Agent skill

Openapi To Python Lungo

by agntcy in agntcy/coffeeAgntcy

Generates and validates Python FastAPI routers and DTOs from the OpenAPI schemas in coffeeAGNTCY/coffeeagents/lungo/schema/openapi for the lungo subproject.

Apache-2.0Auto-check passedBackend & APIs

Install Openapi To Python Lungo

skills CLI
$ npx skills add agntcy/coffeeAgntcy --skill openapi-to-python-lungo -a claude-code

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

GitHub CLI
$ gh skill install agntcy/coffeeAgntcy openapi-to-python-lungo --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/agntcy/coffeeAgntcy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/domain-lungo/openapi-to-python-lungo .claude/skills/openapi-to-python-lungo && 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
openapi-to-python-lungo
GitHub stars
112
Token cost
~4.3k tokens
SKILL.md length
1,808 words
Files
2
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generates and validates Python FastAPI routers and DTOs from the OpenAPI schemas in coffeeAGNTCY/coffeeagents/lungo/schema/openapi for the lungo subproject.

  • Works in 11 steps: Identify affected tags → Resolve the OpenAPI spec → Regenerate dtos.py → …
  • Modifying endpoints in any lungo OpenAPI document
  • SKILL.md covers Conventions, File ownership, Workflow selector and Generate / regenerate workflow, plus 3 more sections
  • Calls uv and make

What it does

Openapi To Python Lungo is an agent skill from agntcy/coffeeAgntcy. Generates and validates Python FastAPI routers and DTOs from the OpenAPI schemas in coffeeAGNTCY/coffeeagents/lungo/schema/openapi for the lungo subproject. When contracts change, the sibling agentic-workflows-api-documentation-lungo skill updates OpenAPI operation responses and docs/workflow-instanceapi.md; this skill aligns handlers and DTOs with the spec. Use when adding, removing, renaming, or modifying endpoints in any lungo OpenAPI document; when generating or regenerating files under…

Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `reference.md`).

It sits in Backend & APIs, covering OpenAPI specifications. It works with OpenAPI, Python and FastAPI. The repository describes itself as: End-to-end reference application for AGNTCY Components. The licence is Apache-2.0.

When your agent uses it

  • Modifying endpoints in any lungo OpenAPI document
  • Regenerating files under coffeeAGNTCY/coffeeagents/lungo/api/<tag/ (router.py
  • Validating that hand-edited handlers
  • DTOs still match the OpenAPI spec

Example prompts

  • “Use the openapi-to-python-lungo skill to generate and validates Python FastAPI routers and DTOs from the OpenAPI schemas in…”
  • “/openapi-to-python-lungo”

Requirements

  • Python 3

Workflow steps

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

  1. Identify affected tags
  2. Resolve the OpenAPI spec
  3. Regenerate dtos.py
  4. Reconcile router.py
  5. Generate tests
  6. Run tests and linter
  7. Resolve and validate the spec
  8. Path/method diff
  9. Per-operation signature check
  10. DTO drift check
  11. Run the tests

What it can do on your machine

Read from SKILL.md and the folder at commit 36f1923. 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:

    • uv
    • make

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

  • Network

    No URLs in SKILL.md. Its commands use uv, 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

Openapi To Python Lungo loads about 4.3k tokens when it runs. Until then it costs about 181 tokens; SKILL.md has 1,808 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~181
When it runs · the whole SKILL.md, loaded when a task matches
~4.3k

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 agntcy/coffeeAgntcy at commit 36f1923, republished under its Apache-2.0 licence (© agntcy). 1,808 words, ~4,262 tokens.

Download SKILL.mdSave it as .claude/skills/openapi-to-python-lungo/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
openapi-to-python-lungo
description
Generates and validates Python FastAPI routers and DTOs from the OpenAPI schemas in coffeeAGNTCY/coffee_agents/lungo/schema/openapi for the lungo subproject. When contracts change, the sibling agentic-workflows-api-documentation-lungo skill updates OpenAPI operation responses and docs/workflow-instance_api.md; this skill aligns handlers and DTOs with the spec. Use when adding, removing, renaming, or modifying endpoints in any lungo OpenAPI document; when generating or regenerating files under coffeeAGNTCY/coffee_agents/lungo/api/<tag>/ (router.py, dtos.py); when validating that hand-edited handlers or DTOs still match the OpenAPI spec; or when scaffolding the OpenAPI unit tests for a router.

