agentleFS
vhmarquezvhmarquez/argo/skills/onboard/SKILL.md

onboard

Skill1 starsChanged 7 months agoMITView on GitHub

Onboard a new developer to a Salesforce project — verify Salesforce CLI version, Dev Hub authentication, project config, and run an end-to-end sanity check (scratch org create → deploy → tests pass). Outputs a checklist with green/red status per item.

165 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test, team-live-ops and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • CoralGameSkill

    project-stage-detect

    Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.

    Also in 15 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 11 projects that use this

  • +5 more from lilangMax
  • +2 more from CoralGame

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 153 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a scratch org: /argo:scratch-org create scratch-onboard --days 1 --no-seed

    line 74
  2. Very specific:

    Run lint: invoke ${LINT_CMD} from package.json

    line 76
  3. Very specific:

    Run unit tests: invoke ${TEST_CMD}

    line 77
  4. Very specific:

    Run Apex coverage on a small class: /argo:test-coverage <class> --target-org scratch-onboard

    line 78
  5. Very specific:

    Don't skip on warnings: If docs/project-context.md has _TODO_ markers, that's a real onboarding gap.

    line 150
  6. Distinctive:

    Clean up after yourself: Always destroy the scratch org created during smoke, even on partial failure

    line 152

“Common” is measured: kept by at least 6 in 10 of the 153 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are walking a new developer through the prerequisites and a smoke test for this Salesforce project. The skill verifies their machine is set up correctly and that they can complete the basic dev loop end-to-end.

Read Project Config First

source "${CLAUDE_PLUGIN_ROOT}/hooks/lib/config.sh"
DEV_HUB="$(sf_config_get '.platform.devHubAlias // \"DevHub\"' "$ENV")"
API_VERSION="$(sf_config_get '.platform.apiVersion' "$ENV")"
LINT_CMD="$(sf_config_get '.quality.lintCommand' "$ENV")"
TEST_CMD="$(sf_config_get '.quality.unitTestCommand' "$ENV")"

Input

$ARGUMENTS:

  • (empty) — full onboard check (verify + smoke)
  • verify — checks only, no scratch org / deploy
  • smoke — assumes verify passed; runs the smoke flow only
  • --ci — JSON output, exit 1 if any check fails

Steps

1. Tool versions

ToolRequiredCheck
sf (Salesforce CLI)latestsf --version
nodeLTS (20+)node --version
npmbundled with nodenpm --version
git2.30+git --version
jqany 1.6+jq --version
java11+ (only if PMD-based skills will be used)java -version 2>&1
bash4+ (Git Bash on Windows)bash --version

For each, capture installed version and pass/fail.

2. Salesforce auth

# Dev Hub
sf_cli_alias_exists "$DEV_HUB" && echo "dev-hub: ✅" || echo "dev-hub: ❌ (run: sf org login web --alias $DEV_HUB --set-default-dev-hub)"
# Default target org
DEFAULT_ORG="$(sf_config_get '.platform.defaultTargetOrg' "$ENV")"
sf_cli_alias_exists "$DEFAULT_ORG" && echo "default-org: ✅" || echo "default-org: ❌ (run: sf org login web --alias $DEFAULT_ORG)"

3. Project state

CheckHow
.claude/sf-project.json exists[[ -f .claude/sf-project.json ]]
Standards docs in place (docs/apex-standards.md etc.)check the configured paths
Patterns docs in placecheck paths.patternsSalesforceDoc, paths.patternsProjectDoc
docs/project-context.md has been filled in (no remaining _TODO_ markers)! grep -q "_TODO_" docs/project-context.md
package.json has lint and test:unit scriptscheck package.json

4. Repo state

CheckHow
Working tree cleangit diff --quiet && git diff --cached --quiet
Has at least one commit on a feature branchgit log -1 --pretty=format:%H
Remote configuredgit remote get-url origin (warning if missing)

5. Smoke flow (only in smoke or default mode)

Walk the user through:

  1. Create a scratch org: /argo:scratch-org create scratch-onboard --days 1 --no-seed
  2. Deploy is automatic (the scratch-org skill pushes source)
  3. Run lint: invoke ${LINT_CMD} from package.json
  4. Run unit tests: invoke ${TEST_CMD}
  5. Run Apex coverage on a small class: /argo:test-coverage <class> --target-org scratch-onboard
  6. Destroy the scratch org: /argo:scratch-org destroy scratch-onboard

For each step, report timing and pass/fail.

Output

Default Markdown:

# Onboard: <project.name>

User: <git config user.email>
Run at: 2026-04-28T15:45:00Z

## Tools
- sf:    2.45.6      ✅
- node:  v20.11.1    ✅
- npm:   10.2.4      ✅
- git:   2.44.0      ✅
- jq:    1.7.1       ✅
- java:  17.0.10     ✅
- bash:  5.2.21      ✅

## Auth
- Dev Hub (DevHub):           ✅
- Default org (DevSandbox):   ✅

## Project state
- .claude/sf-project.json:                  ✅
- docs/apex-standards.md:                   ✅
- docs/lwc-standards.md:                    ✅
- docs/quality-checklist.md:                ✅
- docs/patterns/salesforce-patterns.md:     ✅
- docs/patterns/project-patterns.md:        ✅
- docs/project-context.md filled in:        ⚠️  (still has 3 `_TODO_` markers)
- package.json scripts (lint + test:unit):  ✅

## Repo state
- Working tree clean:    ✅
- Has commits:           ✅
- Remote configured:     ✅ (origin: github.com/...)

## Smoke flow
- Scratch org create:    ✅ (8.2s)
- Source push:           ✅ (54.1s, 137 components)
- Lint:                  ✅ (1.3s)
- Unit tests (Jest):     ✅ (12 tests, 0 failures, 4.7s)
- Apex coverage on Order:    ✅ (94.7%, target 85%)
- Scratch org destroy:   ✅ (1.1s)

## Result
**Ready to develop.** ✅

## Recommended next reads
- README.md (project overview)
- docs/project-context.md (object model + glossary)
- docs/patterns/project-patterns.md (project-specific patterns)
- The pattern docs SF-1..SF-20 in docs/patterns/salesforce-patterns.md

## Suggested next command
`@architect: design a small change` — to see the full architect → dev → qa flow in action.

CI mode: emit JSON object with { tools: {...}, auth: {...}, project: {...}, repo: {...}, smoke: {...}, ok: bool }. Exit 1 if any item failed.

6. Exit codes

  • 0 — all checks passed
  • 1 — any check failed (in --ci)
  • 2 — invocation error

Rules

  • Don't skip on warnings. If docs/project-context.md has _TODO_ markers, that's a real onboarding gap; flag as warning
  • Don't run smoke if verify fails. Bail out cleanly with a summary
  • Clean up after yourself. Always destroy the scratch org created during smoke, even on partial failure
  • Honor --days 1 for the smoke scratch — short-lived; don't hold a slot longer than needed
  • Don't commit anything. This skill is read-only against the repo

Consumers

  • New developer joining the project
  • CI bootstrap step (verify-only mode) confirming the runner has prerequisites
  • Periodic check — /argo:onboard verify --ci in a weekly job to detect drift

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.