Install
$ agentstack add skill-latticecast-claude-skills-developing-onboarding ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Codebase Onboarding
Explore a codebase and produce .tmp/llm*.md docs so future Claude sessions (and humans) can ramp up instantly.
Process
1. Register Project in LatticeCast PM
Use Skill(developing-project-management) — "Setup Project" section.
This creates the PM board with tickets, views (Table/Kanban/Timeline), and shared workspace.
2. Scan Project Root
Read overview first (if they exist). ex:
README.md,CLAUDE.md,*.md— project overviewpackage.json/pyproject.toml/Cargo.toml— stack + depsdocker-compose.yml— services architecture.env.example— config shape
3. Map Directory Structure
find . -type f -not -path './.git/*' -not -path './node_modules/*' -not -path './.tmp/*' | head -200
Identify layers: frontend, backend, API, DB, auth, infra, tests.
4. Trace Key Flows
For each major module, trace:
- Entry point — where does it start?
- Data flow — input → processing → output
- Dependencies — what does it import/call?
- Config — env vars, constants, feature flags
5. Write .tmp/llm*.md Docs
Create .tmp/ if not exists. examples: (just possible, not must)
| File | Content | |------|---------| | llm.arch.md | Overall architecture, tech stack, directory map | | llm.arch.auth.md | Auth flow, session handling, permissions | | llm.arch.db.md | DB schema, ORM, migrations, key queries | | llm.arch.api.md | API routes, request/response shapes, middleware | | llm.frontend.md | UI structure, components, state management | | llm.backend.md | Server logic, services, business rules | | llm.infra.md | Deploy, CI/CD, Docker, env config | | llm.gotchas.md | Non-obvious quirks, footguns, tech debt |
Only create files for domains that exist in the project. Skip what's not there.
6. Doc Format
Each llm*.md follows:
# [Domain] — [Project Name]
## Overview
One paragraph: what this layer does and why.
## Key Files
- `path/to/file.ts` — what it does
- `path/to/other.ts` — what it does
## Architecture
How components connect. Use ascii diagram if complex:
A → B → C ↓ D
## Patterns
- Pattern name — brief explanation
- Another pattern — brief explanation
## Gotchas
- Non-obvious thing 1
- Non-obvious thing 2
Rules
- All output goes to
./.tmp/— never/tmp/ - Keep each doc under 100 lines — dense, scannable
- File paths must be current — verify they exist before writing
- No opinions — document what IS, not what should be
- Skip boilerplate/obvious stuff — only document what's non-trivial
- If project is large, prioritize: auth > API > DB > frontend > infra
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: LatticeCast
- Source: LatticeCast/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.