OpenAPI → FastAPI Generator and Validator (lungo)

This skill turns the OpenAPI documents under coffeeAGNTCY/coffee_agents/lungo/schema/openapi/ into Python FastAPI routers and Pydantic DTOs, and validates that hand-edited code still matches the spec. All paths in this document are relative to the repository root.

The lungo project root is coffeeAGNTCY/coffee_agents/lungo/. All other paths below (api/..., schema/..., tests/...) are relative to that project root.

Conventions

The skill follows one consistent layout per OpenAPI tag. The tag is the discriminator that maps an OpenAPI operation to a Python package; everything else is derived deterministically from it.

OpenAPI conceptPython artifact
Tag (kebab-case), e.g. agentic-workflowsSnake-case package: api/agentic_workflows/
All operations sharing that tagSingle api/<tag_snake>/router.py
All components/schemas referenced by those operationsSingle api/<tag_snake>/dtos.py
Per-tag router functioncreate_<tag_snake>_router() -> APIRouter
OpenAPI entry pointschema/openapi/openapi.yaml (may $ref paths/<tag>.yaml and components/schemas.yaml)

The skill must remain general across tags: never hard-code endpoint names, schemas, or counts. Only the layout and naming rules above are fixed.

File ownership

  • dtos.py is owned by this skill. It is regenerated from scratch on every run; never preserve hand edits inside it. If a user needs to edit a DTO, they must edit the OpenAPI schema instead.

  • router.py is co-owned. The skill owns:

    • the module-level imports it adds for DTOs,
    • the create_<tag_snake>_router() function signature and the presence of tags=[<tag>] on the APIRouter(...) construction (the skill ensures tags=[<tag>] is set, but it must not discard other constructor arguments - see below),
    • the route decorators (path, method, response_model, status_code, summary, etc.) and handler signatures (parameters, type annotations, return type).

    The skill does not generate or reconcile per-operation OpenAPI responses on FastAPI decorators. Operation responses (success and error statuses) live in schema/openapi/paths/*.yaml and shared components/responses - the published contract (source of truth under schema/openapi/, not generated from code). Update OpenAPI and docs/workflow-instance_api.md via agentic-workflows-api-documentation-lungo first, then use this skill to align handlers when endpoints, payload shapes, or HTTP statuses change.

    The user owns:

    • the bodies of existing handlers,
    • any module-level helpers (constants, helper functions, classes) added around the router function,
    • additional imports the user added for those helpers,
    • any other arguments already passed to the APIRouter(...) constructor (e.g. dependencies=[...], prefix=, responses=, default_response_class=) and the imports backing them. These encode router-level behavior (most notably authentication/authorization) that is not derivable from the OpenAPI document, so the skill must preserve them verbatim rather than overwrite them.

    When regenerating an existing handler, preserve its body verbatim. When decorator metadata or the signature must change to match the spec, rewrite the decorator and signature, but keep the body.

  • The OpenAPI tests under tests/unit/openapi/ are owned by this skill. Regenerate them when missing or stale; do not preserve hand edits inside them except openapi_spec_helpers.py and the status-code conformance test module, which assert the hand-maintained spec is complete and that api/<tag_snake>/ implementation uses only declared status codes (see reference.md § Status-code conformance). Error bodies in schema/openapi/components/schemas.yaml are split as ApplicationError (string detail) and ValidationError (422 array detail); shared components/responses must $ref the name that matches the HTTP status (enforced by collect_error_response_ref_violations() in the same test module).

Workflow selector

Pick the workflow that matches the user's intent, then jump to that section:

TriggerWorkflow
OpenAPI changed (added/removed/renamed paths or schemas), or router.py / dtos.py is missingGenerate / regenerate
User edited a handler signature, decorator, or DTO and wants to confirm it is still validValidate
Just want to confirm everything is consistent end-to-endValidate, then run tests

Generate / regenerate workflow

Track progress with this checklist:

- [ ] 1. Identify affected tags
- [ ] 2. Resolve the OpenAPI spec
- [ ] 3. Regenerate dtos.py from scratch
- [ ] 4. Reconcile router.py (preserve handler bodies)
- [ ] 5. Generate or refresh tests under tests/unit/openapi/
- [ ] 6. If contracts changed, ensure OpenAPI and `workflow-instance_api.md` are updated ([agentic-workflows-api-documentation-lungo](../agentic-workflows-api-documentation-lungo/SKILL.md)); align handlers to use only OpenAPI-declared statuses
- [ ] 7. Run the tests and the linter
Step 1 - Identify affected tags

Read schema/openapi/openapi.yaml and any files it $refs under schema/openapi/paths/ and schema/openapi/components/. List every tag that appears on at least one operation. For each tag, the target package is api/<tag_snake>/ where tag_snake is the kebab-case tag with - replaced by _.

