Claude-Tools-for-Delphi

In the author's own words, from each skill's SKILL.md — showing the first 30 of 32 files.

• light-bug-Android

  Triage a Delphi FMX Android bug/crash from the PC over adb: capture logcat, pull the app's LightCore.ExceptionLogger log via run-as, classify the failure (SIGUSR1 IDE noise / Pascal exception / Java exception / native tombstone / deployment), symbolicate stripped-.so addresses against the linker .map (Tools\MapLookup.ps1), then root-cause and fix (build via light-compiler, never release). Use whe…

  .claude/skills/light-bug-Android/SKILL.md on GitHub (opens in a new tab)

• light-bug-BioniX

  Alias for /light-bug-MadShi with the BioniX product preselected. Diagnose and fix a BioniX Wallpaper crash report from Thunderbird, then build (never release). Use when the user says "/light-bug-BioniX", "new BioniX bug report", "check the latest BioniX crash", or similar.

  .claude/skills/light-bug-BioniX/SKILL.md on GitHub (opens in a new tab)

• light-bug-MadShi

  Diagnose and fix a Delphi crash report (madExcept .mad) for any registered product (BioniX, ...). Reads the product profile in products.ini, lists the recent .mad attachments across that product's Thunderbird mbox(es), lets the user pick one (or accept the newest), then launches the light-bug-MadShi agent to diagnose, fix, and build (never release). This is the crash-report-specific pipeline behi…

  .claude/skills/light-bug-MadShi/SKILL.md on GitHub (opens in a new tab)

• light-bug

  Diagnose and fix a Delphi bug end-to-end, however it arrived: a Thunderbird crash report (.mad), a pasted exception/stack trace, or a symptom described in plain words. Routes internally — a .mad or 'crash report' goes to the light-bug-MadShi pipeline, an Android-only symptom hands off to /light-bug-Android, everything else runs here: intake, reproduce (a failing DUnitX test preferred), localize,…

  .claude/skills/light-bug/SKILL.md on GitHub (opens in a new tab)

• light-code-ArchitectureClass

  Audit a Delphi project's own classes, forms included, for bad shapes — god classes, anemic data classes, misplaced responsibility, fat config records, shared mutable singletons, Ex-downcast holders. Reports ranked reshapes (extract-class, move-method, replace-singleton); never refactors. Say "is this a god class", "review the class design", "find anemic classes", "which classes carry too many res…

  .claude/skills/light-code-ArchitectureClass/SKILL.md on GitHub (opens in a new tab)

• light-code-ArchitectureUnit

  Audit a Delphi project's own units (files) for SHALLOW modules that should merge into one deep module — information leakage, temporal decomposition, pass-through layers, always-paired usage. Reports ranked merge candidates; never merges. Say "find shallow units", "what units should be merged", "which files should be folded together", "audit the module structure". For CLASS shapes use light-code-A…

  .claude/skills/light-code-ArchitectureUnit/SKILL.md on GitHub (opens in a new tab)

• light-code-CheckOsCompatibility

  Audit Delphi FMX source for cross-platform issues — Windows-only APIs, hardcoded paths, missing platform conditionals, mobile-incompatible patterns. Say "check this for Android/iOS", "is this safe on mobile/macOS/Linux", "audit for cross-platform issues".

  .claude/skills/light-code-CheckOsCompatibility/SKILL.md on GitHub (opens in a new tab)

• light-code-StyleChecker

  Scan imported/3rd-party Delphi code for style compliance, common mistakes, dangerous patterns (leaks, unsafe casts, missing try/finally). Not for our own code — use /light-review-Full. Say "check this 3rd-party unit", "scan the imported library".

  .claude/skills/light-code-StyleChecker/SKILL.md on GitHub (opens in a new tab)

• light-code-Win64Audit

  Audit Delphi source for Win64 truncation bugs — pointer-width API results (DWORD_PTR/LRESULT/handles) stored in 32-bit variables (Integer/Cardinal/DWORD/UInt), and 32-bit casts of pointers passed to the API. Say "audit for Win64 bugs", "check 64-bit safety", "search for SysIL-class bugs".

