ffca-feature SKILL.md skillA
ffca-feature from verygoodopensource/vgv-ffca-plugin is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add verygoodopensource/vgv-ffca-plugin/ffca-feature@git:20261001.0f5d29ePins git:20261001.0f5d29e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- verygoodopensource/vgv-ffca-plugin
- Path
skills/ffca-feature/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261001.0f5d29e, committed Oct 1, 2026
- First version recorded
- Jun 16, 2026
- Size
- 7,576 bytes
- Repository stars
- 6
- License
- MIT
Scaffold and extend FFCA features: the three-package domain, data, and presentation structure, models, repositories, Commands and Queries, DTOs, mappers, Cubits, and Modules. Use in an FFCA monorepo, a features/ folder whose packages are named {feature}_domain, {feature}_data, and {feature}_presentation, when creating a new feature, a headless feature, a presentation-only feature, or a screen, or when adding a layer, repository, Command, Query, DTO, mapper, or Cubit to an existing feature.…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# FFCA Feature
Workflow for building a feature in an FFCA monorepo. Conventions and code shapes are not restated here: read the cited sections of `${CLAUDE_PLUGIN_ROOT}/references/ffca/` and adapt the templates in `${CLAUDE_PLUGIN_ROOT}/references/code_templates/`.
## Before you start
1. Confirm the repo is FFCA-shaped (a `features/` folder with `{feature}_{layer}` packages). If not, stop and use the layered-architecture skill.
2. Read `references/ffca/overview.md`, section *Feature layers*, for the layer model, and `references/ffca/project_structure.md`, section *Naming conventions*, for package names (the hook validates them).
3. Check for a pre-generated API client first. If the backend ships one OpenAPI/Swagger definition, read `references/ffca/faq.md`, section *What if the backend has one large OpenAPI or Swagger definition for every endpoint?* The client belongs in `shared/`, and each feature's data layer consumes it.
## Build order: domain, then data, then presentation
…Read the whole file at its exact version.
How to install
mdr add verygoodopensource/vgv-ffca-plugin/ffca-feature@sha256:2bb56bec501d5202The line at the top of this page pins the label git:20261001.0f5d29e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_u7sw6a2p7z6uzvud)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 16, 2026 and Oct 1, 2026, about one every 27 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261001.0f5d29e latest | 2026-10-01 | 0f5d29e | 7,576 B | A | view · diff |
| git:20260929.ceab714 | 2026-09-29 | ceab714 | 7,530 B | A | view · diff |
| git:20260929.fbd8e1d | 2026-09-29 | fbd8e1d | 4,956 B | A | view · diff |
| git:20260924.91accd9 | 2026-09-24 | 91accd9 | 4,479 B | A | view · diff |
| git:20260616.d36ae1d | 2026-06-16 | d36ae1d | 4,477 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7576 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
verygoodopensource/vgv-ffca-plugin · 6 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_u7sw6a2p7z6uzvud GET https://markdownregistry.com/api/v1/resolve?ref=verygoodopensource/vgv-ffca-plugin/ffca-feature GET https://markdownregistry.com/api/v1/blob/2bb56bec501d52028f07ebb4e9a34a78f87d3f965e6b284a6cae616e152149af
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.