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

Run Checks

by osama-raddad in osama-raddad/FireCrasher

Run the full local build that mirrors CI for FireCrasher — unit tests, Android lint, and the ABI baseline comparison.

Apache-2.0Auto-check passedTesting & QA

Install Run Checks

skills CLI
$ npx skills add osama-raddad/FireCrasher --skill run-checks -a claude-code

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

GitHub CLI
$ gh skill install osama-raddad/FireCrasher run-checks --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/osama-raddad/FireCrasher.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/run-checks .claude/skills/run-checks && 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
run-checks
GitHub stars
147
Token cost
~403 tokens
SKILL.md length
149 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run the full local build that mirrors CI for FireCrasher — unit tests, Android lint, and the ABI baseline comparison.

  • Works in 3 steps: Confirm the toolchain is JDK 21 (java… → Run the full build → For a faster inner loop while iterating,…
  • Tasks that involve Unit testing
  • SKILL.md covers Steps and If it fails
  • Calls java

What it does

Run Checks is an agent skill from osama-raddad/FireCrasher. Run the full local build that mirrors CI for FireCrasher — unit tests, Android lint, and the ABI baseline comparison. Use before pushing or opening a PR, or whenever asked to "run the tests", "check the build", or "verify it compiles".

Its SKILL.md is about 400 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 Unit testing and Linting and formatting. It works with Android and Java. The repository describes itself as: FireCrasher is a Uncaught Exceptions recovery library for android. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Unit testing
  • Tasks that involve Linting and formatting

Example prompts

  • “run the tests”
  • “check the build”
  • “verify it compiles”
  • “/run-checks”

Workflow steps

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

  1. Confirm the toolchain is JDK 21 (java -version). AGP 9.x + the Java 21
  2. Run the full build
  3. For a faster inner loop while iterating, run the pieces directly

What it can do on your machine

Read from SKILL.md and the folder at commit 7a06228. 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:

    • java

    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.

Context cost

Run Checks loads about 403 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 149 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~403

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 osama-raddad/FireCrasher at commit 7a06228, republished under its Apache-2.0 licence (© osama-raddad). 149 words, ~403 tokens.

Download SKILL.mdSave it as .claude/skills/run-checks/SKILL.md (or your agent's skills folder).
name
run-checks
description
Run the full local build that mirrors CI for FireCrasher — unit tests, Android lint, and the ABI baseline comparison. Use before pushing or opening a PR, or whenever asked to "run the tests", "check the build", or "verify it compiles".

Run the CI-equivalent checks

CI (.github/workflows/build.yml) runs ./gradlew build --stacktrace on JDK 21. build depends on check, which runs the unit tests, Android lint (abortOnError = true), and :firecrasher:apiCheck (the ABI baseline comparison). Reproduce it locally before pushing.

Steps

  1. Confirm the toolchain is JDK 21 (java -version). AGP 9.x + the Java 21 bytecode target require it.
  2. Run the full build:
    bash
    ./gradlew build --stacktrace
  3. For a faster inner loop while iterating, run the pieces directly:
    bash
    ./gradlew :firecrasher:test        # Robolectric unit tests
./gradlew :firecrasher:lint        # Android lint
./gradlew :firecrasher:apiCheck    # ABI baseline comparison

If it fails

  • Test failures — reports are under firecrasher/build/reports/tests/.
  • Lint failures — reports under firecrasher/build/reports/lint-results-*. Lint is set to fail the build; fix the finding rather than lowering severity.
  • apiCheck failure — the public API changed. If the change was intentional, use the update-abi-baseline skill; if not, it means you leaked something into the public surface — revisit the change.

Do not weaken abortOnError, delete tests, or edit the ABI baseline just to get green. Fix the underlying cause.

© osama-raddad, Apache-2.0. 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/run-checks of osama-raddad/FireCrasher.

Open the folder on GitHubat commit 7a06228

Compare with similar skills

Run Checks 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.

Run Checks compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Run Checks this skillosama-raddad/FireCrasher147—~403Automated safety check: PassApache-2.0
Checktimusus/Shuttle2229—~449Automated safety check: PassApache-2.0
Validationjosstei/maestro-orchestrate465—~2.3kAutomated safety check: PassApache-2.0
Android CheckAdyen/adyen-android149—~357Automated safety check: PassMIT
Android Unit Testnwjs/chromium.src160—~1.8kAutomated safety check: PassBSD-3-Clause
Dep Validateblokadaorg/blokada3.3k—~5.7kAutomated safety check: NotesMPL-2.0

Similar skills

  • Check

    timusus/Shuttle2

    Run lint + unit tests, investigate and fix failures. An agent skill from timusus/Shuttle2.

