Agent skill

Alpaca CLI Regenerate

Keep the CLI in sync with upstream OpenAPI specs. An agent skill from alpacahq/cli.

Apache-2.0Auto-check passedBackend & APIs

Install Alpaca CLI Regenerate

skills CLI

$ npx skills add alpacahq/cli --skill alpaca-cli-regenerate -a claude-code

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

GitHub CLI

$ gh skill install alpacahq/cli alpaca-cli-regenerate --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/alpacahq/cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/alpaca-cli-regenerate .claude/skills/alpaca-cli-regenerate && 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/

Paste into Claude Code

Install the "alpaca-cli-regenerate" agent skill from https://github.com/alpacahq/cli/tree/main/.agents/skills/alpaca-cli-regenerate into .claude/skills/alpaca-cli-regenerate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alpaca-cli-regenerate", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/alpacahq/cli/tree/main/.agents/skills/alpaca-cli-regenerate

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add alpacahq/cli --skill alpaca-cli-regenerate -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install alpacahq/cli alpaca-cli-regenerate --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alpacahq/cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/alpaca-cli-regenerate .agents/skills/alpaca-cli-regenerate && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "alpaca-cli-regenerate" agent skill from https://github.com/alpacahq/cli/tree/main/.agents/skills/alpaca-cli-regenerate into .agents/skills/alpaca-cli-regenerate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alpaca-cli-regenerate", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alpacahq/cli --skill alpaca-cli-regenerate -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install alpacahq/cli alpaca-cli-regenerate --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alpacahq/cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/alpaca-cli-regenerate .cursor/skills/alpaca-cli-regenerate && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "alpaca-cli-regenerate" agent skill from https://github.com/alpacahq/cli/tree/main/.agents/skills/alpaca-cli-regenerate into .cursor/skills/alpaca-cli-regenerate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alpaca-cli-regenerate", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/alpacahq/cli.git --path .agents/skills/alpaca-cli-regenerate

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add alpacahq/cli --skill alpaca-cli-regenerate -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install alpacahq/cli alpaca-cli-regenerate --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alpacahq/cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/alpaca-cli-regenerate .gemini/skills/alpaca-cli-regenerate && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "alpaca-cli-regenerate" agent skill from https://github.com/alpacahq/cli/tree/main/.agents/skills/alpaca-cli-regenerate into .gemini/skills/alpaca-cli-regenerate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alpaca-cli-regenerate", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install alpacahq/cli alpaca-cli-regenerate

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add alpacahq/cli --skill alpaca-cli-regenerate -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/alpacahq/cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/alpaca-cli-regenerate .github/skills/alpaca-cli-regenerate && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "alpaca-cli-regenerate" agent skill from https://github.com/alpacahq/cli/tree/main/.agents/skills/alpaca-cli-regenerate into .github/skills/alpaca-cli-regenerate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alpaca-cli-regenerate", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add alpacahq/cli --skill alpaca-cli-regenerate -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install alpacahq/cli alpaca-cli-regenerate --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/alpacahq/cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/alpaca-cli-regenerate .opencode/skills/alpaca-cli-regenerate && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "alpaca-cli-regenerate" agent skill from https://github.com/alpacahq/cli/tree/main/.agents/skills/alpaca-cli-regenerate into .opencode/skills/alpaca-cli-regenerate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alpaca-cli-regenerate", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: alpaca-cli-regenerate
GitHub stars: 178
Token cost: ~2k tokens
SKILL.md length: 783 words
Files: 1
Skills in repo: 2
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Keep the CLI in sync with upstream OpenAPI specs. An agent skill from alpacahq/cli.

Works in 6 steps: Pull latest specs → Generate code → Fix generator failures → …
Specs changed upstream
SKILL.md covers Pipeline, Quick reference, Key files and Anti-Patterns
Calls make, go and git

What it does

Alpaca CLI Regenerate is an agent skill from alpacahq/cli. Keep the CLI in sync with upstream OpenAPI specs. Pulls latest specs, runs the code generator, registers new operations, updates golden files, and runs all checks. Use when specs changed upstream, a new API endpoint was added, generation is stale, or the user says "regenerate", "generate", "sync specs", "update specs", or "spec-update".

Its SKILL.md is about 2k 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 OpenAPI specifications and REST APIs. It works with Alpaca. The licence is Apache-2.0.