If the spec references types from schema/jsonschemas/ (and therefore from schema/types/ Pydantic mirrors), prefer importing those Pydantic types into dtos.py rather than redeclaring them. See reference.md for the mapping rules.

Step 2 - Resolve the OpenAPI spec

Use prance.ResolvingParser to dereference $refs before mapping. The resolved paths and components.schemas must drive generation; do not read the raw YAML directly to extract operations or schemas.

python
from prance import ResolvingParser
parser = ResolvingParser("schema/openapi/openapi.yaml", lazy=True)
parser.parse()
spec = parser.specification  # dict with resolved $refs
Step 3 - Regenerate dtos.py

Overwrite api/<tag_snake>/dtos.py from scratch using the rules in reference.md § DTO mapping. In summary:

  • One Pydantic class per components/schemas.<Name> referenced by an operation under this tag.
  • Object schema with additionalProperties: false → class X(BaseModel): model_config = ConfigDict(extra="forbid").
  • Object schema acting as a map (additionalProperties: <schema>) → class X(RootModel[dict[str, <value_t>]]). The key type is always str (or whatever underlying JSON primitive is - usually str), even when propertyNames references a typed schema. JSON object keys are strings on the wire, and using a Pydantic RootModel subclass as a dict key is broken in practice (the default class is unhashable; frozen=True makes it hashable but model_dump_json then writes the model's Python repr as the JSON key, which violates the contract).
  • Known exception - propertyNames is currently not enforced in dtos.py. When propertyNames adds a constraint (pattern, format, $ref, etc.), the skill deliberately does not generate a field_validator that re-implements that constraint. The reason: doing so would duplicate logic that already lives in schema/types/ (e.g. the InstanceId regex would have to be copied into every DTO map that keys on it, drifting on every change). Generated DTOs use a plain dict[str, <value_t>] and rely on the value type's own validation (the value typically references the typed key via a nested field, e.g. WorkflowInstance.id: InstanceId). This means propertyNames constraints are not currently enforced at the DTO layer; flag this in any output that mentions a propertyNames constraint and treat it as a known limitation to revisit (a single-source-of-truth helper, e.g. exposing pattern constants from schema.types, would let the skill enforce this without duplication). See reference.md § Map responses with constrained keys.
  • Schemas that resolve to types already exported from schema.types (for example InstanceId, WorkflowInstance, Event, Workflow, Topology) must be imported from schema.types, not redefined.
  • Required fields are non-default annotations; optional fields default to None.
  • Use Annotated[T, Field(min_length=..., pattern=..., ge=..., ...)] for string/numeric constraints.
  • Always include the standard SPDX header at the top of the file.
Show full SKILL.md (880 more words)Show less
Step 4 - Reconcile router.py

For each operation under this tag:

  1. Compute the expected handler from the OpenAPI operation:

    • Function name: operationId converted to snake_case. If operationId is missing, derive a stable name from <method>_<path> and warn the user that adding operationId is preferred.
    • Decorator: @router.<method>(<path>, response_model=<dto_or_type>, status_code=<status>, summary="<summary>"). Omit response_model / status_code only when the operation declares no non-default 2xx response or no schema.
    • Parameters:
      • Path params: Annotated[<py_type>, Path(<constraints>)].
      • Query params: Annotated[<py_type>, Query(<constraints>)] with the OpenAPI default if present.
      • Request body: typed parameter using the body schema's DTO.
    • Return type annotation: the response DTO (or RedirectResponse, StreamingResponse, etc. for non-JSON responses).
  2. If the function does not exist, create it with the signature above and a stub body:

    python
    raise HTTPException(status_code=501, detail="Not implemented")

    Add a one-line docstring summarizing the method and path.