    229 GitHub stars~449 tokensUpdated today
    Testing & QAAuto-check passed

  • Validation

    josstei/maestro-orchestrate

    Cross-cutting validation methodology for verifying phase outputs and project integrity

    465 GitHub stars~2.3k tokensUpdated 3 days ago
    Testing & QAAuto-check passed

  • Android Check

    Adyen/adyen-android

    Run compile, lint, and unit test checks. An agent skill from Adyen/adyen-android.

    149 GitHub stars~357 tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Android Unit Test

    nwjs/chromium.src

    Guide for writing and converting Chromium Android unit tests across host Robolectric (chromejunittests) and on-device (chromepublicunittestapk) suites.

    160 GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed

  • Dep Validate

    blokadaorg/blokada

    A skill your agent uses to validate risky dependency bumps end to end as a local or cloud-launched agent.

    3.3k GitHub stars~5.7k tokensUpdated yesterday
    DevelopmentAuto-check: notes

  • Android Code Quality Checker

    wordpress-mobile/WordPress-Android

    Runs detekt, checkstyle, and Android lint together, reads their reports, and proposes approved fixes grouped by file.

    3.2k GitHub stars~587 tokensUpdated today
    DevelopmentAuto-check passed

More from osama-raddad/FireCrasher

All 8 skills in this repo

  • Add Library Test

    osama-raddad/FireCrasher

    Add or update a Robolectric JVM unit test for the FireCrasher library.

    147 GitHub stars~612 tokensUpdated 3 mo ago
    Auto-check passed

  • Customize Recovery

    osama-raddad/FireCrasher

    Inspect FireCrasher's recovery level and show custom recovery UX (loading dialog, toast, snackbar) or force a specific recovery level.

    147 GitHub stars~624 tokensUpdated 3 mo ago
    Auto-check passed

  • Detect Native Crashes And Anrs

    osama-raddad/FireCrasher

    Report native crashes, ANRs, and low-memory kills that FireCrasher's in-process handler cannot catch, using ApplicationExitInfo on API 30+.

    147 GitHub stars~662 tokensUpdated 3 mo ago
    Auto-check passed

  • Install Firecrasher

    osama-raddad/FireCrasher

    Add the FireCrasher crash-recovery library to an Android app and install it in the Application class.

    147 GitHub stars~562 tokensUpdated 3 mo ago
    Auto-check passed

  • Release

    osama-raddad/FireCrasher

    Cut a new FireCrasher library release — bump the version, sync the README and ABI baseline, verify, and tag for JitPack.

    147 GitHub stars~649 tokensUpdated 3 mo ago
    Auto-check passed

  • Update Abi Baseline

    osama-raddad/FireCrasher

    Regenerate and review FireCrasher's committed public ABI baseline (firecrasher/api/firecrasher.api) after an intentional public API change.

    147 GitHub stars~508 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Categories

Questions about Run Checks

What does Run Checks do?

Run the full local build that mirrors CI for FireCrasher — unit tests, Android lint, and the ABI baseline comparison. Run Checks is an agent skill from osama-raddad/FireCrasher. Run the full local build that mirrors CI for FireCrasher — unit tests, Android lint, and the ABI baseline comparison.

When should I use Run Checks?

Run Checks fits situations like: tasks that involve Unit testing; tasks that involve Linting and formatting.

How do I install Run Checks in Claude Code?

Run `npx skills add osama-raddad/FireCrasher --skill run-checks -a claude-code`. Or copy the skill folder (.claude/skills/run-checks in osama-raddad/FireCrasher) into .claude/skills/run-checks in your project. Claude Code loads it when a task matches its description.

How do I install Run Checks in Codex?

Run `npx skills add osama-raddad/FireCrasher --skill run-checks -a codex`. Or copy the skill folder (.claude/skills/run-checks in osama-raddad/FireCrasher) into .agents/skills/run-checks in your project. Codex loads it when a task matches its description.

Can I use Run Checks 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 osama-raddad/FireCrasher --skill run-checks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/run-checks, .gemini/skills/run-checks, .github/skills/run-checks and .opencode/skills/run-checks in your project.

What does Run Checks need to run?

Going by SKILL.md and its folder, Run Checks needs the command-line tools its instructions call (java).

Does Run Checks 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 Run Checks 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 Run Checks use?

Run Checks is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Run Checks use?

About 403 tokens (SKILL.md is roughly 1.6k 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 Run Checks?

Skills that share tags, products or a category with Run Checks: Check (timusus/Shuttle2, 229 stars), Validation (josstei/maestro-orchestrate, 465 stars), Android Check (Adyen/adyen-android, 149 stars) and Android Unit Test (nwjs/chromium.src, 160 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Run Checks?

osama-raddad (a GitHub user) maintains it in osama-raddad/FireCrasher, which has 147 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on July 3, 2026.

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