When your agent uses it

Specs changed upstream
A new API endpoint was added
Generation is stale
The user says regenerate

Example prompts

“regenerate”
“generate”
“sync specs”
“/alpaca-cli-regenerate”

Workflow steps

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

Pull latest specs
Generate code
Fix generator failures
Update golden files
Run all checks
Verify completeness

What it can do on your machine

Read from SKILL.md and the folder at commit 5360627. 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:
- make
- go
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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

Alpaca CLI Regenerate loads about 2k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 783 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~90
When it runs · the whole SKILL.md, loaded when a task matches: ~2k

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 alpacahq/cli at commit 5360627, republished under its Apache-2.0 licence (© alpacahq). 783 words, ~1,982 tokens.

Download SKILL.mdSave it as .claude/skills/alpaca-cli-regenerate/SKILL.md (or your agent's skills folder).

name: alpaca-cli-regenerate
description: Keep the CLI in sync with upstream OpenAPI specs. Pulls latest specs, runs the code generator, registers new operations, updates golden files, and runs all checks. Use when specs changed upstream, a new API endpoint was added, generation is stale, or the user says "regenerate", "generate", "sync specs", "update specs", or "spec-update".

Generate - Keep the CLI Up to Date

Pipeline

Run each phase in order. Stop and fix before moving to the next.

Phase 1: Pull latest specs

make spec-update requires network access (it curls docs.alpaca.markets). Request full_network permissions if running in a sandbox.

bash

make spec-update

Downloads trading-api.json and market-data-api.json from docs.alpaca.markets/openapi/ into api/specs/.

After pulling, check what changed:

bash

git diff --stat api/specs/

If nothing changed, specs are already current - skip to Phase 4 to verify generated code is still fresh.

Phase 2: Generate code

bash

make generate

This runs go run ./cmd/generate which reads the specs and writes:

Generated file	Contents
`internal/api/trading_types.gen.go`	Structs and enums from trading spec
`internal/api/trading_client.gen.go`	Trading API client methods
`internal/api/marketdata_types.gen.go`	Structs and enums from market data spec
`internal/api/marketdata_client.gen.go`	Market data API client methods
`internal/api/descriptions.gen.go`	Op metadata, flags, response schemas
`internal/cmd/commands.gen.go`	Cobra command tree

Never edit *.gen.go files directly. Change the specs or generator, then re-run make generate.

Phase 3: Fix generator failures

The generator enforces exhaustiveness. Common failures and fixes:

New operation not registered

unregistered operation "FooBar" — add to cmdRegistry or cmdSkip

Every operationId in the specs must appear in either cmdRegistry or cmdSkip in cmd/generate/commands.go.

To register a new command, add an entry to cmdRegistry:

"FooBar": {
    parent:   "<parent-group>",   // key in cmdParents
    use:      "<subcommand-name>",
    examples: "  alpaca <parent> <subcommand> --flag value",
},

Rules for registry entries:

parent must be a key in cmdParents (or create a new parent group)
examples is required - the generator fails without it
Use kebab-case for use names
Add defaults for sensible default flag values
Add bodyAliases if a body field name collides with a query/path param
Add bodyHook / bodySkipFields for complex body construction
Add configureFunc for hand-written configure hooks (e.g. order submit's bracket legs)
Add normalize for path params that need URL normalization (e.g. symbols with /)

If the command IS its parent (e.g. alpaca clock runs directly, not alpaca clock get), use self: true and omit use:

"LegacyClock": {
    parent:   "clock",
    self:     true,
    examples: "  alpaca clock",
},

To skip an operation (intentionally exclude from the CLI):

var cmdSkip = map[string]string{
    "FooBar": "reason for skipping",
}

Body field collision

body field "name" collides with a query/path param — add bodyAliases

Fix by adding a bodyAliases entry that renames the body flag:

"UpdateFoo": {
    parent:      "foo",
    use:         "update",
    bodyAliases: map[string]string{"name": "new-name"},
    examples:    "  alpaca foo update --name old --new-name new",
},

New parent group needed

Add to cmdParents in cmd/generate/commands.go:

"myGroup": {
    use:   "my-group",
    short: "Short description",
    long:  "Longer description for --help.",
},

For nested groups, set parent:

"mySubGroup": {
    use:    "sub",
    short:  "Sub-group description",
    parent: "myGroup",
},

Top-level parent groups also need root wiring. If the new group is not nested under an existing parent, add it to addGroup() in internal/cmd/root.go. Pick the right group (tradingGroup, accountGroup, or utilGroup):

addGroup(rootCmd, tradingGroup.ID, orderCmd, ..., myGroupCmd)

Without this, the command won't appear in --help or --help-all.

After fixing, re-run make generate until it succeeds.

