Borrowing it
Nothing to install: this file belongs to BloomBooks/BloomDesktop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BloomBooks/BloomDesktop/master/.claude/skills/add-e2e-test/SKILL.mdgit clone --depth 1 https://github.com/BloomBooks/BloomDesktopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bloombooks/bloomdesktop/add-e2e-test)<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/add-e2e-test"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/add-e2e-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/add-e2e-test"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/add-e2e-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 30 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.09329 |
| Opus 5.5 | $0.00036 | $0.03732 |
| Sonnet 5.5 | $0.00018 | $0.01866 |
| Haiku 4.5 | $0.00009 | $0.00933 |
Grade A, and why
add-e2e-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 575 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add an edge-to-edge test
What an e2e test is here
An e2e test launches its own Bloom.exe on a known collection, drives the real UI in
the embedded WebView2, asserts, and tears the instance down. You can run a single test
locally; the nightly workflow (.github/workflows/nightly.yml) runs the whole suite every night
and on demand (its run_e2e_tests input).
Test code lives in BloomDesktop (src/BloomE2E/), versioned with the product code.
Test input collections live in https://github.com/BloomBooks/bloom-testing-inputs,
pinned by build/testing-inputs.pin and fetched to output/testing-inputs/ by
node build/get-testing-inputs.mjs.
Build Bloom whenever it helps; the usual rules are suspended here
The repo's guidance for agents says not to build Bloom: use the agent-dotnet wrapper, never
run pnpm build, let the dev server push front-end edits into the developer's running Bloom.
Those rules protect a Bloom the developer is running from this worktree. They do not apply
while you follow this skill. The suite launches its own Bloom.exe from output/Debug/ (or
output/Release/), with --e2e --automation --dont-disturb, on a temp copy of a collection, and
that instance runs alongside whatever Bloom the developer has open, never taking their keyboard.
Developing a test does not disturb them. (On CI the fixture leaves --dont-disturb off; a test
that fails only there may depend on focus. See "In CI" in src/BloomE2E/README.md.)
The Bloom you launch is also not the one the dev server feeds: it reads the front end from
output/browser and the C# from the built exe. So a test sees a change to Bloom only after a
build, and you build whenever it helps, without asking.
- A fresh worktree:
./init.sh(dependencies,pnpm install, and the full front-end build), thenpnpm installinsrc/BloomE2E,node build/get-testing-inputs.mjs, and the C# build below. - C# changed (an
E2eTestingApihook, anything undersrc/BloomExe/), or noBloom.exeis built yet:dotnet build src/BloomExe/BloomExe.csproj. Plaindotnet, not thebuild/agent-dotnetwrapper: the wrapper builds into a private tree and builds noBloom.exeapphost, so the suite would never find its output. - Front end changed (a
data-testidin a.tsxfile):pnpm build:uiinsrc/BloomBrowserUIrebuilds the bundles inoutput/browser, manifest included. Run the fullpnpm buildthere when the change also touches pug, LESS, markdown, or content. - Before you trust a failure, ask whether the build is current. A
data-testidthat is in the source but not inoutput/browser, or a hook that is inE2eTestingApi.csbut not in the exe, fails exactly like a bug in the test.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed · +37 lines faff65c0898a
- 1mo ago Changed · +2 lines 2f7e36c022df
- 1mo ago Changed · +6 lines 5311562c59f5
- 1mo ago Changed a6ca5a12a695
- 1mo ago Changed bc531f1d26fb
- 1mo ago Changed · +6 lines 924ca1c53e6c
- 1mo ago Changed · +3 lines 963d45055bca
- 1mo ago Changed · +21 lines 871477533063
- 1mo ago First seen · 500 lines · 89 tokens per session scan A a106bba824f0
add-e2e-test is a skill published in the GitHub repository BloomBooks/BloomDesktop (43 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 9,329 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.