onboarding-codebase
Use when working in a repository for the first time, or in an unfamiliar area of a large repo — before making any edit, especially when the task "should be…
Skill by Roflochinsky
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/roflochinsky-onboarding-codebase
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/onboarding-codebase
What's inside
- Skill name
onboarding-codebase- Description
- Use when working in a repository for the first time, or in an unfamiliar area of a large repo — before making any edit, especially when the task "should be quick".
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Onboarding to a Codebase ## Overview The classic first-session failure: a locally-plausible edit that violates conventions you never surveyed — logic in the wrong layer, a hand-rolled duplicate of an existing utility, a pattern the repo deliberately avoids. Ten minutes of recon before the first edit is what separates "quick" from "quick and silently wrong". ## Recon before the first edit (~10 minutes, read-only) 1. **Orientation**: README, CLAUDE.md/AGENTS.md (if present — follow them and skip what they already answer), top-level layout, build files (Makefile/package.json/go.mod...) for the real commands: build, test, lint, run. 2. **The task's neighborhood**: find the code nearest to what you're asked to build (`grep` for the domain words). Read one complete example of the pattern you're about to imitate — a full handler/component/module, not a snippet. Note: layering (who calls whom), error handling style, test style and location. 3. **The data**: if the task touches data, read the actual schema/models — not the user's description of them. Nullable fields, join tables, and naming surprises live here; this is where "the data's all there" turns out to mean a three-way join. 4. **Baseline**: run the test suite once BEFORE changing anything. A pre-existing red suite discovered after your edits becomes your fault. ## While working - **Imitate, don't innovate**: copy the repo's existing pattern even where you'd personally do it differently. An existing similar feature (an export button, a list endpoint) is your template — extend the pattern, don't invent a parallel one. - **State assumptions in one message** when recon surfaced design decisions the user didn't specify (NULL handling, aggregation level, naming). Proceed unless contradicted — don't stall, don't guess silently. - **No new dependencies or abstractions** in your first sessions in a repo unless the task demands it. ## Close the loop If the repo had no CLAUDE.md: offer to record what you learned (run commands, layering, conventions, footguns) as one — the `init` skill or a short hand-written file. Your recon is exactly the onboarding the next agent will otherwise redo from scratch. If CLAUDE.md existed but was wrong/stale, report the mismatch (codifying-learnings). ## Red flags | Thought | Reality | |---|---| | "Should be quick, I'll just add the endpoint" | Quick tasks hide schema wrinkles. Recon catches them in minutes; production catches them in weeks. | | "I'll figure out conventions as I go" | "As you go" = after the reviewer rejects the diff. | | "This repo surely has no helper for X" | Grep first. Duplicating an existing utility is the #1 onboarding diff smell. | | "Tests are probably green on main" | Run them. Baselines are free; blame-untangling isn't. |
From Roflochinsky/workshopskills, MIT.
More from Roflochinsky/workshopskills
- 0.474score
classifying-tasks
Roflochinsky
Use when receiving any new work request, before writing code or choosing an approach — especially multi-item requests, vague one-liners, "quick" asks, or work…
SkillCFreshness: CClaude Code +9 - 0.474score
decomposing-to-issues
Roflochinsky
Use when breaking a spec or plan into tracker issues for execution — especially when different agents or sessions will pick the pieces up independently.
SkillCFreshness: CClaude Code +9 - 0.474score
delivering-heavy-features
Roflochinsky
Use when a task is classified heavy — a new feature with its own business logic, work spanning several layers with a new or changed contract, or anything…
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
Roflochinsky
Use before running heavy composite workflows (delivering-heavy-features etc.), when a required skill or tool is missing, when setting up a new machine or…
SkillCFreshness: CClaude Code +9 - 0.474score
fixing-incidents
Roflochinsky
Use when production is down or degraded, users are reporting errors, or the user demands an urgent fix ("prod is down", "fix it now", "clients are calling") —…
SkillCFreshness: CClaude Code +9 - 0.474score
getting-second-opinion
Roflochinsky
Use when about to approve, merge, or sign off on non-trivial work you authored yourself — especially when feeling confident, when the user says "I trust your…
SkillCFreshness: CClaude Code +9 - 0.474score
upgrading-dependencies
Roflochinsky
Use when asked to update, upgrade, or bump dependencies, fix dependency vulnerabilities, or when CI flags outdated/vulnerable packages — before running any…
SkillCFreshness: CClaude Code +9 - 0.474score
codifying-learnings
Roflochinsky
Use when the user corrects you, repeats an instruction they gave before, or you notice you've made the same mistake or received the same feedback more than…
SkillCFreshness: CClaude Code +9 - 0.474score
shipping-a-release
Roflochinsky
Use when implementation is complete and the user explicitly asks to wrap up, ship, release, merge, or publish the work.
SkillCFreshness: CClaude Code +9 - 0.471score
runtime-sql-review
Roflochinsky
Mandatory write→review loop for runtime-/live-only fixes the test suite cannot catch — raw SQL via SQLAlchemy text() / asyncpg, migrations, queries, any…
SkillCFreshness: CClaude Code +9 - 0.471score
heavy-task-pipeline
Roflochinsky
Use for Tier 2 / heavy Workwatch tasks — a new dashboard section with its own business logic, anything spanning API + DB migrations + UI, or any ADR-gate…
SkillCFreshness: CClaude Code +9 - 0.445score
grill-me
Roflochinsky
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 16, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Roflochinsky/workshopskills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Roflochinsky
- 0.474score
classifying-tasks
Roflochinsky
Use when receiving any new work request, before writing code or choosing an approach — especially multi-item requests, vague one-liners, "quick" asks, or work…
SkillCFreshness: CClaude Code +9 - 0.474score
decomposing-to-issues
Roflochinsky
Use when breaking a spec or plan into tracker issues for execution — especially when different agents or sessions will pick the pieces up independently.
SkillCFreshness: CClaude Code +9 - 0.474score
delivering-heavy-features
Roflochinsky
Use when a task is classified heavy — a new feature with its own business logic, work spanning several layers with a new or changed contract, or anything…
SkillCFreshness: CClaude Code +9 - 0.474score
doctor
Roflochinsky
Use before running heavy composite workflows (delivering-heavy-features etc.), when a required skill or tool is missing, when setting up a new machine or…
SkillCFreshness: CClaude Code +9 - 0.474score
fixing-incidents
Roflochinsky
Use when production is down or degraded, users are reporting errors, or the user demands an urgent fix ("prod is down", "fix it now", "clients are calling") —…
SkillCFreshness: CClaude Code +9 - 0.474score
getting-second-opinion
Roflochinsky
Use when about to approve, merge, or sign off on non-trivial work you authored yourself — especially when feeling confident, when the user says "I trust your…
SkillCFreshness: CClaude Code +9
Cite this page
onboarding-codebase skill. Agent Mart. https://agentmart.dev/skills/roflochinsky-onboarding-codebase (last updated 2026-10-24)