Phase 4: Update golden files

If the command tree or op metadata changed, golden files will be stale:

bash

go test ./internal/cmd -run TestCommandTreeGolden -update
go test ./internal/cmd -run TestOpsGolden -update

Phase 5: Run all checks

bash

make check

This runs golangci-lint, go test -race ./..., and go build. Fix any failures before proceeding.

If tests fail due to golden drift you missed, re-run Phase 4.

Show full SKILL.md (365 more words)Show less

Phase 6: Verify completeness

Review what changed end-to-end:

bash

git diff --stat

Verify:

api/specs/ - spec files updated
internal/api/*.gen.go - types and clients regenerated
internal/cmd/commands.gen.go - command tree regenerated
internal/cmd/testdata/*.golden - golden files updated if needed
cmd/generate/commands.go - new operations registered if needed
internal/cmd/root.go - new top-level parent groups wired via addGroup
test/integration/ - integration tests added for new commands

If commands were added, add integration tests in test/integration/. Follow the rules in the "Integration tests" section of AGENTS.md - one file per feature area, t.Parallel() for read-only tests, cleanup for writes. If the endpoint is unavailable on paper (see the paper-unavailable list in AGENTS.md), write a test that accepts either a valid response or a structured JSON error.

If commands or flags were added, removed, or renamed, follow the "Keep docs in sync" section in AGENTS.md.

Keep README.md concise. It should describe command areas and point to alpaca --help-all, <command> --help, and <command> --schema instead of listing generated command tables. Add README detail only when user-facing behavior, safety guidance, authentication, output, or install/update flow changes.

Quick reference

Task	Command
Pull specs	`make spec-update`
Generate code	`make generate`
Update golden files	`go test ./internal/cmd -run TestCommandTreeGolden -update && go test ./internal/cmd -run TestOpsGolden -update`
Lint + test + build	`make check`
See what changed	`git diff --stat`
Integration tests	`make test-integration` (needs API keys)

Key files

File	Role	Editable?
`api/specs/*.json`	OAS specs (read-only inputs)	No - pull from upstream
`cmd/generate/main.go`	Generator logic	Yes
`cmd/generate/commands.go`	Command registry and parent groups	Yes
`internal/api/*.gen.go`	Generated types and clients	No - regenerate
`internal/cmd/commands.gen.go`	Generated Cobra commands	No - regenerate
`internal/cmd/root.go`	Root command wiring (`addGroup` for top-level parents)	Yes
`internal/cmd/testdata/*.golden`	Golden test snapshots	Update via `-update` flag

Anti-Patterns

NEVER edit *.gen.go files directly - they are overwritten by make generate. Change the specs or the generator instead.
NEVER edit spec files in api/specs/ - fix bugs upstream and re-import with make spec-update.
NEVER skip make check after generating - generated code can introduce lint failures or test regressions.
NEVER update golden files without reviewing the diff - golden updates should reflect intentional command tree changes, not mask bugs.
NEVER add a cmdRegistry entry without examples - the generator enforces this and will fail.
NEVER add an operation to cmdSkip without a reason - the reason documents why the endpoint is excluded from the CLI.

Files

Just SKILL.md in .agents/skills/alpaca-cli-regenerate of alpacahq/cli.

Open the folder on GitHubat commit 5360627

Compare with similar skills

Alpaca CLI Regenerate 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.

Alpaca CLI Regenerate compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Alpaca CLI Regenerate this skillalpacahq/cli	178	—	~2k	Automated safety check: Pass	Apache-2.0	today
OpenAPI to MCP Servermcp-use/mcp-use	11k	—	~5.2k	Automated safety check: Pass	Apache-2.0	yesterday
Use Yaakmountain-loop/yaak	19k	—	~1.9k	Automated safety check: Pass	MIT	3 days ago
API DesignerJeffallan/claude-skills	12k	1 repos	~2k	Automated safety check: Pass	MIT	6 days ago
Old Coder API DesignAmazingAng/old-coder	750	—	~3.4k	Automated safety check: Pass	MIT	1 mo ago
API CallerNVIDIA/SkillEvaluator	554	—	~1.1k	Automated safety check: Pass	Apache-2.0	today

