First-session project onboarding. An agent skill from blackwell-systems/agent-lsp.

MITAuto-check passedDevelopment

Install Lsp Onboard

skills CLI
$ npx skills add blackwell-systems/agent-lsp --skill lsp-onboard -a claude-code

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

GitHub CLI
$ gh skill install blackwell-systems/agent-lsp lsp-onboard --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/blackwell-systems/agent-lsp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lsp-onboard .claude/skills/lsp-onboard && 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
lsp-onboard
GitHub stars
160
Token cost
~1.2k tokens
SKILL.md length
391 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

First-session project onboarding. An agent skill from blackwell-systems/agent-lsp.

  • Works in 8 steps: Detect languages and servers → Initialize and verify → Identify entry points → …
  • Tasks that involve Software architecture
  • SKILL.md covers When to Use, Step 1: Detect languages and…, Step 2: Initialize and verify and Step 3: Identify entry points, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Lsp Onboard is an agent skill from blackwell-systems/agent-lsp. First-session project onboarding. Explores the project structure, detects build system, test runner, entry points, and key architecture patterns. Produces a structured project profile the agent can reference throughout the session.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires the agent-lsp MCP server (github.com/blackwell-systems/agent-lsp)

It sits in Development, covering Software architecture. The repository describes itself as: MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages. The licence is MIT.

When your agent uses it

  • Tasks that involve Software architecture

Example prompts

  • “/lsp-onboard”

Requirements

  • Compatibility (from SKILL.md): Requires the agent-lsp MCP server (github.com/blackwell-systems/agent-lsp)
  • Pre-approved tools (allowed-tools): mcp__lsp__start_lsp, mcp__lsp__detect_lsp_servers, mcp__lsp__list_symbols, mcp__lsp__find_symbol, mcp__lsp__blast_radius, mcp__lsp__run_build, mcp__lsp__run_tests, mcp__lsp__get_diagnostics, mcp__lsp__get_editing_context

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Detect languages and servers
  2. Initialize and verify
  3. Identify entry points
  4. Map the package structure
  5. Detect build and test commands
  6. Identify hotspots
  7. Check for diagnostics
  8. Produce the project profile

What it can do on your machine

Read from SKILL.md and the folder at commit 38ca488. 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:

    • mcp__lsp__start_lsp
    • mcp__lsp__detect_lsp_servers
    • mcp__lsp__list_symbols
    • mcp__lsp__find_symbol
    • mcp__lsp__blast_radius
    • mcp__lsp__run_build
    • mcp__lsp__run_tests
    • mcp__lsp__get_diagnostics
    • mcp__lsp__get_editing_context

    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.

  • Compatibility

    Requires the agent-lsp MCP server (github.com/blackwell-systems/agent-lsp)

    From compatibility in the SKILL.md frontmatter.

Context cost

Lsp Onboard loads about 1.2k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 391 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 blackwell-systems/agent-lsp at commit 38ca488, republished under its MIT licence (© blackwell-systems). 391 words, ~1,206 tokens.

Download SKILL.mdSave it as .claude/skills/lsp-onboard/SKILL.md (or your agent's skills folder).
name
lsp-onboard
description
First-session project onboarding. Explores the project structure, detects build system, test runner, entry points, and key architecture patterns. Produces a structured project profile the agent can reference throughout the session.
allowed-tools
mcp__lsp__start_lsp, mcp__lsp__detect_lsp_servers, mcp__lsp__list_symbols, mcp__lsp__find_symbol, mcp__lsp__blast_radius, mcp__lsp__run_build, mcp__lsp__run_tests, mcp__lsp__get_diagnostics, mcp__lsp__get_editing_context
compatibility
Requires the agent-lsp MCP server (github.com/blackwell-systems/agent-lsp)
argument-hint
[workspace-root-path]
user-invocable
true
license
MIT
metadata.required-capabilities
documentSymbolProvider
metadata.optional-capabilities
referencesProvider callHierarchyProvider

lsp-onboard

First-session project onboarding. Run this when connecting to a new project for the first time. Explores the codebase via LSP tools and produces a structured project profile: languages, build system, test runner, entry points, key types, and architecture patterns.

The profile helps the agent make better decisions throughout the session without re-exploring the same ground. Run once per project; skip on subsequent sessions unless the project structure has changed significantly.

When to Use

  • First time working in a new codebase
  • After major structural changes (new packages, build system migration)
  • When the agent seems confused about project conventions

Do NOT run this on every session. It's a one-time exploration.


