claude

aldc-verify

Verifiable AL loop for Business Central: compile, analyzers and a Stop gate.

0 on GitHubby javiarmestov0.3.0MITupdated 28 days ago
/

Plugin aldc-verify from marketplace aldc-verify-dev in javiarmesto/aldc-verify-plugin. Commands read from the repo's manifest — 26 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (4)

  • al-go

    Ship finished AL work without waiting for a human - verify (compile + analyzers), BCQuality review if installed, commit file by file, push a claude/ branch and open a draft PR. Use when a task's AL changes are complete and you want them delivered for review; the guard hook blocks merges, force pushe

  • al-learn

    After the user corrects how you worked in an AL repo (a convention, a rule, a mistake not to repeat), propose ONE line for the repo's CLAUDE.md and add it only if the user approves. Use right after such a correction, or when the user says "apréndetelo", "que no vuelva a pasar", "add this to CLAUDE.m

  • al-verify

    Compile the repo's Business Central AL projects (L1) and run the code analyzers (L2), returning a short grouped summary of errors and warnings. Use after changing AL code, before saying work is done, or when the user asks to build, compile, check or verify AL.

  • init

    Apply the aldc-verify layer to an AL repo without overwriting anything - .claude/aldc-verify.json (BC version + pinned compiler), .claude/settings.json, CLAUDE.md, .gitignore entry and a GitHub Actions compile workflow. Only runs when the user invokes it.

Subagents (1)

  • al-build-validator

    Compiles the repo's Business Central AL projects (L1) and runs the code analyzers (L2), then returns only grouped diagnostics with likely root causes, so compiler output never floods the main context. Read-only - never edits files. Use after implementing AL changes, before review or commit, or when

Hooks (6)

  • SessionStart

    node

  • UserPromptSubmit

    node

  • PreToolUse

    node

  • SubagentStart

    node

  • SubagentStop

    node

  • Stop

    node

View source on GitHub

Similar plugins

ruflo-iot-cognitum

claude

IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware

5 skills · 1 command · 4 agents

ruvnet/ruflo 81,589

hunter

claudecodex

Find and verify professional email addresses, search contacts by domain, and enrich company data -- directly in Claude.

13 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

operating-kit

claude

Portable operating method: session lifecycle agents, pre-ship code review, deploy with live verification and state doc update, and production log health check

5 agents

wshobson/agents 42,461

agent-launcher-skills

claude

Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).

6 skills · 8 commands · 4 agents · hooks

alirezarezvani/claude-skills 29,725

ml-paper-writing

claude

Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Includes LaTeX templates, citation verification, reviewer guidelines, publication-quality figure generation, systems paper structural blueprints, and conference presentation slides.

98 skills

Orchestra-Research/AI-Research-SKILLs 14,502

dbs-theory-grounding

claude

理论溯源与案例重释。审查 PPT、课程、文案或方法论中的经验判断，先判断命题是否成立，再匹配并核实可信理论，用该理论重释案例并标明边界。适用于给自创理论找依据、给 PPT 补理论来源、判断一句话能否上升为理论、检查是否硬套名人；聚焦单次理论锚定，不默认展开历史同构研究。

1 skill

dontbesilent2025/dbskill 11,416

Maintain aldc-verify?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted