Skip to content
Back to search

ai-dlc-sdk-angular

In-repository AI-DLC SDK for Angular embedded front-panel GUIs: GitHub Copilot CLI implements screens from HTML/CSS + OpenAPI + ui-bindings, loops (max N) until Excel-derived subsystem tests pass, then reverse-generates design docs and benchmarks QCD.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 19 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/sun-flat-yamada/ai-dlc-sdk-angular with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/sun-flat-yamada/ai-dlc-sdk-angular'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/sun-flat-yamada--ai-dlc-sdk-angular/badge.svg)](/listings/sun-flat-yamada--ai-dlc-sdk-angular)

HTML

<a href="/listings/sun-flat-yamada--ai-dlc-sdk-angular"><img src="/api/listings/sun-flat-yamada--ai-dlc-sdk-angular/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Everything runs in the bundled **sandbox** ([docs/sandbox.md](docs/sandbox.md)). The host needs only Docker and Node.js — no `npm ci` on the host. In VS Code, **Reopen in Container** does the same.

npm run sandbox -- up            # build + start the sandbox (firewall, npm ci, Copilot CLI, Chromium)
npm run sandbox -- shell         # a shell inside the sandbox; the commands below run there

npm run aidlc:parse-excel        # Excel -> .ai-dlc/outputs/generated-tests/subsystem-cases.json
npm run aidlc:validate-inputs    # Gate 0 + binding matrix (.ai-dlc/outputs/reports/binding-matrix.md)
npm run aidlc:init-check -- --dry-run
npm run aidlc:run -- --max-iterations 3 --dry-run   # whole pipeline without calling Copilot

Real run (needs a [GitHub Copilot](https://docs.github.com/copilot/how-tos/copilot-cli) subscription and a clean git tree). Copilot CLI is already installed in the sandbox:

copilot login                    # once, inside the sandbox (or COPILOT_GITHUB_TOKEN on the host)
npm run aidlc:init-check
npm run aidlc:run -- --max-iterations 5

Single commands can also be run from the host: `npm run sandbox -- exec npm run aidlc:run -- --max-iterations 5`.

Results: `.ai-dlc/outputs/reports/` (final gate, unresolved issues, QCD), `.ai-dlc/outputs/reverse-docs/`, `.ai-dlc/outputs/telemetry/run-history.json`.