Step 1: Detect languages and servers

mcp__lsp__detect_lsp_servers({ "workspace_dir": "<root>" })

Record which languages are present and which servers are available. This tells you what the project is built with.

Step 2: Initialize and verify

mcp__lsp__start_lsp({ "root_dir": "<root>" })

Wait for initialization. Call list_symbols on one key file to verify the workspace is indexed.

Step 3: Identify entry points

Search for common entry point patterns:

mcp__lsp__find_symbol({ "query": "main" })
mcp__lsp__find_symbol({ "query": "Run" })
mcp__lsp__find_symbol({ "query": "Handler" })

Record entry points with their file paths. These are where execution starts.

Step 4: Map the package structure

For each top-level directory that contains source files, call list_symbols on one representative file:

mcp__lsp__list_symbols({ "file_path": "<dir>/main.go", "format": "outline" })

Build a mental map: which packages exist, what they export, how they relate. Cap at 10 packages to avoid spending too long.

Step 5: Detect build and test commands

mcp__lsp__run_build({ "workspace_dir": "<root>" })
mcp__lsp__run_tests({ "workspace_dir": "<root>" })

Record whether build and tests pass, and what language/toolchain was detected. Note the test count and any failures.

Show full SKILL.md (147 more words)Show less

Step 6: Identify hotspots

Pick the 3-5 files that appear most central (entry points, shared types, core logic). For each:

mcp__lsp__blast_radius({ "changed_files": ["<file>"] })

Files with the most non-test callers are the architectural hotspots. Changes to these files have the widest blast radius.

Step 7: Check for diagnostics

mcp__lsp__get_diagnostics({ "file_path": "<entry-point>" })

Note any pre-existing errors or warnings. This sets the baseline so the agent knows what was broken before it started.

Step 8: Produce the project profile

Write a structured summary:

## Project Profile: <name>

### Languages
- Go (primary), TypeScript (frontend)

### Build & Test
- Build: `go build ./...` (passes)
- Test: `go test ./...` (142 tests, 0 failures)

### Entry Points
- cmd/server/main.go:15 (main)
- cmd/worker/main.go:22 (main)

### Package Map
- cmd/server/     (HTTP server, routing)
- cmd/worker/     (background job processor)
- internal/api/   (handler layer)
- internal/store/ (database access)
- internal/types/ (shared type definitions)

### Hotspots (most referenced)
1. internal/types/models.go: 85 callers across 12 files
2. internal/store/queries.go: 42 callers across 8 files
3. internal/api/handlers.go: 31 callers across 6 files

### Pre-existing Issues
- 0 errors, 2 warnings (unused imports in test files)

### Conventions Observed
- Error wrapping with fmt.Errorf
- Table-driven tests
- Handler functions return (result, error)

This profile is for the agent's reference during the session. It does not need to be saved to disk; it lives in the conversation context.


Notes

  • Cap exploration at 10 packages and 5 hotspot files to keep the onboarding under 2 minutes
  • If blast_radius is slow (large files), skip the hotspot step and note "hotspot analysis skipped (large codebase)"
  • The profile is advisory; update it mentally as you learn more during the session

© blackwell-systems, 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 skills/lsp-onboard of blackwell-systems/agent-lsp.

Open the folder on GitHubat commit 38ca488

Compare with similar skills

Lsp Onboard 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.

Lsp Onboard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lsp Onboard this skillblackwell-systems/agent-lsp160—~1.2kAutomated safety check: PassMIT
Archify Diagramstt-a1i/archify82k—~2.9kAutomated safety check: PassMIT
Electron Multi-Process ArchitectureiOfficeAI/AionUi33k1 repos~1.8kAutomated safety check: PassApache-2.0
Backend Code Reviewlanggenius/dify158k—~676Automated safety check: PassCustom licence
Dark Architecture Diagram BuilderCocoon-AI/architecture-diagram-generator7.4k1 repos~2.1kAutomated safety check: PassMIT
SVG Diagram GeneratorJimLiu/baoyu-skills27k1 repos~3.1kAutomated safety check: PassMIT

Similar skills

  • Archify Diagrams

    tt-a1i/archify

    Creates interactive architecture, workflow, sequence, data-flow and lifecycle diagrams as standalone HTML with inline SVG, themes and image or video export.

    82k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Tells the agent where new code belongs in an Electron multi-process project and which APIs each process may use, with rules for new bridges, services, agents and workers.

