onboard-project
Skill2 starsChanged 7 days agoApache-2.0View on GitHub
Onboard a new project into projects/<KEY>/ — fills PROJECT.md from the template, seeds learnings.md + bug-report template, adds it to memory/INDEX.md. Use for "/onboard-project", "Projekt einrichten", "neues Projekt onboarden", or when a ticket's prefix has no PROJECT.md. Not for adding a product — /onboard-product.
- Reads credentials
6 other projects use a version of this.
Adopted by
Most recently taken up by
- andrewgolovanov/agent-ostheir own version, first seen Nov 8, 2026
- Recluse/HyperMnesiatheir own version, first seen Nov 5, 2026
- BenaliHQ/paxus-skillstheir own version, first seen Oct 30, 2026
- qu1r0ra/skillstheir own version, first seen Oct 20, 2026
- crissmoldovan/agent-skillstheir own version, first seen Oct 15, 2026
- xiaolongnk/SuperHarnesstheir own version, first seen Sep 26, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- Recluse/HyperMnesia★ 17same name
- andrewgolovanov/agent-os★ 7same name
- BenaliHQ/paxus-skills★ 4same name
- xiaolongnk/SuperHarness★ 4same name
- crissmoldovan/agent-skills★ 2same name
- qu1r0ra/skills★ 1same name
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 repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessibility-testingSkill
- agentswitchSkill
- api-testingSkill
- bug-reportSkill
- bug-reproductionSkill
- demoSkill
- deploy-to-stageSkill
- exploratory-testingSkill
- failure-analysisSkill
- model-setupSkill
- onboard-productSkill
- perf-analysisSkill
- qa-helpSkill
- qa-metricsSkill
- qa-reportSkill
- re-boardSkill
- reconSkill
- release-readinessSkill
- report-to-jiraSkill
- retest-bugSkill
- retro-learnSkill
- risk-based-testingSkill
- scaffold-suiteSkill
- security-testingSkill
- skill-reviewSkill
- test-automationSkill
- test-case-managementSkill
- test-reliabilitySkill
- test-ticketSkill
- visual-testingSkill
- webdriverio-testingSkill
- whats-newSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 1 is distinctive, and 6 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Ask for the JIRA project key (must match the directory name you'll create).
- Very specific: line 26
Read projects/EXAMPLE/PROJECT.md alongside the template as a filled reference — it's fictional but shows what a complete answer looks like …
- Very specific: line 50
Test users — vault paths only, never actual passwords in this conversation.
- Very specific: line 84
Test assets — framework first: Ask which framework the suite uses (playwright or webdriverio) before asking where it lives.
- Very specific: line 97
Leave any field the user can't answer yet as TODO: — never fill a guess.
- Very specific: line 113
Add one line for the new project to memory/INDEX.md under "Projects" — this is what keeps lookups fast later.
- Very specific: line 121
Resolve secrets if the source is keychain: run the blueprint's resolve-secrets.sh once (bash …
“Common” is measured: kept by at least 6 in 10 of the 6 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
/onboard-project — teach the agent a new project
Expect this to take real back-and-forth with the user (~30–60 min for a first
project) — every field matters for later autonomous testing, and guessing here is
exactly what the router (CLAUDE.md in Claude Code, .opencode/ROUTER.md in
opencode) forbids ("never guess a project's process").
Steps
- Ask for the JIRA project key (must match the directory name you'll create).
- Copy
projects/_template/toprojects/<KEY>/(includingtemplates/, but notproducts/— that scaffold stays put until/onboard-productneeds it). In plugin mode the scaffold is not in this repo: the session start bootstrap createsprojects/empty on purpose, so copy fromprojects/_template/(plugin mode:$CLAUDE_PLUGIN_ROOT/projects/_template/) and write only into the consumer's repo. Same for the two reads below — the reference project lives atprojects/EXAMPLE/(plugin mode:$CLAUDE_PLUGIN_ROOT/projects/EXAMPLE/). Without this branch step 2 copies from a path that does not exist and onboarding stops at its first write. Readprojects/EXAMPLE/PROJECT.mdalongside the template as a filled reference — it's fictional but shows what a complete answer looks like per field. Ignore itsproducts/tree and its## Productssection unless the user says this project covers several products. - Walk through every
PROJECT.mdsection with the user, section by section, not as one giant question dump:- Basics — and ask for the JIRA deployment early:
cloudordatacenter. It decides the MCP backend and auth (Cloud: official remote server + OAuth; Data Center: community serversooperset/mcp-atlassian+ PAT via environment variables, server still namedatlassian) and the report content format — all detailed indocs/rules/testing/jira-confluence.md→ "Deployments". If Data Center and the consumer's.mcp.jsonstill carries the Cloud default, offer to swap the entry (name unchanged, no secrets in the file). Then ask for the JIRA access mode:mcp(default, everything above applies) orbrowser— for environments where no API path exists at all (policy forbids tokens, REST blocked, only a web login). Onbrowser: record the JIRA base URL and the secret keys holding the JIRA login in PROJECT.md, skip the MCP-swap offer entirely, and readdocs/rules/testing/jira-browser.md— it governs every JIRA interaction from then on. TheatlassianMCP entry may be left out of.mcp.jsonaltogether in a browser-only QA home. - Confluence links, environments (stage URL, version-check method, who deploys).
