Agent skill

Delphi Code Reviewer

by gustavoeenriquez in gustavoeenriquez/MakerAi

Reviews Delphi or Pascal code for memory leaks, invalid object access and swallowed exceptions, reporting only what it finds in a fixed severity format.

MITAuto-check passedDevelopment

SKILL.md written in Spanish; this summary is our English description.

Install Delphi Code Reviewer

skills CLI
$ npx skills add gustavoeenriquez/MakerAi --skill revisor-delphi -a claude-code

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

GitHub CLI
$ gh skill install gustavoeenriquez/MakerAi revisor-delphi --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/gustavoeenriquez/MakerAi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Demos/091-Skills/skills/revisor-delphi .claude/skills/revisor-delphi && 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
revisor-delphi
GitHub stars
212
Token cost
~166 tokens
SKILL.md length
80 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Reviews Delphi or Pascal code for memory leaks, invalid object access and swallowed exceptions, reporting only what it finds in a fixed severity format.

  • Works in 4 steps: Fugas de memoria: objetos creados sin… → Accesos inválidos: uso de objetos ya… → Excepciones tragadas: except vacíos o… → …
  • Reviewing Delphi or Pascal code for memory and resource leaks
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Checking for use of already-freed objects or bad array indexes

What it does

Written in Spanish, the skill instructs the agent to act as a Delphi code reviewer and check, in order, for memory leaks from objects created without try/finally or an owner, invalid access such as using already-freed objects or out-of-range indexes, and swallowed exceptions from empty or error-hiding except blocks. Style issues are only reported when nothing more serious is found.

Findings are returned as a list in the format severity, approximate line, problem, and the suggested correction. If the code has no issues, the reply is exactly "Sin hallazgos" (no findings), with no other commentary.

When your agent uses it

  • Reviewing Delphi or Pascal code for memory and resource leaks
  • Checking for use of already-freed objects or bad array indexes
  • Finding exception handlers that hide errors

Example prompts

  • “Revisa este código Delphi en busca de fugas de memoria.”
  • “Review unit1.pas for invalid object access and swallowed exceptions.”
  • “Check this Pascal procedure and report any memory leaks with a fix.”

Requirements

  • Pre-approved tools (allowed-tools): Read

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Fugas de memoria: objetos creados sin try/finally o sin dueño.
  2. Accesos inválidos: uso de objetos ya liberados, índices fuera de rango.
  3. Excepciones tragadas: except vacíos o que ocultan el error.
  4. Estilo: solo si no hay nada de lo anterior.

What it can do on your machine

Read from SKILL.md and the folder at commit 39c093b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Delphi Code Reviewer loads about 166 tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 80 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~166

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 gustavoeenriquez/MakerAi at commit 39c093b, republished under its MIT licence (© gustavoeenriquez). 80 words, ~166 tokens.

Download SKILL.mdSave it as .claude/skills/revisor-delphi/SKILL.md (or your agent's skills folder).
name
revisor-delphi
description
Úsalo cuando el usuario pida revisar código Delphi o Pascal en busca de errores.
allowed-tools
Read

Eres un revisor de código Delphi. Revisa en este orden y reporta solo lo que encuentres:

  1. Fugas de memoria: objetos creados sin try/finally o sin dueño.
  2. Accesos inválidos: uso de objetos ya liberados, índices fuera de rango.
  3. Excepciones tragadas: except vacíos o que ocultan el error.
  4. Estilo: solo si no hay nada de lo anterior.

Formato de la respuesta: una lista con [SEVERIDAD] línea aproximada: problema -> corrección. Si el código está bien, responde exactamente: Sin hallazgos.

© gustavoeenriquez, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in Demos/091-Skills/skills/revisor-delphi of gustavoeenriquez/MakerAi.

Open the folder on GitHubat commit 39c093b

Compare with similar skills

Delphi Code Reviewer 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.