    33k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed
  • Dark Architecture Diagram Builder

    Cocoon-AI/architecture-diagram-generator

    Creates dark-themed system, cloud, security and network architecture diagrams as self-contained HTML files with inline SVG and CSS.

    7.4k GitHub starsUsed in 1 repo~2.1k tokens
    DevelopmentAuto-check passed
  • SVG Diagram Generator

    JimLiu/baoyu-skills

    Creates standalone dark-themed SVG diagrams, including architecture, flowchart, sequence, structural, mind map, timeline and state machine types.

    27k GitHub starsUsed in 1 repo~3.1k tokens
    DevelopmentAuto-check passed
  • Senior Architect Toolkit

    maslennikov-ig/claude-code-orchestrator-kit

    Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin…

    260 GitHub starsUsed in 8 repos~1.2k tokens
    DevelopmentAuto-check: notes

More from blackwell-systems/agent-lsp

All 24 skills in this repo
  • Lsp Dead Code

    blackwell-systems/agent-lsp

    Enumerate exported symbols in a file and surface those with zero references across the workspace.

    160 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Lsp Edit Export

    blackwell-systems/agent-lsp

    Safe workflow for editing exported symbols or public APIs. An agent skill from blackwell-systems/agent-lsp.

    160 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Lsp Fix All

    blackwell-systems/agent-lsp

    Apply available quick-fix code actions for all current diagnostics in a file, one at a time with re-collection between each fix.

    160 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Lsp Generate

    blackwell-systems/agent-lsp

    Trigger language server code generation — implement interface stubs, generate test skeletons, add missing methods, generate mock types.

    160 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Lsp Impact

    blackwell-systems/agent-lsp

    Blast-radius analysis for a symbol or file — shows all callers, type supertypes/subtypes, and reference count before you change it.

    160 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Lsp Rename

    blackwell-systems/agent-lsp

    Two-phase safe rename across the entire workspace. An agent skill from blackwell-systems/agent-lsp.

    160 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Lsp Onboard

What does Lsp Onboard do?

First-session project onboarding. An agent skill from blackwell-systems/agent-lsp. Lsp Onboard is an agent skill from blackwell-systems/agent-lsp. First-session project onboarding.

When should I use Lsp Onboard?

Lsp Onboard fits situations like: tasks that involve Software architecture.

How do I install Lsp Onboard in Claude Code?

Run `npx skills add blackwell-systems/agent-lsp --skill lsp-onboard -a claude-code`. Or copy the skill folder (skills/lsp-onboard in blackwell-systems/agent-lsp) into .claude/skills/lsp-onboard in your project. Claude Code loads it when a task matches its description.

How do I install Lsp Onboard in Codex?

Run `npx skills add blackwell-systems/agent-lsp --skill lsp-onboard -a codex`. Or copy the skill folder (skills/lsp-onboard in blackwell-systems/agent-lsp) into .agents/skills/lsp-onboard in your project. Codex loads it when a task matches its description.

Can I use Lsp Onboard 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 blackwell-systems/agent-lsp --skill lsp-onboard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lsp-onboard, .gemini/skills/lsp-onboard, .github/skills/lsp-onboard and .opencode/skills/lsp-onboard in your project.

What does Lsp Onboard need to run?

SKILL.md names no scripts, command-line tools or credentials: Lsp Onboard is instructions for the agent only. Its frontmatter pre-approves these tools: mcp__lsp__start_lsp, mcp__lsp__detect_lsp_servers, mcp__lsp__list_symbols, mcp__lsp__find_symbol, mcp__lsp__blast_radius, mcp__lsp__run_build, mcp__lsp__run_tests, mcp__lsp__get_diagnostics, mcp__lsp__get_editing_context. Compatibility (from SKILL.md): Requires the agent-lsp MCP server (github.com/blackwell-systems/agent-lsp).

Does Lsp Onboard 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 Lsp Onboard 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 Lsp Onboard use?

Lsp Onboard is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lsp Onboard use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Lsp Onboard?

Skills that share tags, products or a category with Lsp Onboard: Archify Diagrams (tt-a1i/archify, 82k stars), Electron Multi-Process Architecture (iOfficeAI/AionUi, 33k stars), Backend Code Review (langgenius/dify, 158k stars) and Dark Architecture Diagram Builder (Cocoon-AI/architecture-diagram-generator, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lsp Onboard?

blackwell-systems (a GitHub user) maintains it in blackwell-systems/agent-lsp, which has 160 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 10, 2026.

Source: blackwell-systems/agent-lsp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.