> Read [SECURITY.md](SECURITY.md) before a real run: the agent runs with tool permissions. Every `aidlc:*` > command refuses to run outside the sandbox (`sandbox.enforce: strict` in `aidlc.config.yaml`).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 150 lines
  1. [English](README.md) | [日本語](README.ja.md)
  2. # ai-dlc-sdk-angular
  3. [![CI](https://github.com/sun-flat-yamada/ai-dlc-sdk-angular/actions/workflows/ci.yml/badge.svg)](https://github.com/sun-flat-yamada/ai-dlc-sdk-angular/actions/workflows/ci.yml)
  4. [![Security](https://github.com/sun-flat-yamada/ai-dlc-sdk-angular/actions/workflows/security.yml/badge.svg)](https://github.com/sun-flat-yamada/ai-dlc-sdk-angular/actions/workflows/security.yml)
  5. [![Angular 22](https://img.shields.io/badge/Angular-22-dd0031?logo=angular)](https://angular.dev)
  6. [![GitHub Copilot CLI](https://img.shields.io/badge/GitHub%20Copilot%20CLI-1.0-000?logo=githubcopilot)](https://docs.github.com/copilot/how-tos/copilot-cli)
  7. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
  8. **An in-repository AI-DLC (AI-driven development life cycle) SDK for Angular GUIs of embedded device front panels.**
  9. GitHub Copilot CLI implements a screen from requirements, an HTML/CSS design and a REST API specification,
  10. writes and passes the unit tests, and keeps iterating — at most **N** times — until automated tests derived
  11. from the **human-written Excel subsystem test specification** pass. Afterwards it reverse-generates design
  12. documents along human interpretation axes and compares **QCD** (quality, cost, delivery) with the human
  13. development of the same requirement.
  14. ```mermaid
  15. flowchart LR
  16. subgraph inputs["Human inputs (.ai-dlc/inputs)"]
  17. R[Requirements]
  18. D["HTML/CSS design<br/>data-ui-id"]
  19. A["OpenAPI<br/>operationId"]
  20. B["ui-bindings.yaml<br/>UI ⇄ API ⇄ states"]
  21. X["Excel subsystem tests<br/>@ui-id"]
  22. end
  23. G0{{"Gate 0<br/>input consistency"}}
  24. subgraph loop["Self-healing loop (i = 1..N)"]
  25. C["GitHub Copilot CLI<br/>skills 01-04"]
  26. G1{{"Gate 1 boundary"}}
  27. G2{{"Gate 2 build + lint"}}
  28. G3{{"Gate 3 unit + coverage"}}
  29. G4{{"Gate 4 Excel-derived<br/>Playwright = final gate"}}
  30. end
  31. P["Reverse design docs (skill 05)<br/>QCD report (skill 06)"]
  32. inputs --> G0 --> C --> G1 --> G2 --> G3 --> G4
  33. G4 -- fail: structured failures --> C
  34. G4 -- pass or i = N --> P
  35. ```
  36. ## Why
  37. | Problem when an AI develops embedded GUIs | What this SDK does |
  38. | --- | --- |
  39. | HTML/CSS and OpenAPI do not say *which button calls which API* or *what the screen does on 503* — the AI guesses | **`ui-bindings.yaml`** binds design elements (`data-ui-id`) to API operations (`operationId`), request / response mapping, screen states and error handling; **Gate 0** checks it against the HTML, OpenAPI and Excel before any AI work |
  40. | The AI rewrites code it should only reuse | **Boundary policy** with five zones (`immutable`, `extensible` = append-only, `rebuildable`, `deletable`, `ignored`) enforced with `git diff` and automatic revert |
  41. | "Tests pass" is decided by the AI itself | The **final gate is the human Excel specification**: every case must have a passing Playwright test, expected values are hashed and protected, skipped tests fail the gate |
  42. | The agent runs arbitrary commands with your credentials | Every operation runs in the bundled **sandbox** (dev container): non-root, no-new-privileges, default-deny egress firewall, no host credentials. The harness **refuses to run outside it** |
  43. | Unbounded agent loops | **Max N iterations** with structured failure feedback, then an unresolved-issues summary |
  44. | AI output is hard to review | **Reverse design docs** on four human axes (reuse/delta architecture, screen & state spec, API sequences, requirement ↔ test traceability) |
  45. | "Is it worth it?" | **QCD report**: pass-rate trend, coverage, defects, AI credits / tokens, human effort and lead time vs. the human baseline |
  46. ## Quick start
  47. Everything runs in the bundled **sandbox** ([docs/sandbox.md](docs/sandbox.md)). The host needs only
  48. Docker and Node.js — no `npm ci` on the host. In VS Code, **Reopen in Container** does the same.
  49. ```bash
  50. npm run sandbox -- up # build + start the sandbox (firewall, npm ci, Copilot CLI, Chromium)
  51. npm run sandbox -- shell # a shell inside the sandbox; the commands below run there
  52. npm run aidlc:parse-excel # Excel -> .ai-dlc/outputs/generated-tests/subsystem-cases.json
  53. npm run aidlc:validate-inputs # Gate 0 + binding matrix (.ai-dlc/outputs/reports/binding-matrix.md)
  54. npm run aidlc:init-check -- --dry-run
  55. npm run aidlc:run -- --max-iterations 3 --dry-run # whole pipeline without calling Copilot
  56. ```
  57. Real run (needs a [GitHub Copilot](https://docs.github.com/copilot/how-tos/copilot-cli) subscription and a
  58. clean git tree). Copilot CLI is already installed in the sandbox:
  59. ```bash
  60. copilot login # once, inside the sandbox (or COPILOT_GITHUB_TOKEN on the host)
  61. npm run aidlc:init-check
  62. npm run aidlc:run -- --max-iterations 5
  63. ```
  64. Single commands can also be run from the host: `npm run sandbox -- exec npm run aidlc:run -- --max-iterations 5`.
  65. Results: `.ai-dlc/outputs/reports/` (final gate, unresolved issues, QCD), `.ai-dlc/outputs/reverse-docs/`,
  66. `.ai-dlc/outputs/telemetry/run-history.json`.
  67. > Read [SECURITY.md](SECURITY.md) before a real run: the agent runs with tool permissions. Every `aidlc:*`
  68. > command refuses to run outside the sandbox (`sandbox.enforce: strict` in `aidlc.config.yaml`).
  69. ## Use it in your existing Angular repository
  70. ```bash
  71. npm run aidlc:install -- --target ../your-panel-app --dry-run # preview
  72. npm run aidlc:install -- --target ../your-panel-app
  73. ```
  74. The installer copies the harness, skills, input skeleton and the sandbox (`.devcontainer/`,
  75. `scripts/sandbox.ts`), adds the `aidlc:*` / `sandbox` scripts and devDependencies, and never touches `src/`.
  76. Then run `npm run sandbox -- up` in the target. Then adapt `boundary-policy.yaml` and `.ai-dlc/references/` to your code base.
  77. See [docs/adoption-guide.md](docs/adoption-guide.md).
  78. ## Commands
  79. | Command | Purpose |
  80. | --- | --- |
  81. | `npm run sandbox -- <up\|exec …\|shell\|status\|down\|rebuild>` | Start / use / remove the sandbox from the host (Docker + Node.js only) |
  82. | `npm run aidlc:sandbox-check` | Is this process inside the sandbox (container, egress firewall, no host credentials)? |
  83. | `npm run aidlc:init-check` | Environment check (Node, git, Copilot CLI, Angular CLI, Playwright, inputs, skills) |
  84. | `npm run aidlc:parse-excel` | Excel subsystem tests → structured JSON + checklist |
  85. | `npm run aidlc:validate-inputs` | Gate 0: `ui-bindings.yaml` ⇄ HTML ⇄ OpenAPI ⇄ requirements ⇄ Excel; writes the binding matrix |
  86. | `npm run aidlc:guard` | Boundary check against the baseline (`--revert`, `--snapshot`, `--baseline <ref>`) |
  87. | `npm run aidlc:gate` | Gates 0-4 (`--only build,unit`, `--json`) |
  88. | `npm run aidlc:run` | Full loop (`--max-iterations N`, `--dry-run`, `--skip-post`, `--allow-dirty`, `--no-revert`) |
  89. | `npm run aidlc:reverse-doc` | Reverse design documents only |
  90. | `npm run aidlc:qcd` | QCD comparison report (`--run-id`) |
  91. | `npm run aidlc:schemas` | Regenerate the JSON Schema of `ui-bindings.yaml` |
  92. | `npm run aidlc:install` | Install the SDK into another Angular repository |
  93. | `npm run gate` | Repository quality gate (sandbox check, format, typecheck, lint, unit, harness tests, secret scan, build) |
  94. ## Repository layout
  95. ```text
  96. .devcontainer/ sandbox: Dockerfile, devcontainer.json, egress firewall, allow-list
  97. .ai-dlc/
  98. config/ aidlc.config.yaml, boundary-policy.yaml, schemas/
  99. inputs/ requirements/ ui-design/ api-specs/ ui-bindings/ subsystem-tests/ human-baseline/ (sample: REQ-NET)
  100. references/ existing-architecture, reusable-catalog, panel-hardware-constraints, coding-and-test-conventions
  101. tools/ orchestrator, copilot-cli-adapter, boundary-guard, excel-to-test-ast, validate-inputs,
  102. gate-runner, qcd-calculator, subsystem-kit, install, tests/
  103. outputs/ generated-tests/ reverse-docs/ telemetry/ reports/ (generated, git-ignored)
  104. .github/skills/ 01-context-and-boundary … 06-qcd-benchmark (Agent Skills for Copilot CLI)
  105. src/ sample "existing" Angular 22 front-panel app (800×480, zoneless, signals)
  106. scripts/ sandbox.ts (host launcher of the sandbox), scan-secrets.ts
  107. docs/ sandbox, architecture, input format, adoption guide
  108. ```
  109. ## Documentation
  110. - [Sandbox](docs/sandbox.md) — the isolated environment every command runs in, and how it is enforced
  111. - [Architecture](docs/architecture.md) — loop, gates, telemetry, safety model
  112. - [Input format](docs/input-format.md) — why and how to bind HTML/CSS to the REST API (`ui-bindings.yaml`, Excel notation)
  113. - [Adoption guide](docs/adoption-guide.md) — install into an existing repository, tune the boundary policy, run a pilot
  114. - [Original specification](specs/2026-11-18_scaffolding-ai-dlc-sdk-angular/spec.md) (Japanese)
  115. ## Status
  116. `0.1.0` — the harness, skills, input validation and dry-run pipeline are tested in CI. Gates 0-4 were also
  117. verified end to end against a reference implementation of the sample screen (not committed, because the
  118. sample code base must stay in its "before" state): build, lint, 37 unit tests at 99 % line coverage and 8/8
  119. Excel-derived Playwright cases passed, and wrong texts, skipped tests and append-only violations were
  120. rejected. Real Copilot CLI runs depend on your Copilot plan and environment; please report results and issues.
  121. ## License
  122. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.