Delphi Code Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Delphi Code Reviewer this skillgustavoeenriquez/MakerAi212—~166Automated safety check: PassMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
SeekDB Code Reviewoceanbase/seekdb3.1k—~2.1kAutomated safety check: PassApache-2.0
Cross-Language Coding Standardszereight/gitlab-mcp2k1 repos~1.4kAutomated safety check: PassMIT
Code Qualitypiomin/claude-ai-spring-boot1.3k—~2.2kAutomated safety check: PassApache-2.0
Blindspot Code Critiqueyologdev/yoyo-evolve1.9k—~2.2kAutomated safety check: PassMIT

Similar skills

  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • SeekDB Code Review

    oceanbase/seekdb

    Reviews seekdb pull requests and diffs for real defects in correctness, resources, concurrency, security and tests, reporting only Blocker or Major findings.

    3.1k GitHub stars~2.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Shared reference for naming, function size, complexity and error handling rules that reviewer agents apply across TypeScript, Python, Go, Rust, Java, C# and Swift.

    2k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • Code Quality

    piomin/claude-ai-spring-boot

    Comprehensive code review for Java - clean code principles, API contracts, null safety, exception handling, and performance.

    1.3k GitHub stars~2.2k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • Blindspot Code Critique

    yologdev/yoyo-evolve

    Runs a structured critique of code, architecture or APIs to surface what familiarity hides, such as panics, security holes and design debt.

    1.9k GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Java Code Review

    decebals/claude-code-java

    Checklist-driven review of Java code covering null safety, exception handling, collections and streams, and concurrency, with findings reported by severity.

    751 GitHub stars~2.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from gustavoeenriquez/MakerAi

  • Facturas

    gustavoeenriquez/MakerAi

    Úsalo cuando el usuario pida redactar una factura, una cuenta de cobro o una nota de cobro.

    212 GitHub stars~127 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Delphi Code Reviewer

What does Delphi Code Reviewer do?

Reviews Delphi or Pascal code for memory leaks, invalid object access and swallowed exceptions, reporting only what it finds in a fixed severity format. Written in Spanish, the skill instructs the agent to act as a Delphi code reviewer and check, in order, for memory leaks from objects created without try/finally or an owner, invalid access such as using already-freed objects or out-of-range indexes, and swallowed exceptions from empty or error-hiding except blocks. Style issues are only reported when nothing more serious is found.

When should I use Delphi Code Reviewer?

Delphi Code Reviewer fits situations like: reviewing Delphi or Pascal code for memory and resource leaks; checking for use of already-freed objects or bad array indexes; finding exception handlers that hide errors.

How do I install Delphi Code Reviewer in Claude Code?

Run `npx skills add gustavoeenriquez/MakerAi --skill revisor-delphi -a claude-code`. Or copy the skill folder (Demos/091-Skills/skills/revisor-delphi in gustavoeenriquez/MakerAi) into .claude/skills/revisor-delphi in your project. Claude Code loads it when a task matches its description.

How do I install Delphi Code Reviewer in Codex?

Run `npx skills add gustavoeenriquez/MakerAi --skill revisor-delphi -a codex`. Or copy the skill folder (Demos/091-Skills/skills/revisor-delphi in gustavoeenriquez/MakerAi) into .agents/skills/revisor-delphi in your project. Codex loads it when a task matches its description.

Can I use Delphi Code Reviewer 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 gustavoeenriquez/MakerAi --skill revisor-delphi -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/revisor-delphi, .gemini/skills/revisor-delphi, .github/skills/revisor-delphi and .opencode/skills/revisor-delphi in your project.

What does Delphi Code Reviewer need to run?

SKILL.md names no scripts, command-line tools or credentials: Delphi Code Reviewer is instructions for the agent only. Its frontmatter pre-approves these tools: Read.

Does Delphi Code Reviewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Delphi Code Reviewer 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 Delphi Code Reviewer use?

Delphi Code Reviewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Delphi Code Reviewer use?

About 166 tokens (SKILL.md is roughly 664 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 Delphi Code Reviewer?

Skills that share tags, products or a category with Delphi Code Reviewer: Mole Bug Patterns (tw93/Mole, 70k stars), SeekDB Code Review (oceanbase/seekdb, 3.1k stars), Cross-Language Coding Standards (zereight/gitlab-mcp, 2k stars) and Code Quality (piomin/claude-ai-spring-boot, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Delphi Code Reviewer?

gustavoeenriquez (a GitHub user) maintains it in gustavoeenriquez/MakerAi, which has 212 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

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