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

Leapp Corpus Run

by abrignoni in abrignoni/VLEAPP

Run a LEAPP tool end to end against a real extraction to validate artifact changes and produce a handoff.

MITAuto-check passedTesting & QA

Install Leapp Corpus Run

skills CLI
$ npx skills add abrignoni/VLEAPP --skill leapp-corpus-run -a claude-code

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

GitHub CLI
$ gh skill install abrignoni/VLEAPP leapp-corpus-run --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/abrignoni/VLEAPP.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/leapp-corpus-run .claude/skills/leapp-corpus-run && 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
leapp-corpus-run
GitHub stars
118
Token cost
~792 tokens
SKILL.md length
448 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Run a LEAPP tool end to end against a real extraction to validate artifact changes and produce a handoff.

  • Works in 5 steps: Build a focused profile → Pick an extraction that actually… → Run it and read the output → …
  • Changed artifacts before a PR
  • SKILL.md covers 1. Build a focused profile, 2. Pick an extraction that…, 3. Run it and read the output and 4. Record what you verified, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Leapp Corpus Run is an agent skill from abrignoni/VLEAPP. Run a LEAPP tool end to end against a real extraction to validate artifact changes and produce a handoff. Use when verifying new or changed artifacts before a PR, when asked to "run it against a real image" or "check the report", or when confirming recorded sampledata row counts.

Its SKILL.md is about 790 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. The repository describes itself as: Vehicle Logs Events And Properties Parser. The licence is MIT.

When your agent uses it

  • Changed artifacts before a PR
  • Asked to run it against a real image
  • Check the report
  • Confirming recorded sampledata row counts

Example prompts

  • “run it against a real image”
  • “check the report”
  • “/leapp-corpus-run”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Build a focused profile
  2. Pick an extraction that actually exercises the change
  3. Run it and read the output
  4. Record what you verified
  5. Hand off

What it can do on your machine

Read from SKILL.md and the folder at commit eada9a9. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Leapp Corpus Run loads about 792 tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 448 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~792

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 abrignoni/VLEAPP at commit eada9a9, republished under its MIT licence (© abrignoni). 448 words, ~792 tokens.

Download SKILL.mdSave it as .claude/skills/leapp-corpus-run/SKILL.md (or your agent's skills folder).
name
leapp-corpus-run
description
Run a LEAPP tool end to end against a real extraction to validate artifact changes and produce a handoff. Use when verifying new or changed artifacts before a PR, when asked to "run it against a real image" or "check the report", or when confirming recorded sample_data row counts.
<!-- SHARED SKILL. Canonical copy lives in leapps-org/leapps-parity under skills/.
     Do not edit in place; edit the canonical copy and re-run the sync script. -->

Validating against a real extraction

Unit tests and a clean import prove the module loads. They do not prove it parses. An end-to-end run against a real extraction is the validation that counts, and it is what should back any claim in the PR.

1. Build a focused profile

Create a tool profile containing only the artifacts you changed or added. A profile naming a handful of modules turns a full-image run from tens of minutes into seconds, which is what makes iterating on real data practical.

Plugin names in a profile are the artifact function names.

2. Pick an extraction that actually exercises the change

One that contains the app, at an OS version where the data shape matches what you parsed. When no single image covers everything, assemble a compact composite from the relevant files plus their SQLite sidecars. A -wal or -shm left behind changes what a reader sees, so carry them or knowingly drop them.

Keep source images read-only. Do extraction and any permission changes on a temporary copy. Never point the tool at your only copy of an image.

3. Run it and read the output

Generate output somewhere you will actually look at it, then check:

  • Row counts per artifact, against what you expected. Both zero and implausibly large are findings.
  • Column alignment. A tuple-width mismatch shifts every column right and is easy to miss when the values are plausible.
  • Timestamps in the first column, in the right epoch, in the right zone.
  • Export formats the artifact declares. If output_types includes KML, open it.
  • Parser errors in the log. A caught exception per artifact does not fail the run, so a green exit code is not evidence of a clean parse.
  • The LAVA output, if the artifact writes one. Open the case in LAVA rather than assuming the manifest is right. Record counts come from the manifest, not a live query, so an artifact that writes rows without updating the count shows as empty.
Show full SKILL.md (118 more words)Show less

4. Record what you verified

Add the confirmed counts to sample_data as "<corpus key>": "<OS> <ver> | <n> rows", including zero-row corpora.

