Agent skill

Verification

by forcedotcom in forcedotcom/salesforcedx-vscode

Verification steps for code changes. An agent skill from forcedotcom/salesforcedx-vscode.

BSD-3-ClauseAuto-check passedTesting & QA

Install Verification

skills CLI
$ npx skills add forcedotcom/salesforcedx-vscode --skill verification -a claude-code

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

GitHub CLI
$ gh skill install forcedotcom/salesforcedx-vscode verification --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/forcedotcom/salesforcedx-vscode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/verification .claude/skills/verification && 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
verification
GitHub stars
1k
Token cost
~458 tokens
SKILL.md length
168 words
Files
3 (incl. references)
Skills in repo
37
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Verification steps for code changes. An agent skill from forcedotcom/salesforcedx-vscode.

  • Works in 3 steps: Dupes — npm run check:dupes, check… → GitHub Actions (only if changing… → Playwright (only if working in these…
  • Testing & QA work in your project
  • SKILL.md covers Rules, Plans and References
  • Calls npm

What it does

Verification is an agent skill from forcedotcom/salesforcedx-vscode. Verification steps for code changes. Use after ANY code change to ensure quality, or when creating plans because those should include verification steps.

Its SKILL.md is about 460 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/compile.md` and `references/unit-tests.md`).

It sits in Testing & QA. It works with Visual Studio Code, GitHub Actions, npm and Playwright. The repository describes itself as: Salesforce Extensions for VS Code. The licence is BSD-3-Clause.

When your agent uses it

  • Testing & QA work in your project

Example prompts

  • “/verification”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Dupes — npm run check:dupes, check jscpd-report for flagged changes
  2. GitHub Actions (only if changing .github/workflows/*.{yml,yaml} or .github/actions/*/action.{yml,yaml}) — npm run check:actions
  3. Playwright (only if working in these packages: salesforcedx-vscode-core, salesforcedx-vscode-org, salesforcedx-vscode-services…

What it can do on your machine

Read from SKILL.md and the folder at commit f7bb6fe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    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.

Context cost

Verification loads about 458 tokens when it runs, and up to ~926 if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 168 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~458
With references · SKILL.md plus every file in references/, read only if the agent opens them
~926

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 forcedotcom/salesforcedx-vscode at commit f7bb6fe, republished under its BSD-3-Clause licence (© forcedotcom). 168 words, ~458 tokens.

Download SKILL.mdSave it as .claude/skills/verification/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
verification
description
Verification steps for code changes. Use after ANY code change to ensure quality, or when creating plans because those should include verification steps.
review
never

Verification

The stop hook runs compile, lint, effect LS, test, vscode:bundle, and knip automatically when the agent stops — no need to run these manually.

Run this only if the stop hook doesn't catch it:

  1. Dupes — npm run check:dupes, check jscpd-report for flagged changes

  2. GitHub Actions (only if changing .github/workflows/*.{yml,yaml} or .github/actions/*/action.{yml,yaml}) — npm run check:actions

  3. Playwright (only if working in these packages: salesforcedx-vscode-core, salesforcedx-vscode-org, salesforcedx-vscode-services, salesforcedx-vscode-org-browser, salesforcedx-vscode-metadata, salesforcedx-vscode-apex-testing, salesforcedx-vscode-apex-log, playwright-vscode-ext)

    • Run from root: npm run test:web -w <package-name> -- --retries 0 / npm run test:desktop -w <package-name> -- --retries 0

Rules

  • Don't change /src AND /test together (except imports/renames)
  • All commands run from repo root; use -w for single package, never cd into a package
  • Don't call a failure "pre-existing" without verifying on a prior commit

Plans

Include verification steps after the "actual" todos. Follow this checklist.

References

  • references/unit-tests.md — unit tests
  • references/compile.md — compile; TS4023 / TS1261 skills
  • @.claude/skills/ts4023-effect-errors/ — TS4023
  • @.claude/skills/ts1261-filename-casing/ — TS1261
  • @.claude/skills/playwright-e2e/ — Playwright E2E
  • effect-advocate subagent — invoke after Effect-related changes to flag missed Effect idioms (schemas, Option, retry/timeout/cache, services reuse).

© forcedotcom, BSD-3-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .claude/skills/verification of forcedotcom/salesforcedx-vscode.

  • SKILL.md
  • references/compile.md
  • references/unit-tests.md

Open the folder on GitHubat commit f7bb6fe

Compare with similar skills

Verification 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.

Verification compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verification this skillforcedotcom/salesforcedx-vscode1k—~458Automated safety check: PassBSD-3-Clause
Blockless Extension E2EFreakStudioCN/mpy-hardware-extension118—~1.2kAutomated safety check: NotesCustom licence
Actions CI Tuningmizchi/skills356—~2.6kAutomated safety check: PassNone
Publish ExtensionFreakStudioCN/mpy-hardware-extension118—~1.3kAutomated safety check: PassCustom licence
Publish ExtensionFreakStudioCN/mpy-hardware-extension118—~1.5kAutomated safety check: PassCustom licence
Debug Playwright Prowquay/quay2.8k—~2.2kAutomated safety check: PassApache-2.0

Similar skills

  • Blockless Extension E2E

    FreakStudioCN/mpy-hardware-extension

    Run and debug the Blockless VS Code extension release gate: CI-equivalent API and extension tests, V0 protocol smoke, live DeepSeek full-stack e2e, VSIX packaging, local reinstall, direct…

    118 GitHub stars~1.2k tokensUpdated 9 days ago
    Testing & QAAuto-check: notes
  • Actions CI Tuning

    mizchi/skills

    A skill your agent uses when auditing or improving GitHub Actions workflows for a project.

