bootstrap
Skill1 starsChanged 3 months agoMITView on GitHub
Use as the FIRST thing on a fresh clone (when PROJECT.md does not exist). Interviews the user about the target app, applies a profile (generic/controlled/salesforce/api-only), prunes what isn't needed, and writes PROJECT.md.
- Reads credentials
72 other projects use a version of this.
Adopted by
Most recently taken up by
- flavien-ia/hypervibe-harnesstheir own version, first seen Nov 15, 2026
- YardonYan/ui-design-skillstheir own version, first seen Nov 15, 2026
- joi-fairshare/agentic-workflowtheir own version, first seen Nov 14, 2026
- vercel/vercel-plugintheir own version, first seen Nov 12, 2026
- victorbeppler/claude-bootstraptheir own version, first seen Nov 8, 2026
- zedarvates/frugal-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use surprise-me, ppt-generation and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
stophobiaSkillsurprise-me
Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".
Also in 3 projects that use this
HK-hubSkillppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
Also in 3 projects that use this
stophobiaSkillgithub-deep-research
Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.
Also in 3 projects that use this
HK-hubSkillconsulting-analysis
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This skill operates in two phases — (1) generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic, and (2) after data collection by other skills, producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights.
Also in 3 projects that use this
MicrosoftSkillpodcast-generation
Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.
Also in 3 projects that use this
VercelSkillvercel-deploy
Deploy applications and websites to Vercel with a claimable preview. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". No authentication required - returns preview URL and claimable deployment link.
Also in 4 projects that use this
- +1 more from HK-hub
Other versions72 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 72
- bytedance/deer-flow★ 85ksame name
- mozilla-mobile/firefox-ios★ 13ksame name
- openai/plugins★ 7.8ksame name
- agentscope-ai/OpenJudge★ 1.1ksame name
- modelscope/OpenJudge★ 1.1ksame name
- iovisor/ubpf★ 996same name
- stophobia/deerflow2.0-enhanced★ 821same name
- infragate/capa★ 718same name
- EvovexAI/EvoFlow★ 612same name
- vercel/vercel-plugin★ 336same name
62 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ai-native-workflowSkill
- api-testingSkill
- common-tasksSkill
- configSkill
- data-strategySkill
- debuggingSkill
- enumsSkill
- fixturesSkill
- page-objectsSkill
- salesforce-authSkill
- salesforce-dataSkill
- salesforce-locatorsSkill
- salesforce-metadata-contractSkill
- salesforce-personasSkill
- salesforceSkill
- salesforce-waitsSkill
- security-testingSkill
- selectorsSkill
- test-standardsSkill
- type-safetySkill
- wait-strategySkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 63 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Ask the user (batch the questions):
- Distinctive: line 23
If the answer is "API only", AND the suite will be large, AND the API is the primary SUT, AND the backend is non-TypeScript → recommend a …
- Distinctive: line 30
Read the chosen profile file.
- Distinctive: line 58
Commit the generated schemas.
- Very specific: line 72
no auth → delete the setup project + its dependencies, and delete helpers/auth/auth.setup.ts, and drop storageState from UI projects.
- Very specific: line 73
Env: create env/.env.<env> from the example.
- Very specific: line 91
Don't generate tests before PROJECT.md exists.
- Very specific: line 92
Don't silently delete OR silently keep the example files — ask (see Phase 4).
- Distinctive: line 93
Don't pick a profile for the user silently — confirm the app type first.
“Common” is measured: kept by at least 6 in 10 of the 63 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Bootstrap — Day 0
Turns the generic scaffold into one tailored to a specific target. Run this once per new project,
before writing any tests. If PROJECT.md already exists, do NOT run this — read it instead.
Phase 1 — Interview (ask, don't guess)
Ask the user (batch the questions):
- What are we testing? UI, API, or both?
- App type? generic web app / an app we control the source of / Salesforce (or other heavy SPA).
- Auth? Is there a login? Credentials/SSO? Or no auth (e.g. a local app)?
- API contract? Is there an OpenAPI/Swagger spec? Where?
- Base URL(s) for the first environment.
Phase 2 — The API-only gate (be honest)
If the answer is "API only", AND the suite will be large, AND the API is the primary SUT, AND the
backend is non-TypeScript → recommend a backend-native tool instead (pytest+Pydantic, RestAssured,
Schemathesis/Dredd) and stop. Don't scaffold browser projects for that. (CLAUDE.md §5, api-testing P1.)
Phase 3 — Select the profile
Map app type → profile (see profiles/*.md): generic | controlled | salesforce | api-only.
Read the chosen profile file; it specifies locator priority, wait notes, and auth handling.