Reference corpora by key only. A key plus a row count is a pointer back to the data behind it, so do not name files, paths or values.

5. Hand off

State what was run, against which extraction, what the counts were, and what you did not cover: OS versions untested, app versions unseen, code paths present but never exercised. The gaps are the most useful part of the report, and leaving them out turns a bounded result into an implied general claim.

Give clickable paths to the profile, the report entry point and the output folder.

© abrignoni, MIT. 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/leapp-corpus-run of abrignoni/VLEAPP.

Open the folder on GitHubat commit eada9a9

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in abrignoni/VLEAPP, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Leapp Corpus Run 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.

Leapp Corpus Run compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Leapp Corpus Run this skillabrignoni/VLEAPP118—~792Automated safety check: PassMIT
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
Diagnosing Bugsfossasia/eventyay-interpretation1.6k32 repos~2.1kAutomated safety check: PassApache-2.0
TDDpietheinstrengholt/rssmonster56430 repos~906Automated safety check: PassMIT
TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph11211 repos~2.4kAutomated safety check: PassNone
TDDsanity-io/sanity6.4k20 repos~1kAutomated safety check: PassMIT

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed

  • Diagnosing Bugs

    fossasia/eventyay-interpretation

    Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 32 repos~2.1k tokens
    Testing & QAAuto-check passed

  • TDD

    pietheinstrengholt/rssmonster

    Test-driven development. An agent skill from pietheinstrengholt/rssmonster.

    564 GitHub starsUsed in 30 repos~906 tokens
    Testing & QAAuto-check passed

  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed

  • TDD

    sanity-io/sanity

    Official

    Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.

    6.4k GitHub starsUsed in 20 repos~1k tokens
    Testing & QAAuto-check passed

  • Context Driven Development

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…

    381 GitHub starsUsed in 9 repos~2.9k tokens
    Testing & QAAuto-check passed

More from abrignoni/VLEAPP

  • Leapp New Artifact

    abrignoni/VLEAPP

    Write, rework, review or audit a LEAPP artifact module. An agent skill from abrignoni/VLEAPP.

    118 GitHub stars~3.9k tokensUpdated 2 days ago
    Auto-check passed

  • Lava Data View

    abrignoni/VLEAPP

    Wire up how an artifact renders in LAVA, end to end across the producer and the viewer.

    118 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

  • Leapp Sweep Siblings

    abrignoni/VLEAPP

    After fixing an artifact in one LEAPP core, find and fix the same defect in the sibling cores.

    118 GitHub stars~695 tokensUpdated 2 days ago
    Auto-check passed

  • Leapp Validate Globs

    abrignoni/VLEAPP

    Validate LEAPP artifact path globs against real extraction file listings before committing them.

    118 GitHub stars~776 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Leapp Corpus Run

What does Leapp Corpus Run do?

Run a LEAPP tool end to end against a real extraction to validate artifact changes and produce a handoff. Leapp Corpus Run is an agent skill from abrignoni/VLEAPP. Run a LEAPP tool end to end against a real extraction to validate artifact changes and produce a handoff.

When should I use Leapp Corpus Run?

Leapp Corpus Run fits situations like: changed artifacts before a PR; asked to run it against a real image; check the report; confirming recorded sampledata row counts.

How do I install Leapp Corpus Run in Claude Code?

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

How do I install Leapp Corpus Run in Codex?

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

Can I use Leapp Corpus Run 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 abrignoni/VLEAPP --skill leapp-corpus-run -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/leapp-corpus-run, .gemini/skills/leapp-corpus-run, .github/skills/leapp-corpus-run and .opencode/skills/leapp-corpus-run in your project.

What does Leapp Corpus Run need to run?

SKILL.md names no scripts, command-line tools or credentials: Leapp Corpus Run is instructions for the agent only.

Does Leapp Corpus Run 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 Leapp Corpus Run 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 Leapp Corpus Run use?

Leapp Corpus Run is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Leapp Corpus Run use?

About 792 tokens (SKILL.md is roughly 3.2k 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 Leapp Corpus Run?

Skills that share tags, products or a category with Leapp Corpus Run: Web Application Testing (anthropics/skills, 180k stars), Diagnosing Bugs (fossasia/eventyay-interpretation, 1.6k stars), TDD (pietheinstrengholt/rssmonster, 564 stars) and TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Leapp Corpus Run?

abrignoni (a GitHub user) maintains it in abrignoni/VLEAPP, which has 118 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

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