  .claude/skills/light-code-Win64Audit/SKILL.md on GitHub (opens in a new tab)

• light-md-Coherent

  Say the last answer again in plain, short English — the jargon-stripped version, an N-point version, or an explanation of just the part that did not land. Use when the user says "in plain English", "coherent", "I do not understand", "I have no clue", "what does that mean", "rephrase that", "too long", "shorter", "TL;DR", "give me 3 points", "wait, what?", "short answer". Rewrites what was ALREADY…

  .claude/skills/light-md-Coherent/SKILL.md on GitHub (opens in a new tab)

• light-md-DelphiIdiom

  Fix Delphi vocabulary and writing-clarity issues in the Markdown documentation of a Delphi project — swap terms borrowed from C, Java or Python for the Delphi word, plus bounded clarity rewrites. Say "check vocab", "fix vocabulary", "delphi terms", "vocab pass", "scan docs for vocab", "clean up the md", "fix the docs". Also fire it yourself, without being asked, after writing or editing any *.md…

  .claude/skills/light-md-DelphiIdiom/SKILL.md on GitHub (opens in a new tab)

• light-md-DriftUpdate

  Scan project markdown docs (CLAUDE.md, README.md, docs/*.md) for drift after code changes. Flag sections out of sync with current code — class names, file paths, settings keys, procedure signatures, architecture claims. Propose and apply concrete edits. Use when the user says "update md", "check docs", "verify docs", "refresh claude.md", "are the docs still accurate", "doc drift check". Also fire…

  .claude/skills/light-md-DriftUpdate/SKILL.md on GitHub (opens in a new tab)

• light-md-PruneClaudeMD

  Prune and tighten a CLAUDE.md or other agent/skill instruction markdown — cut bloat/duplication, fix stale rules, relayer misplaced content, without losing load-bearing info. Backs up first. Say "clean up this CLAUDE.md", "my CLAUDE.md is too long".

  .claude/skills/light-md-PruneClaudeMD/SKILL.md on GitHub (opens in a new tab)

• light-new-Align

  One-question-at-a-time design interview before any non-trivial Delphi task — each question carries your recommended answer, highest-stakes first, skip what you can decide yourself. Say "align first", "interview me", or "ask before you build".

  .claude/skills/light-new-Align/SKILL.md on GitHub (opens in a new tab)

• light-new-Feature

  Turn "I want feature X" into a designed, sliced, test-driven Delphi implementation — align, PRD, vertical slices, red-green each (failing DUnitX test first), then hand to light-review-PostEdit / light-review-Full. Say "add a feature", "build feature X", "implement a new feature", "create a new screen/dialog/option".

  .claude/skills/light-new-Feature/SKILL.md on GitHub (opens in a new tab)

• light-ref-DesignPatterns

  Quick index of the GoF design patterns that actually pay off in Delphi desktop/mobile code, each with its Delphi-native shortcut (anonymous methods, virtual methods, System.Messaging, class functions, enumerators) so you reach for the full pattern only when it earns its keep. Load this when choosing a structure for varying behaviour, decoupling producer from consumer, building objects step by ste…

  .claude/skills/light-ref-DesignPatterns/SKILL.md on GitHub (opens in a new tab)

• light-ref-Memory

  Reference for Delphi memory-safety and exception handling — the try..finally gold standard, freeing owned fields, FreeAndNil, Owner-managed components, functions that return objects, specific try..except, domain exception hierarchies and bare raise. Load this when writing or reviewing code that creates objects, manages lifetimes, or handles exceptions.

  .claude/skills/light-ref-Memory/SKILL.md on GitHub (opens in a new tab)

• light-ref-Refactoring

  Reference catalog of behaviour-preserving Delphi refactorings — Extract Method, Extract Class, Guard Clauses, Named Constants, Replace Conditional with Polymorphism, Introduce Parameter Object (record), Remove with, Rename, Inline Method, and introducing a test seam via a shared base class. Load this when cleaning up smelly code, taming a long method or god class, or planning a safe refactor. Ada…

  .claude/skills/light-ref-Refactoring/SKILL.md on GitHub (opens in a new tab)

• light-ref-Threading

  Reference for writing or reviewing Delphi threading code on VCL and FMX (incl. Android/iOS) — TThread, TThread.CreateAnonymousThread, PPL (TTask/TParallel/TFuture), Synchronize vs Queue, TInterlocked/TCriticalSection/TMonitor/TLightweightMREW, TThreadList/TThreadedQueue/TEvent, graceful cancellation and thread-safety. Load this when a task works with threads, or touches shared state from more tha…

  .claude/skills/light-ref-Threading/SKILL.md on GitHub (opens in a new tab)

• light-review-Critical

  Counter-analyze review findings already in this conversation, verify each surviving claim against the code and the documentation, drop the false positives, then fix every one that remains — not just the easy ones. Use whenever a review, audit, listing or subagent report has produced findings and the next step is deciding which of them are real — "counter-analyze these findings", "vet and fix", "v…

  .claude/skills/light-review-Critical/SKILL.md on GitHub (opens in a new tab)