If the profile is NOT salesforce, prune the Salesforce pack — it's dead weight otherwise:
.claude/skills/salesforce*/, config/salesforce.config.ts, enums/salesforce/, helpers/salesforce/,
fixtures/salesforce/, pages/salesforce/, test-data/salesforce/, tests/salesforce/,
scripts/generate-sobject-schemas.ts, docs/salesforce/, the org + persona-setup projects in
playwright.config.ts, and the sf:* / test:contract / test:personas scripts in package.json.
If the profile IS salesforce, go to Phase 3b instead of Phase 4.
Phase 3b — Salesforce bootstrap (only for the salesforce profile)
Load the salesforce skill, then work through these in order. Ask; don't guess — every item here is org
state you cannot read from a repo.
- Org access. Which org(s) (scratch / Dev / Partial / Full sandbox / prod)? Recommend a scratch org
per CI run if the team can adopt it. Never bootstrap against production. Testing more than one
environment (e.g. dev + staging)? Copy the
env/.env.salesforce.exampleblock into EACHenv/.env.<environment>file — storage state and the generated snapshot are already namespaced byENVIRONMENTwith nothing extra to do; seedocs/salesforce/TEST-ARCHITECTURE.md§"Multi-environment" for what ISN'T automatic (the hand-authored contract/personas assume one environment's model). - Auth strategy (
salesforce-auth).jwtfor CI needs a Connected App — that's a human-with-Setup task; hand them the 5 steps from the skill and confirm step 4 (app assigned to the test users' profile/permset) is done.sfdxis fine locally. - Personas. Which users/profiles/permission sets matter? Write them into
test-data/salesforce/personas.tsand add oneSF_USERNAME_<KEY>env var per persona. - Objects in scope. Which sObjects will the suite touch? Then run the generator:
npm run sf:schemas -- Account Contact Opportunity— this is what makes rule #15 satisfiable. Commit the generated schemas; they are the drift snapshot. - API version. Pin
SF_API_VERSIONand run the contract spec to confirm the org supports it. - Verify the assumptions. Walk
docs/salesforce/VERIFY-BEFORE-FIRST-RUN.mdwith the user. It lists every org-dependent thing the pack assumes (session injection mechanism, IP locking, which screens useui-apivs/aura, whether Duplicate Rules are on). Do NOT skip this — the pack ships patterns that are correct in general and need confirming per org. - Then continue with Phase 4 (env, enums, example files) and Phase 5.
Phase 4 — Apply the profile (propose the diff first, then edit on approval)
- Selector priority: the active profile is recorded in
PROJECT.md; theselectorsskill reads it. (No code change needed unless flipping example locators inpages/login.page.ts.) - Projects: in
playwright.config.ts, remove projects the target doesn't use:- api-only → delete
setup,functional,e2e; keepapi. - UI-only → keep
setup/functional/e2e; you may keepapifor setup/teardown. - no auth → delete the
setupproject + itsdependencies, and deletehelpers/auth/auth.setup.ts, and dropstorageStatefrom UI projects.
- api-only → delete
- Env: create
env/.env.<env>from the example; fillBASE_URL/API_URL/creds.BASE_URLis the app ROOT (e.g.https://demo.playwright.dev) — do NOT bake a path segment into it (e.g..../todomvc), or agoto('/')will drop the path. Put path segments inenums/util/routes.tsand navigate to them. - Enums/config: replace the example endpoints/routes/messages with the target's real ones (verify live / against OpenAPI — don't guess).
- Example files — ASK the user, don't decide silently: the scaffold ships example page objects + specs. Ask whether to (a) delete them or (b) keep them as reference. If kept, the example specs (
tests/**/*.spec.ts—login,users,users.security,user-journey) MUST be moved out oftests/(e.g. to anexamples/folder) — they target a fake app and will run and FAIL if left in a test project. Example page objects/components are harmless to keep.
Phase 5 — Write PROJECT.md
Copy PROJECT.md.template → PROJECT.md and fill in: profile, what's tested, auth model, locator
priority, API-contract source, base URLs, and any target-specific facts discovered (framework, known
flaky areas, iframe/shadow-DOM notes for Salesforce). This file overrides the generic defaults for all
future tasks.
Phase 6 — Hand off
Point the user at the first real task (usually a page object via page-objects, or an API suite via
api-testing). From here, normal audit-then-edit applies.
Don't
- Don't generate tests before
PROJECT.mdexists. - Don't silently delete OR silently keep the example files — ask (see Phase 4). If the user keeps them, move the example specs out of
tests/so they don't run and fail against the real app. - Don't pick a profile for the user silently — confirm the app type first.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

