHub stars~2.6k tokensUpdated today
    Backend & APIsAuto-check passed
  • API Gateway

    itsmostafa/aws-agent-skills

    AWS API Gateway for REST and HTTP API management. An agent skill from itsmostafa/aws-agent-skills.

    1.2k GitHub starsUsed in 1 repo~2.2k tokens
    Backend & APIsAuto-check passed
  • Official

    A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.

    3.5k GitHub starsUsed in 1 repo~4.5k tokens
    Backend & APIsAuto-check passed
  • API Design Interviewer

    PrepLabsAI/InterviewMentor

    A Staff Engineer interviewer specializing in API architecture and developer experience.

    112 GitHub stars~2.6k tokensUpdated yesterday
    Backend & APIsAuto-check passed

More from microbus-io/fabric

All 32 skills in this repo
  • Add Config

    microbus-io/fabric

    TRIGGER when user asks to add or modify a configuration property or setting, or to make a value configurable.

    172 GitHub stars~2.3k tokensUpdated 10 days ago
    Auto-check passed
  • Add Inbound Event

    microbus-io/fabric

    TRIGGER when user asks to listen for, subscribe to, or handle an event emitted by another microservice.

    172 GitHub stars~1.4k tokensUpdated 10 days ago
    Auto-check passed
  • Add Metric

    microbus-io/fabric

    TRIGGER when user asks to add or modify a metric, counter, gauge, or histogram, or to track/measure an operation.

    172 GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check passed
  • Add Outbound Event

    microbus-io/fabric

    TRIGGER when user asks to fire, emit, or publish an event that other microservices can subscribe to.

    172 GitHub stars~1.7k tokensUpdated 10 days ago
    Auto-check passed
  • Add Python Function

    microbus-io/fabric

    TRIGGER when user asks to add a Python-backed function endpoint to an existing Python-backed microservice.

    172 GitHub stars~1.3k tokensUpdated 10 days ago
    Auto-check passed
  • Add Python Microservice

    microbus-io/fabric

    TRIGGER when user asks to create a microservice that calls Python, runs ML inference, or uses Python libraries (PyTorch, pandas, sentence-transformers, numpy) for its core compute.

    172 GitHub stars~1.1k tokensUpdated 10 days ago
    Auto-check passed

Categories

Questions about Add Function

What does Add Function do?

TRIGGER when user asks to add, create, or modify an API endpoint, function, or RPC, or a route that accepts typed arguments and returns typed results. Add Function is an agent skill from microbus-io/fabric. TRIGGER when user asks to add, create, or modify an API endpoint, function, or RPC, or a route that accepts typed arguments and returns typed results.

When should I use Add Function?

Add Function fits situations like: user asks to add; modify an API endpoint; A route that accepts typed arguments and returns typed results.

How do I install Add Function in Claude Code?

Run `npx skills add microbus-io/fabric --skill add-function -a claude-code`. Or copy the skill folder (.claude/skills/microbus/add-function in microbus-io/fabric) into .claude/skills/add-function in your project. Claude Code loads it when a task matches its description.

How do I install Add Function in Codex?

Run `npx skills add microbus-io/fabric --skill add-function -a codex`. Or copy the skill folder (.claude/skills/microbus/add-function in microbus-io/fabric) into .agents/skills/add-function in your project. Codex loads it when a task matches its description.

Can I use Add Function 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 microbus-io/fabric --skill add-function -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-function, .gemini/skills/add-function, .github/skills/add-function and .opencode/skills/add-function in your project.

What does Add Function need to run?

Going by SKILL.md and its folder, Add Function needs the command-line tools its instructions call (go).

Does Add Function 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 Add Function 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 Add Function use?

Add Function is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Add Function use?

About 2.4k tokens (SKILL.md is roughly 9.6k 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 Add Function?

Skills that share tags, products or a category with Add Function: Nodejs Backend Patterns (ever-works/ever-works, 158 stars), Dr Jskill (jdubois/dr-jskill, 342 stars), Hybrid Cloud Test Gen (getsentry/sentry, 46k stars) and API Gateway (itsmostafa/aws-agent-skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Add Function?

microbus-io (a GitHub organization) maintains it in microbus-io/fabric, which has 172 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on September 28, 2026.

Source: microbus-io/fabric on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.