• light-review-DelphiExceptions

  Audit every try..except in a Delphi project and judge each one - does it hide OUR bug from madExcept, or correctly absorb an environment failure (locked folder, full disk, dropped share)? Gives each block a verdict (JUSTIFIED / SILENT / BLIND / NARROW / UNSURE) plus the exact exception classes to narrow it to. Say "check the try/except blocks", "audit exception handling", "are we swallowing excep…

  .claude/skills/light-review-DelphiExceptions/SKILL.md on GitHub (opens in a new tab)

• light-review-DUnitX

  Reference for structuring Delphi DUnitX unit tests — test project layout, [TestFixture]/[Setup]/[TearDown]/[Test], Method_Scenario_Expected naming, the assertion cheat-sheet, substituting collaborators with a concrete fake (shared base, no interface required), and SQLite :memory: integration tests. Load this when writing, organising or reviewing DUnitX tests. Adapted to Gabriel's rules — no fake/…

  .claude/skills/light-review-DUnitX/SKILL.md on GitHub (opens in a new tab)

• light-review-FakeTest

  Audit a Delphi DUnitX/DUnit suite for FAKE or WEAK tests that pass without verifying the behavior they name (zero assertions, Assert.Pass-only, tautologies, setup-only). Establishes the green baseline, launches the auditor agent, and can PROVE fakeness with a git-safe mutation pass. Say "are these tests fake", "audit test integrity", "did we game the tests to pass".

  .claude/skills/light-review-FakeTest/SKILL.md on GitHub (opens in a new tab)

• light-review-Full

  Full three-stage Delphi code review pipeline: find correctness bugs, counter-analyze and apply the fixes that survive, verify them and compile. Say "review this Delphi code", "code review FormFoo.pas", "deep review the Lib folder", "review the code I just changed", "check this unit for bugs", "is this code correct". With no file named it reviews whatever `git status` shows as uncommitted, so it w…

  .claude/skills/light-review-Full/SKILL.md on GitHub (opens in a new tab)

• light-review-PostEdit

  Verify the code you just wrote (fix or feature) works — confirm each change matches intent, broke nothing observable, missed no call sites, didn't break DFM/FMX bindings; revert what fails; then test or compile through the light-compiler agent. Use when the user says "check what you just changed", "verify your edits", "did that break anything", "post-edit review", "make sure the fix is right". Fi…

  .claude/skills/light-review-PostEdit/SKILL.md on GitHub (opens in a new tab)

• light-review-RedGreen

  Red-green TDD for any Delphi change (new behavior OR bug fix): write the FAILING DUnitX test first, confirm red on its assertion (not a compile error), then drive to green, compiling only via the light-compiler agent. For a bug the failing test is the reproduction. Say "TDD this", "write the test first", "reproduce the bug with a test", "red-green".

  .claude/skills/light-review-RedGreen/SKILL.md on GitHub (opens in a new tab)

• light-security-ClaudeSettingsAudit

  Audit Claude Code config files (settings.json, settings.local.json, .mcp.json) across the computer for unsafe or malicious content — hooks that run shell commands, credential/proxy env vars, arbitrary MCP servers, permission-bypass modes, over-broad allow rules. Classifies each finding DANGEROUS / SUSPICIOUS / SAFE. Read-only. Use when the user invokes `/light-security-ClaudeSettingsAudit`, says…

  .claude/skills/light-security-ClaudeSettingsAudit/SKILL.md on GitHub (opens in a new tab)

• light-task-DerailmentCheck

  Pause mid-task and verify your own conclusions before continuing: classify every load-bearing conclusion VERIFIED / INFERRED / ASSUMED with evidence, actively attack the unverified ones, and find the earliest wrong turn if one exists. Not Delphi-specific — usable in any long or drifting task, in any language. Use when the user says "derailment check", "are you on track", "checkpoint yourself", "p…

  .claude/skills/light-task-DerailmentCheck/SKILL.md on GitHub (opens in a new tab)

• light-web-CodeReview

  Review HTML, CSS, or JavaScript for errors, formatting, best practices, accessibility, cross-browser issues. Say "review this HTML/CSS/JS", "check my stylesheet", or after writing/editing web frontend code.

  .claude/skills/light-web-CodeReview/SKILL.md on GitHub (opens in a new tab)

• light-web-PushToFTP

  Release a Delphi tool's new version to its website FTP. Reads the tool's ReleaseProfile.md and follows it. Use when the user says "push <tool> to FTP", "release a new version", "upload the new build", "promote to stable".

  .claude/skills/light-web-PushToFTP/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 127k stars · 1 skill