  3. If the function exists:

    • Update its decorator and signature in place to match the spec.
    • Preserve the handler body verbatim.
    • Preserve any decorator-unrelated import the user added.
  4. After processing all spec operations, look for handler functions inside create_<tag_snake>_router() that no longer correspond to any operation. Do not delete them silently - emit a warning of the form:

    Stale handler: <function_name> is no longer in the OpenAPI spec for tag '<tag>'. Remove it manually if intentional.
  5. Make sure the APIRouter is constructed with tags=["<tag>"] and that create_<tag_snake>_router() returns it. Preserve every other argument already passed to APIRouter(...). When regenerating an existing router, the OpenAPI document does not describe router-level construction options, so anything the user put on the constructor must survive untouched:

    • dependencies=[...] - router-level dependencies (e.g. an auth gate). Keep the full list and the imports backing it. This rule is general: treat any value found in dependencies= the same way, regardless of which callable it wraps.
    • prefix=, responses=, default_response_class=, deprecated=, and any other keyword arguments - keep them verbatim.

    Only add tags=[<tag>] if it is missing, and only reconcile tags itself; never drop, reorder, or rewrite the user's other constructor arguments. If you cannot safely merge tags while preserving an existing argument, stop and ask the user.

    python
    # If the existing code looks like this, keep `dependencies=` (and its import) on regen:
    from api.<tag_snake>.auth import require_workflow_api_key  # example dependency - preserve whatever import is present
    
    router = APIRouter(
        tags=[_TAG],
        dependencies=[Depends(require_workflow_api_key)],  # example only - preserve any dependencies found
    )

See reference.md § Router templates for concrete snippets.

Step 5 - Generate tests

Ensure the directory tests/unit/openapi/ exists. For each tag, generate (or refresh) two files. File names are not load-bearing; the convention below uses <tag_snake> and is recommended:

  • tests/unit/openapi/test_<tag_snake>_openapi_spec.py - validates the resolved OpenAPI document with openapi_spec_validator.
  • tests/unit/openapi/test_<tag_snake>_openapi_routes_match_app.py - builds a minimal FastAPI app via create_<tag_snake>_router() and asserts that the (path, METHOD) set from app.openapi() equals the set extracted from the resolved OpenAPI spec.

For the agentic-workflows tag, also keep (do not regenerate from templates):

  • tests/unit/openapi/openapi_spec_helpers.py - load resolved spec; collect declared vs implemented status codes.
  • tests/unit/openapi/test_agentic_workflow_openapi_status_codes.py - global security, every operation declares responses, implementation statuses ⊆ OpenAPI, and error status codes $ref the matching components/responses name (404 → NotFound, 422 → UnprocessableEntity, etc.; see ERROR_STATUS_TO_RESPONSE_COMPONENT in helpers).

When adding a new tag with non-trivial error surfaces, add matching helpers/tests using the agentic-workflows pair as a pattern; see reference.md § Status-code conformance.

Both standard tests resolve schema/openapi/openapi.yaml via prance and use the same _HTTP_METHODS filter shown in reference.md § Test templates. They must not assume any specific endpoint names - they compare full sets.

Step 6 - Run tests and linter

Run from coffeeAGNTCY/coffee_agents/lungo/:

bash
uv run pytest tests/unit/openapi/ tests/unit/api/ -q

If integration tests reference the affected tag (for example tests/integration/... files matching the tag), run them too. Then run the project's standard linter / formatter (ruff, make lint, etc., as configured for the project) on all touched files. Fix any errors before finishing.

Validate workflow

Use this when the user has hand-edited router.py or dtos.py and wants confirmation that the spec, code, and tests are still consistent.

- [ ] 1. Resolve the OpenAPI spec (prance) and confirm it validates
- [ ] 2. Diff (path, METHOD) sets: spec vs FastAPI app
- [ ] 3. For each spec operation, confirm the handler signature matches
- [ ] 4. Confirm dtos.py would be regenerated identically
- [ ] 5. Run the OpenAPI and router tests (includes OpenAPI status conformance for agentic-workflows)
Step 1 - Resolve and validate the spec

Use prance.ResolvingParser plus openapi_spec_validator.validate(...). A failure here means the spec itself is broken; report it and stop.

Step 2 - Path/method diff

Build the minimal FastAPI app exactly as in the generated test_<tag_snake>_openapi_routes_match_app.py, then compute the symmetric difference between the spec and app (path, METHOD) sets. Report:

  • Only in spec: ... - handlers missing from router.py.
  • Only in app: ... - extra handlers not in the spec (likely stale).
Step 3 - Per-operation signature check

For every spec operation, confirm:

  • the handler exists,
  • its decorator matches (response_model, status_code, summary, path, method),
  • the parameter list (path, query, body) and types match the spec.

Report mismatches with the operation id and a one-line diff.

Step 4 - DTO drift check

Run the regeneration logic from step 3 of the generate workflow against an in-memory buffer and diff it against the on-disk dtos.py. If they differ, the user has either edited dtos.py by hand or the spec changed without regeneration. Recommend re-running the generate workflow.

Step 5 - Run the tests

Run the same tests as in the generate workflow. They are the authoritative validation.

When to ask the user

Stop and ask the user before doing any of:

  • deleting or renaming a public symbol from dtos.py that is imported elsewhere in the project,
  • removing a stale handler from router.py (always recommend, never auto-delete),
  • changing an existing handler body to satisfy a signature change (only the signature is yours; body changes belong to the user).

Additional resources

  • reference.md - OpenAPI → Pydantic mapping rules, router templates, and test templates with concrete snippets.

© agntcy, 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

SKILL.md and 1 other file in .agents/skills/domain-lungo/openapi-to-python-lungo of agntcy/coffeeAgntcy.

  • SKILL.md
  • reference.md

Open the folder on GitHubat commit 36f1923

Compare with similar skills

Openapi To Python Lungo 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.

Openapi To Python Lungo compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openapi To Python Lungo this skillagntcy/coffeeAgntcy112—~4.3kAutomated safety check: PassApache-2.0
Fastapi Init Skilljiushiwon/wg-skills110—~1.8kAutomated safety check: NotesApache-2.0
FastAPI ExpertJeffallan/claude-skills12k—~1.8kAutomated safety check: PassMIT
Route To Openapizebbern/claude-code-guide4.6k—~1.1kAutomated safety check: PassMIT
Python Fastapi Patternsaiskillstore/marketplace4301 repos~1.3kAutomated safety check: NotesNone
API Surface Reviewpolarsource/polar10k—~1.3kAutomated safety check: PassMIT

Similar skills

  • Fastapi Init Skill

    jiushiwon/wg-skills

    FastAPI 项目一键初始化技能。面向零基础小白,提供环境探测、自动安装、完整 Web 骨架生成、SSE 流式框架、JWT 鉴权、统一响应封装、文件上传接口、一键启动/重启脚本、Swagger 文档,内置 MySQL(默认)/ PostgreSQL / MongoDB 数据库选择。用户只需说"帮我搭一个 FastAPI 项目"即可一条命令完成从零到跑的完整链路。触发词:"FastAPI…

    110 GitHub stars~1.8k tokensUpdated 3 days ago
    Backend & APIsAuto-check: notes
  • FastAPI Expert

    Jeffallan/claude-skills

    Builds async Python APIs with FastAPI and Pydantic V2, covering endpoints, JWT authentication, async SQLAlchemy, WebSockets and pytest checks against the OpenAPI docs.

    12k GitHub stars~1.8k tokensUpdated 4 days ago
    Backend & APIsAuto-check passed
  • Route To Openapi

    zebbern/claude-code-guide

    Generates RESTful API documentation (OpenAPI 3.0 / Swagger spec) by scanning route definitions in code for Flask, FastAPI, Express, Gin, and other frameworks.

    4.6k GitHub stars~1.1k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Python Fastapi Patterns

    aiskillstore/marketplace

    FastAPI web framework patterns. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 1 repo~1.3k tokens
    Backend & APIsAuto-check: notes
  • API Surface Review

    polarsource/polar

    Review changes to Polar's API contract — Pydantic schemas, FastAPI endpoints, OpenAPI output and the generated SDKs.

    10k GitHub stars~1.3k tokensUpdated today
    Backend & APIsAuto-check passed
  • Land TS Mono

    UKGovernmentBEIS/inspect_ai

    Land a PR that requires a coordinated ts-mono submodule change.

