Automated summary
Performs a structured multi-pass analysis of an existing codebase and writes a colonization report (stack, architecture, API catalog, data layer, tech debt) into .aether/data/colonization/.
Strengths
- Six-step sweep covering stack detection, architecture mapping, API surface, data layer and a tech-debt scan
- Persists findings as separate markdown documents plus an executive orientation summary
- Incremental mode diffs against existing colonization data instead of re-scanning everything
- Honours .gitignore and skips vendored dependencies and build artifacts by default
Limitations
- Assumes the Aether colony framework: agent roles, pheromone tagging and the .aether/ output directory won't exist elsewhere
- Only the top three directory levels and public interfaces are mapped; nothing is verified by running the code or its tests
- The tech-debt scan is pattern-based (TODO/FIXME, deprecated dependencies) and can miss design-level debt
Use when an agent is dropped into an unfamiliar existing repository and you need an onboarding map before any planning starts.
Don't use it on a greenfield project with no code, or for a one-file question where a full report is overkill.
Security analysis
SafeThe skill instructs read-only analysis of an existing codebase and writing structured reports to a local .aether directory. It does not execute destructive commands, exfiltrate data, or use network/obfuscation. The only write action is benign file generation for documentation.
No concerns found
How this analysis is madeExamples
Analyze this codebase and colonize it — map the tech stack, architecture and API surface, and give me a prioritized tech debt list before we plan any work.We just landed on this Express/PostgreSQL/Redis repo. Run the brownfield analysis and write the colony orientation report so the team knows the top risks and where to start.Diff against what's already in .aether/data/colonization/ and update only the parts of the report that changed.source: shipped name: brownfield-codebase-analysis description: Use during colonize to understand an existing codebase before planning work type: colony domains: [analysis, onboarding, codebase-intelligence] agent_roles: [surveyor-provisions, surveyor-nest, surveyor-disciplines, surveyor-pathogens, scout, architect] workflow_triggers: [colonize] priority: normal version: "1.0"
Brownfield Codebase Analysis
Purpose
When a colony lands on an existing codebase (brownfield project), it needs structured understanding before it can plan work. This skill performs deep analysis producing a colonization report -- the colony's orientation map.
When to Use
- User says "analyze this codebase" or "colonize this repo"
- Colony is initialized on an existing project with code already present
- Before planning phases on a brownfield project
- When onboarding to a project the colony hasn't seen before
Instructions
1. Reconnaissance Sweep
1. Scan top-level files: package.json, Cargo.toml, go.mod, pyproject.toml, etc.
2. Identify primary language, framework, and build system
3. Detect test framework and CI/CD configuration
4. Map directory structure (top 3 levels)
5. Identify entry points (main files, index files, config files)
2. Architecture Mapping
1. Trace import/dependency graph from entry points
2. Identify architectural patterns (MVC, microservices, monorepo, etc.)
3. Map module boundaries and their responsibilities
4. Detect data flow: where data enters, transforms, and persists
5. Catalog external service integrations
3. API Surface Catalog
1. Extract all public API endpoints (REST, GraphQL, RPC)
2. Map function signatures of exported/public modules
3. Identify CLI commands if applicable
4. Document authentication and authorization patterns
5. Note rate limiting, versioning, and deprecation markers
4. Data Layer Analysis
1. Identify database type and schema (SQL models, NoSQL documents)
2. Map ORM/ODM usage and migration patterns
3. Trace data flow from user input to persistence
4. Identify caching layers and strategies
5. Catalog background jobs and queue systems
5. Tech Debt Scan
1. Search for TODO, FIXME, HACK, XXX comments
2. Identify deprecated dependency usage
3. Detect dead code paths (unused exports, unreachable branches)
4. Flag inconsistent patterns (mixed state management, duplicate utilities)
5. Note security anti-patterns (hardcoded secrets, SQL injection risks)
6. Colony Report Generation
Write structured documents to .aether/data/colonization/:
tech-stack.md-- Language, frameworks, tools, versionsarchitecture.md-- System design, module map, data flowsapi-catalog.md-- All public interfacesdata-layer.md-- Storage, schemas, migrationstech-debt.md-- Prioritized debt inventorycolony-orientation.md-- Executive summary for colony onboarding
Key Patterns
- Shallow first, deep on demand: Start with broad surface analysis, go deeper only where the colony will work.
- Emit pheromones: Tag high-complexity areas with warning pheromones so planners know to budget extra time.
- Respect
.gitignore: Never analyze node_modules, vendor, or build artifacts. - Incremental updates: If colonization data exists, diff against it rather than rebuilding from scratch.
Output Format
COLONIZATION REPORT -- {project_name}
Language: {primary} ({version})
Framework: {name} ({version})
Architecture: {pattern}
Modules: {count} identified
APIs: {count} endpoints
Data Stores: {list}
Tech Debt Items: {count} ({critical} critical, {high} high)
Colonization Score: {1-10} (10 = fully understood)
Key Risks: {top 3 risk areas}
Recommended First Phase: {suggestion}
Examples
Colonize a Node.js API:
"Colonizing... Detected Express.js API with PostgreSQL, Redis cache, and Bull queue system. 47 endpoints cataloged. 23 tech debt items found (3 critical: auth token rotation, SQL string concatenation in user search, expired SSL cert in config). Colony orientation complete."
Re-colonize after changes:
"Incremental colonization... 3 new modules detected, 2 APIs changed. Tech debt reduced by 5 items. Colonization score improved from 6 to 8."
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/brownfield-codebase-analysis-mrzxuqt9/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/brownfield-codebase-analysis-mrzxuqt9' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/brownfield-codebase-analysis-mrzxuqt9/download' --output '.skill-downloads/brownfield-codebase-analysis-mrzxuqt9/SKILL.md.part' && mv '.skill-downloads/brownfield-codebase-analysis-mrzxuqt9/SKILL.md.part' '.skill-downloads/brownfield-codebase-analysis-mrzxuqt9/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/brownfield-codebase-analysis-mrzxuqt9/SKILL.md' && test -s '.skill-downloads/brownfield-codebase-analysis-mrzxuqt9/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/brownfield-codebase-analysis' && cp -R '.skill-downloads/brownfield-codebase-analysis-mrzxuqt9' '.claude/skills/brownfield-codebase-analysis'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/brownfield-codebase-analysis-mrzxuqt9'openskills read 'brownfield-codebase-analysis-mrzxuqt9'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/brownfield-codebase-analysis-mrzxuqt9/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.