Similar skills

OpenAPI to MCP Server
mcp-use/mcp-use
Turns an OpenAPI or Swagger spec into an MCP server with the mcp-use TypeScript SDK, mapping each operation to a tool, wiring auth, testing and deploying.
11k GitHub stars~5.2k tokensUpdated yesterday
Backend & APIsAuto-check passed
Use Yaak
mountain-loop/yaak
A skill your agent uses when the user mentions Yaak, a Yaak workspace, or the yaak command, or asks to call, hit, or smoke test HTTP/REST endpoints, save or organize API requests for reuse or manual…
19k GitHub stars~1.9k tokensUpdated 3 days ago
Backend & APIsAuto-check passed
API Designer
Jeffallan/claude-skills
Designs REST and GraphQL APIs from resource modeling to an OpenAPI 3.1 contract, with versioning, pagination and RFC 7807 error handling.
12k GitHub starsUsed in 1 repo~2k tokens
Backend & APIsAuto-check passed
Old Coder API Design
AmazingAng/old-coder
Reviews or designs an HTTP/JSON API's endpoints, auth, pagination, versioning and deprecations, guarding against inventing a bespoke interface or silently breaking consumers.
750 GitHub stars~3.4k tokensUpdated 1 mo ago
Backend & APIsAuto-check passed
API Caller
NVIDIA/SkillEvaluator
Official
Call any REST API dynamically. An agent skill from NVIDIA/SkillEvaluator.
554 GitHub stars~1.1k tokensUpdated today
Backend & APIsAuto-check passed
API Endpoint Contract
trycompai/comp
The contract every new or modified API endpoint must follow so it is correct for the public OpenAPI spec, the MCP server (npm @trycompai/mcp-server), the ValidationPipe, and the docs.
2k GitHub stars~2.7k tokensUpdated today
Backend & APIsAuto-check passed

Questions about Alpaca CLI Regenerate

What does Alpaca CLI Regenerate do?

Keep the CLI in sync with upstream OpenAPI specs. An agent skill from alpacahq/cli. Alpaca CLI Regenerate is an agent skill from alpacahq/cli. Keep the CLI in sync with upstream OpenAPI specs.

When should I use Alpaca CLI Regenerate?

Alpaca CLI Regenerate fits situations like: specs changed upstream; A new API endpoint was added; generation is stale; the user says regenerate.

How do I install Alpaca CLI Regenerate in Claude Code?

Run `npx skills add alpacahq/cli --skill alpaca-cli-regenerate -a claude-code`. Or copy the skill folder (.agents/skills/alpaca-cli-regenerate in alpacahq/cli) into .claude/skills/alpaca-cli-regenerate in your project. Claude Code loads it when a task matches its description.

How do I install Alpaca CLI Regenerate in Codex?

Run `npx skills add alpacahq/cli --skill alpaca-cli-regenerate -a codex`. Or copy the skill folder (.agents/skills/alpaca-cli-regenerate in alpacahq/cli) into .agents/skills/alpaca-cli-regenerate in your project. Codex loads it when a task matches its description.

Can I use Alpaca CLI Regenerate 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 alpacahq/cli --skill alpaca-cli-regenerate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/alpaca-cli-regenerate, .gemini/skills/alpaca-cli-regenerate, .github/skills/alpaca-cli-regenerate and .opencode/skills/alpaca-cli-regenerate in your project.

What does Alpaca CLI Regenerate need to run?

Going by SKILL.md and its folder, Alpaca CLI Regenerate needs the command-line tools its instructions call (make, go and git).

Does Alpaca CLI Regenerate access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Alpaca CLI Regenerate 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 Alpaca CLI Regenerate use?

Alpaca CLI Regenerate 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 Alpaca CLI Regenerate use?

About 2k tokens (SKILL.md is roughly 7.9k 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 Alpaca CLI Regenerate?

Skills that share tags, products or a category with Alpaca CLI Regenerate: OpenAPI to MCP Server (mcp-use/mcp-use, 11k stars), Use Yaak (mountain-loop/yaak, 19k stars), API Designer (Jeffallan/claude-skills, 12k stars) and Old Coder API Design (AmazingAng/old-coder, 750 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Alpaca CLI Regenerate?

alpacahq (a GitHub organization) maintains it in alpacahq/cli, which has 178 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

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

Install Alpaca CLI Regenerate

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Generate - Keep the CLI Up to Date

Pipeline

Phase 1: Pull latest specs

Phase 2: Generate code

Phase 3: Fix generator failures

New operation not registered

Body field collision

New parent group needed

Phase 4: Update golden files

Phase 5: Run all checks

Phase 6: Verify completeness

Quick reference

Key files

Anti-Patterns

Files

Compare with similar skills

Similar skills

OpenAPI to MCP Server

Use Yaak

API Designer

Old Coder API Design

API Caller

API Endpoint Contract

More from alpacahq/cli

Alpaca CLI

Related

Questions about Alpaca CLI Regenerate