    2.9k GitHub stars~3k tokensUpdated today
    Backend & APIsAuto-check passed

More from agntcy/coffeeAgntcy

All 16 skills in this repo
  • A2a Protocol

    agntcy/coffeeAgntcy

    A skill your agent uses when the user asks about A2A (Agent-to-Agent) protocol communication, OASF record formats, AGNTCY directory operations, agent card parsing, or dirctl CLI usage.

    112 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Add Repo Operation

    agntcy/coffeeAgntcy

    Guides adding a new repository operation (a check, validation, or piece of tooling) through this repo's standard script - Taskfile task - skill - CI enforcement - rule pipeline.

    112 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Authors and maintains the human-facing Agentic Workflows API documentation for the lungo subproject at coffeeAGNTCY/coffeeagents/lungo/docs/workflow-instanceapi.md.

    112 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed
  • Checking Pinned References

    agntcy/coffeeAgntcy

    Runs task pins:check to find any third-party GitHub Action, reusable-workflow, or image reference that isn't pinned to an immutable SHA/digest, and pins each one it finds.

    112 GitHub stars~578 tokensUpdated yesterday
    Auto-check passed
  • Runs task workflows:check-permissions to find any GitHub Actions workflow file with a write-all grant or no declared permissions, and scopes it down to least privilege.

    112 GitHub stars~513 tokensUpdated yesterday
    Auto-check passed
  • Generate Release Notes

    agntcy/coffeeAgntcy

    Generates coffeeAgntcy CHANGELOG release notes and README Built With updates from PRs and dependency lockfiles since the previous release tag.

    112 GitHub stars~535 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Openapi To Python Lungo

What does Openapi To Python Lungo do?

Generates and validates Python FastAPI routers and DTOs from the OpenAPI schemas in coffeeAGNTCY/coffeeagents/lungo/schema/openapi for the lungo subproject. Openapi To Python Lungo is an agent skill from agntcy/coffeeAgntcy. Generates and validates Python FastAPI routers and DTOs from the OpenAPI schemas in coffeeAGNTCY/coffeeagents/lungo/schema/openapi for the lungo subproject.

When should I use Openapi To Python Lungo?

Openapi To Python Lungo fits situations like: modifying endpoints in any lungo OpenAPI document; regenerating files under coffeeAGNTCY/coffeeagents/lungo/api/<tag/ (router.py; validating that hand-edited handlers; DTOs still match the OpenAPI spec.

How do I install Openapi To Python Lungo in Claude Code?

Run `npx skills add agntcy/coffeeAgntcy --skill openapi-to-python-lungo -a claude-code`. Or copy the skill folder (.agents/skills/domain-lungo/openapi-to-python-lungo in agntcy/coffeeAgntcy) into .claude/skills/openapi-to-python-lungo in your project. Claude Code loads it when a task matches its description.

How do I install Openapi To Python Lungo in Codex?

Run `npx skills add agntcy/coffeeAgntcy --skill openapi-to-python-lungo -a codex`. Or copy the skill folder (.agents/skills/domain-lungo/openapi-to-python-lungo in agntcy/coffeeAgntcy) into .agents/skills/openapi-to-python-lungo in your project. Codex loads it when a task matches its description.

Can I use Openapi To Python Lungo 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 agntcy/coffeeAgntcy --skill openapi-to-python-lungo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openapi-to-python-lungo, .gemini/skills/openapi-to-python-lungo, .github/skills/openapi-to-python-lungo and .opencode/skills/openapi-to-python-lungo in your project.

What does Openapi To Python Lungo need to run?

Going by SKILL.md and its folder, Openapi To Python Lungo needs the command-line tools its instructions call (uv and make). Our summary lists: Python 3.

Does Openapi To Python Lungo access the network?

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

Is Openapi To Python Lungo 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 Openapi To Python Lungo use?

Openapi To Python Lungo 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 Openapi To Python Lungo use?

About 4.3k tokens (SKILL.md is roughly 17k 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 Openapi To Python Lungo?

Skills that share tags, products or a category with Openapi To Python Lungo: Fastapi Init Skill (jiushiwon/wg-skills, 110 stars), FastAPI Expert (Jeffallan/claude-skills, 12k stars), Route To Openapi (zebbern/claude-code-guide, 4.6k stars) and Python Fastapi Patterns (aiskillstore/marketplace, 430 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openapi To Python Lungo?

agntcy (a GitHub organization) maintains it in agntcy/coffeeAgntcy, which has 112 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 6, 2026.

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