New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Verify

by openathleteorg in openathleteorg/openathlete

Run the right OpenAthlete checks before committing or pushing a change (lint, types, unit, integration, AI agent and end-to-end tests).

AGPL-3.0Auto-check passedTesting & QA

Install Verify

skills CLI
$ npx skills add openathleteorg/openathlete --skill verify -a claude-code

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

GitHub CLI
$ gh skill install openathleteorg/openathlete verify --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/openathleteorg/openathlete.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/verify .claude/skills/verify && 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
verify
GitHub stars
101
Token cost
~603 tokens
SKILL.md length
286 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Run the right OpenAthlete checks before committing or pushing a change (lint, types, unit, integration, AI agent and end-to-end tests).

  • Tasks that involve Linting and formatting
  • SKILL.md covers When a step fails and Report
  • Calls pnpm and bundle

What it does

Verify is an agent skill from openathleteorg/openathlete. Run the right OpenAthlete checks before committing or pushing a change (lint, types, unit, integration, AI agent and end-to-end tests). Use after editing code, before a commit, or when asked whether a change is safe.

Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Linting and formatting. It works with Docker and pnpm. The repository describes itself as: The open-source alternative to TrainingPeaks. Self-hostable endurance training platform. Your data stays yours. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Linting and formatting

Example prompts

  • “/verify”

Requirements

  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit a3433f0. 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:

    • pnpm
    • bundle

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, 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

Verify loads about 603 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 286 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~603

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 openathleteorg/openathlete at commit a3433f0, republished under its AGPL-3.0 licence (© openathleteorg). 286 words, ~603 tokens.

Download SKILL.mdSave it as .claude/skills/verify/SKILL.md (or your agent's skills folder).
name
verify
description
Run the right OpenAthlete checks before committing or pushing a change (lint, types, unit, integration, AI agent and end-to-end tests). Use after editing code, before a commit, or when asked whether a change is safe.

Verify a change

Always start with the fast suite, which mirrors the CI static jobs:

bash
scripts/verify.sh

It installs dependencies, generates the Prisma client, builds libs/shared, compiles translations, checks locale parity, then lints, type-checks and runs every unit test (in a non-UTC timezone). It stops at the first failure and prints that step's log.

Then add what the change touches:

ChangedCommandWhy
libs/database schema, SQL, transactions, anything deleting datascripts/verify.sh --integrationRuns *.int-spec.ts on a throwaway PostgreSQL (Docker, port 15436)
apps/api/src/mastra, prompts, structured outputs, AI SDK versionsscripts/verify.sh --buildBuilds everything and runs test:agents against a fake OpenAI API
Dockerfiles, nginx, env vars, auth, routing, a page or user flowscripts/verify.sh --e2eBuilds the production images and runs Playwright (ports 13000 and 18080)
Dependency upgrades, release preparationscripts/verify.sh --allEverything CI runs
apps/docscd apps/docs && pnpm install --frozen-lockfile && pnpm types:check && pnpm buildStandalone project
apps/web/android, apps/web/ios, Capacitor plugins, apps/web/fastlanecd apps/web && bundle exec fastlane android check && bundle exec fastlane ios checkBuilds both native apps unsigned, as the Mobile workflow does (needs Ruby, Java 21 and the Android SDK, Xcode 26+)

When a step fails

  • Read the printed log and fix the cause. Never skip a check or weaken a test to get green.
  • type-check errors in API or web after a libs/shared change: the shared build is stale. verify.sh rebuilds it, so check the shared code itself.
  • unit-tests failing only in TZ=America/New_York: a date is computed in local time. Use the UTC helpers in apps/api/src/modules/core/helpers/training-load.ts.
  • e2e-* failures: follow the e2e skill to read the report and service logs.

Report

State which suites ran and their result. If something could not be run (Docker unavailable, a port in use), say so explicitly rather than implying it passed.

© openathleteorg, AGPL-3.0. 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 .claude/skills/verify of openathleteorg/openathlete.

Open the folder on GitHubat commit a3433f0

Compare with similar skills

Verify 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.

Verify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify this skillopenathleteorg/openathlete101—~603Automated safety check: PassAGPL-3.0
Kouchou AI Developmentdigitaldemocracy2030/kouchou-ai171—~540Automated safety check: NotesAGPL-3.0
Verifygocronx-team/gocron808—~529Automated safety check: PassMIT
Toolchain Commandslatitude-dev/latitude-llm4.7k—~1.4kAutomated safety check: NotesMIT
DeerFlow Smoke Testbytedance/deer-flow84k—~2.5kAutomated safety check: NotesMIT
Babysit PRZenUml/web-sequence150—~871Automated safety check: PassMIT

Similar skills

  • Kouchou AI Development

    digitaldemocracy2030/kouchou-ai

    Local development setup, build and lint commands, environment configuration, and deployment helpers for the kouchou-ai repo.

