Pre Landing Review

Community

Mathews-Tom

pre-landing-review

Gate-oriented safety audit for code changes before landing, using a checklist with two-pass severity triage. Triggers on: "is this safe to land", "pre-landing review", "safety check before merge", "gate check", "/pre-landing-review". NOT for diff review, use pr-review.

Overview

Publisher	Mathews-Tom
Repository	`armory`
Skill name	`pre-landing-review`
Stars	318
Forks	47
Bundled files	2
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Mathews-Tom on GitHub. Read the source before you install it.

Installation

Install the Pre Landing Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Mathews-Tom/armory.git /tmp/armory
mkdir -p .claude/skills
cp -r /tmp/armory/skills/pre-landing-review .claude/skills/pre-landing-review

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pre Landing Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pre Landing Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pre Landing Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Pre-Landing Review

Gate-oriented safety audit for code changes before landing. Uses a structured checklist with two-pass severity triage and blocking/non-blocking classification.

Distinct from pr-review: pr-review is a multi-dimension code quality review. This skill is a gate-oriented safety audit — it uses an external checklist with two-pass severity triage and a blocking/non-blocking classification.

Native alternative: Claude Code's /ultrareview runs a dedicated native review session optimized for bug-finding (Anthropic ships three free per month on Pro/Max plans at Opus 4.7's launch). Use this skill for checklist-driven, gate-oriented blocking classification with a documented triage protocol; use /ultrareview for lightweight bug-hunting on a single change.

Workflow

1. Determine Diff

Identify the changes to review:

If on a feature branch: diff against the default branch (git symbolic-ref refs/remotes/origin/HEAD)
If given a PR number: fetch that PR's diff
If given specific files: review those files

2. Load Checklist

Read references/checklist.md. This is mandatory — if the checklist is unreadable, STOP and report the error.

3. Pass 1 — CRITICAL (blocking)

Review the diff against critical safety categories. These are potential ship-blockers.

SQL & Data Safety

Raw SQL without parameterization
Schema changes without migration safety (lock timeout, reversibility)
Bulk updates/deletes without WHERE clause verification
Direct column updates bypassing model validations/callbacks

Race Conditions & Concurrency

Read-then-write without locking
Unique constraint reliance without database-level enforcement
Shared mutable state without synchronization
Queue/background job idempotency

Trust Boundaries

LLM/AI output used in SQL, shell commands, or rendered HTML without sanitization
User input reaching privileged operations without validation
External API responses used without schema validation
Deserialization of untrusted data

For each CRITICAL finding:

Cite exact file and line
Explain the specific risk
Use AskUserQuestion with exactly three options: Fix now / Acknowledge risk / False positive
If "Fix now": make the fix, then re-check
If "Acknowledge": record acknowledgment, continue
If "False positive": record, continue

4. Pass 2 — INFORMATIONAL (non-blocking)

Review against remaining categories:

Conditional Side Effects — side effects hidden in conditional branches, callbacks triggered by state changes, error handlers silently swallowing failures.

Magic Numbers — unexplained numeric literals, hardcoded thresholds without constants, timeout values without rationale.

Dead Code — unreachable branches, unused imports, commented-out code without explanation.

Test Gaps — new code paths without test coverage, modified behavior without updated tests, missing edge case and error path tests.

Crypto & Entropy — weak random sources for security contexts, hardcoded secrets, missing TLS/encryption for sensitive data in transit.

Time Window Safety — timezone-naive comparisons, daylight saving edge cases, cron expressions not accounting for clock skew.

Type Coercion — implicit type conversions that could lose data, numeric precision loss across boundaries, implicit string encoding at I/O boundaries.

Present all informational findings in a single summary table (file, line, category, description).

5. Gate Classification

All Pass 1 issues resolved (fixed or acknowledged) → CLEAR TO LAND
Any unresolved Pass 1 issue → BLOCKED
Pass 2 issues are advisory — they don't block landing

6. Suppressions

Do NOT flag:

Test files using test fixtures/factories
Migration files following framework conventions
Comments explaining why a pattern is intentional
Configuration files with documented values
Type stubs or interface definitions

Output

Gate verdict (CLEAR TO LAND / BLOCKED), critical issues summary with resolution status, informational findings table.

This skill is read-only by default — only modifies code when user explicitly chooses "Fix now" on a critical issue.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

evals/cases.yaml2 KB
references/checklist.md3 KB

Frequently asked questions

What does the Pre Landing Review AI skill do?

Why use Pre Landing Review on TypingMind?

Because you install it once and use it with any model. Pre Landing Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pre Landing Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Mathews-Tom/armory/tree/main/skills/pre-landing-review. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pre Landing Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pre Landing Review?

As many as you like. As long as a model supports skills, you can use Pre Landing Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pre Landing Review AI skill free?

Yes. It is published on GitHub by Mathews-Tom under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Skill Reviewer

bytedance

OrganizationPopular

Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.

Ahrefs Automation

Automate SEO research with Ahrefs -- analyze backlink profiles, research keywords, track domain metrics history, audit organic rankings, and perform batch URL analysis through the Composio Ahrefs…

Django Patterns

Patrones de arquitectura Django, diseño de API REST con DRF, buenas prácticas de ORM, caché, señales, middleware y aplicaciones Django de nivel producción.

Quarkus Patterns

Patrones de arquitectura Quarkus 3.x LTS con Camel para mensajería, diseño de API RESTful, servicios CDI, acceso a datos con Panache y procesamiento asíncrono.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Pre-Landing Review

Workflow

1. Determine Diff

2. Load Checklist

3. Pass 1 — CRITICAL (blocking)

SQL & Data Safety

Race Conditions & Concurrency

Trust Boundaries

4. Pass 2 — INFORMATIONAL (non-blocking)

5. Gate Classification

6. Suppressions

Output

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now