    356 GitHub stars~2.6k tokensUpdated 5 days ago
    Testing & QAAuto-check passed
  • Publish Extension

    FreakStudioCN/mpy-hardware-extension

    发布 Blockless VS Code 扩展到 Visual Studio Marketplace(含发布前测试)/ ship the Blockless extension to the VS Code Marketplace.

    118 GitHub stars~1.3k tokensUpdated 9 days ago
    DevOps & CloudAuto-check passed
  • Publish Extension

    FreakStudioCN/mpy-hardware-extension

    发布 Blockless VS Code 扩展的预检 + MS Marketplace 那一半 / preflight and the MS Marketplace half of shipping the Blockless extension.

    118 GitHub stars~1.5k tokensUpdated 9 days ago
    DevOps & CloudAuto-check passed
  • Deep-dive diagnosis of a Playwright test failure already isolated to one Quay Prow/OpenShift CI run: downloads its GCS artifacts (results.json, JUnit, build/pod logs, Jaeger traces), classifies real…

    2.8k GitHub stars~2.2k tokensUpdated today
    Testing & QAAuto-check passed
  • Converts RStudio Python Selenium electron tests into TypeScript Playwright tests, checking each against a live RStudio before counting it as migrated.

    5.1k GitHub stars~3.6k tokensUpdated today
    Testing & QAAuto-check passed

More from forcedotcom/salesforcedx-vscode

All 37 skills in this repo
  • Command UI

    forcedotcom/salesforcedx-vscode

    Command palette, CodeLens, context menus, package.nls titles, and NotificationModeService.

    1k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Services Extension Consumption

    forcedotcom/salesforcedx-vscode

    Consume the salesforcedx-vscode-services extension API. An agent skill from forcedotcom/salesforcedx-vscode.

    1k GitHub stars~5k tokensUpdated today
    Auto-check passed
  • Changelog

    forcedotcom/salesforcedx-vscode

    Polish the automated CHANGELOG on develop before the next stable build.

    1k GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Core Extension API

    forcedotcom/salesforcedx-vscode

    Public API exported by salesforcedx-vscode-core activate(). An agent skill from forcedotcom/salesforcedx-vscode.

    1k GitHub stars~842 tokensUpdated today
    Auto-check passed
  • Drivable Vscode

    forcedotcom/salesforcedx-vscode

    Operate a real VS Code instance through drivable-vscode. An agent skill from forcedotcom/salesforcedx-vscode.

    1k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Effect Best Practices

    forcedotcom/salesforcedx-vscode

    Enforces Effect-TS patterns for services, errors, layers, atoms, and Effect.pipe composition.

    1k GitHub stars~6.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Verification

What does Verification do?

Verification steps for code changes. An agent skill from forcedotcom/salesforcedx-vscode. Verification is an agent skill from forcedotcom/salesforcedx-vscode. Verification steps for code changes.

When should I use Verification?

Verification fits situations like: testing & QA work in your project.

How do I install Verification in Claude Code?

Run `npx skills add forcedotcom/salesforcedx-vscode --skill verification -a claude-code`. Or copy the skill folder (.claude/skills/verification in forcedotcom/salesforcedx-vscode) into .claude/skills/verification in your project. Claude Code loads it when a task matches its description.

How do I install Verification in Codex?

Run `npx skills add forcedotcom/salesforcedx-vscode --skill verification -a codex`. Or copy the skill folder (.claude/skills/verification in forcedotcom/salesforcedx-vscode) into .agents/skills/verification in your project. Codex loads it when a task matches its description.

Can I use Verification 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 forcedotcom/salesforcedx-vscode --skill verification -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verification, .gemini/skills/verification, .github/skills/verification and .opencode/skills/verification in your project.

What does Verification need to run?

Going by SKILL.md and its folder, Verification needs the command-line tools its instructions call (npm).

Does Verification access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Verification 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 Verification use?

Verification is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verification use?

About 458 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 468 tokens, read only when the agent opens those files.

What are the alternatives to Verification?

Skills that share tags, products or a category with Verification: Blockless Extension E2E (FreakStudioCN/mpy-hardware-extension, 118 stars), Actions CI Tuning (mizchi/skills, 356 stars), Publish Extension (FreakStudioCN/mpy-hardware-extension, 118 stars) and Publish Extension (FreakStudioCN/mpy-hardware-extension, 118 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verification?

forcedotcom (a GitHub organization) maintains it in forcedotcom/salesforcedx-vscode, which has 1,035 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 7, 2026.

Source: forcedotcom/salesforcedx-vscode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.