    171 GitHub stars~540 tokensUpdated today
    DevelopmentAuto-check: notes

  • Verify

    gocronx-team/gocron

    Reproduce the complete gocron CI pipeline locally and report every result.

    808 GitHub stars~529 tokensUpdated 6 days ago
    DevelopmentAuto-check passed

  • Toolchain Commands

    latitude-dev/latitude-llm

    Installing dependencies, running dev/build/test/lint, filtering packages, single-test runs, git hooks, preparing a clone (.env.development / .env.test), or Docker-backed local services and dev…

    4.7k GitHub stars~1.4k tokensUpdated today
    DevOps & CloudAuto-check: notes

  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    84k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes

  • Babysit PR

    ZenUml/web-sequence

    Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate.

    150 GitHub stars~871 tokensUpdated 4 days ago
    Testing & QAAuto-check passed

  • Verdaccio Change Testing Selector

    verdaccio/verdaccio

    Figures out which rebuild and test suites actually cover a change in the verdaccio monorepo, instead of a scoped run that passes untested.

    18k GitHub stars~1.6k tokensUpdated today
    Testing & QAAuto-check: warnings

More from openathleteorg/openathlete

All 8 skills in this repo

  • API Endpoint

    openathleteorg/openathlete

    Add or change an OpenAthlete API endpoint end to end, from the shared Zod schema to the NestJS controller and service, the web API client, the React Query hook and the UI, with tests.

    101 GitHub stars~682 tokensUpdated today
    Auto-check passed

  • E2E

    openathleteorg/openathlete

    Run, debug or extend the OpenAthlete Playwright end-to-end tests, which exercise the production Docker images (API, worker, web, PostgreSQL, Redis) through the API and a real browser on desktop and…

    101 GitHub stars~675 tokensUpdated today
    Auto-check passed

  • I18n

    openathleteorg/openathlete

    Add or change user-facing text in OpenAthlete (web app Paraglide catalogs, API emails and push notifications, website) in every supported language.

    101 GitHub stars~512 tokensUpdated today
    Auto-check passed

  • Prisma Migration

    openathleteorg/openathlete

    Change the OpenAthlete database schema safely with Prisma, covering the migration SQL, production safety, account deletion coverage and tests.

    101 GitHub stars~575 tokensUpdated today
    Auto-check passed

  • Review PR

    openathleteorg/openathlete

    Review an external pull request on openathleteorg/openathlete, test it on top of current main, resolve trivial conflicts, and approve, request changes or merge with a clear, friendly review.

    101 GitHub stars~823 tokensUpdated today
    Auto-check passed

  • Triage Feedback

    openathleteorg/openathlete

    Gather OpenAthlete user feedback from GitHub (issues, PRs, discussions) and the local Discord export, deduplicate it, prioritize it, and draft replies.

    101 GitHub stars~552 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Verify

What does Verify do?

Run the right OpenAthlete checks before committing or pushing a change (lint, types, unit, integration, AI agent and end-to-end tests). Verify is an agent skill from openathleteorg/openathlete. Run the right OpenAthlete checks before committing or pushing a change (lint, types, unit, integration, AI agent and end-to-end tests).

When should I use Verify?

Verify fits situations like: tasks that involve Linting and formatting.

How do I install Verify in Claude Code?

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

How do I install Verify in Codex?

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

Can I use Verify 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 openathleteorg/openathlete --skill verify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify, .gemini/skills/verify, .github/skills/verify and .opencode/skills/verify in your project.

What does Verify need to run?

Going by SKILL.md and its folder, Verify needs the command-line tools its instructions call (pnpm and bundle). Our summary lists: Docker.

Does Verify 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 Verify 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 Verify use?

Verify is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify use?

About 603 tokens (SKILL.md is roughly 2.4k 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 Verify?

Skills that share tags, products or a category with Verify: Kouchou AI Development (digitaldemocracy2030/kouchou-ai, 171 stars), Verify (gocronx-team/gocron, 808 stars), Toolchain Commands (latitude-dev/latitude-llm, 4.7k stars) and DeerFlow Smoke Test (bytedance/deer-flow, 84k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify?

openathleteorg (a GitHub organization) maintains it in openathleteorg/openathlete, which has 101 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 9, 2026.

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