- Test users — vault paths only, never actual passwords in this
conversation. Then ask once how the secret keys should reach
.env.playwright-secretsand record it as Secrets source:keychain(macOS — each key is a login-keychain service of the same name; give the user the one-time command per key:security add-generic-password -s <SECRET_KEY> -a qa -w) orenv-file(the user fills the gitignored file by hand — tell them to do it directly in the file, out of chat). If the setup has a credential MCP server, it may resolve references — it still never surfaces a value, and browser logins keep going through--secretsmasking (.claude/rules/core/security.md→ "Credential sources"). - Deploy runbook — use
docs/runbooks/stage-deploy-general.mdas the scaffold if the user doesn't have one written down yet. - Pipelines/gate overrides, MR process, test assets location, gotchas. For
readiness, ask for the exact JIRA statuses that permit stage testing, the
merge policy (
when-linkedrecommended,always, ornot-required), and the API/CLI queries for blockers, linked MR/PR state and deployed build. If no version source exists, explicitly chooseBuild verification: unavailableand record the residual reporting risk; do not invent an endpoint or an MR requirement for projects that do not use one. - Reporting — fetch, do not ask. Transition names and the priority scheme are
facts that live in JIRA, and
docs/rules/testing/jira-confluence.mdis explicit that a guessed transition fails loudly in some workflows and silently no-ops in others. So: pull the issue type's workflow transitions and the project's priority names via the Atlassian MCP and let the user pick from the real list, the same wayonboard-productfetches the real component list. Only fall back to asking if the MCP is unavailable — and then mark the fieldsTODO:rather than writing down what the user thinks the transition is probably called. Onbrowseraccess the same rule holds: read the workflow buttons off a real ticket's UI if possible, otherwiseTODO:. - Deploy trigger. "Trigger the pipeline" is not a command. Ask for the exact
one (
gh workflow run …,glab ci run …, a curl, or "manual — ask X") and record it;/deploy-to-stagepreflights it and reports BLOCKED when it is missing. - Test assets — framework first. Ask which framework the suite uses
(
playwrightorwebdriverio) before asking where it lives;test-automatorreads the framework field to pick its conventions. A suite that doesn't exist yet is "none yet" — do not guess a framework for a hypothetical future suite. - Execution mode. One question with a recommended default:
hybrid(recon → spec via CLI → short live verification pass). Offermcp-onlyfor brand-new projects without a suite or heavily visual products, andcli-firstfor mature suites in pipeline operation. Explain in one sentence what each costs; the four sub-fields (Verification pass,Red check required,Escalate at risk,Plan approval) take the template defaults unless the user objects — do not interview them individually. Background:docs/pipeline/00-overview.md.
- Basics — and ask for the JIRA deployment early:
- Leave any field the user can't answer yet as
TODO:— never fill a guess. Flag TODOs clearly at the end so they get resolved before the first real test. - Seed
projects/<KEY>/learnings.mdfrom the template (empty, ready forretro-learnto populate), andprojects/<KEY>/flow-map.mdfrom its template (empty area skeleton —retest-bugscopes regression sweeps from it onceretro-learnhas promoted the first flows; absent map = risk-based fallback, so an empty skeleton is fine). Then replace the placeholderprojects/<KEY>/templates/bug-report.mdwith the base template matching the report format chosen above —.claude/skills/bug-report/templates/jira-cloud.mdorplain-text.md(always the latter onbrowseraccess — the DC editor takes rich text, no ADF needed; plugin mode: the same paths under$CLAUDE_PLUGIN_ROOT/) — and adjust section names, order and extra fields to the project's conventions. This is not optional polish:bug-reporterreads that file as the template, so a project that keeps the placeholder stalls on its first FAIL.projects/EXAMPLE/templates/bug-report.mdshows a finished one. - Add one line for the new project to
memory/INDEX.mdunder "Projects" — this is what keeps lookups fast later. - Stamp the blueprint version into
PROJECT.md→ Basics: readversionfrom the installed plugin manifest (.claude-plugin/plugin.jsonvia the support link; plugin mode:$CLAUDE_PLUGIN_ROOT/.claude-plugin/plugin.json) and write it asBlueprint version: <version>./whats-newand/re-boardkey off this stamp later — never leave itTODO:. - Resolve secrets if the source is keychain: run the blueprint's
resolve-secrets.shonce (bash $CLAUDE_PLUGIN_ROOT/.claude/hooks/resolve-secrets.sh(plugin mode) /bash .claude/hooks/resolve-secrets.sh(opencode/shared/integrate via symlink)). It prints only key names. Offer the two assisted storage paths before handing over the manual command:--importmigrates values the user already hand-filled into.env.playwright-secretsinto the keychain (declared keys only, values never surface);--captureasks the user for each missing key through a native macOS hidden-answer dialog — they type into a GUI box, never into the chat. The manual one-time command (security add-generic-password -s <SECRET_KEY> -a qa -w) remains the fallback for headless setups. Onenv-fileremind the user once to fill.env.playwright-secretsdirectly. Bridge file for vendored skills — one per project, never shared: write
.agents/qa-project-context/<KEY>.md(note: a directory keyed by project, not the single flat.agents/qa-project-context.mdthe vendored skills' own text describes) as a projection of thePROJECT.mdyou just filled — product one-liner, tech/test stack, environments, CI/CD, quality goals (gate overrides), risk areas (from "Gotchas"), team/conventions if known. This lets the vendored skills under.claude/skills/(risk-based-testing,api-testing,accessibility-testing,security-testing,visual-testing,test-reliability,qa-metrics,test-case-management,release-readiness,bug-reproduction— see.claude/skills/THIRD_PARTY_NOTICES.md) work without re-asking discovery questions already answered inPROJECT.md. A filled-in model of this file (for the fictionalSHOPproject, kept next to the example project rather than under.agents/for the same collision reason) isprojects/EXAMPLE/qa-project-context.md— read it before writing your first.Why per-project, not one shared file: this repo can hold many onboarded projects (
projects/SHOP/,projects/ACME/, ...). A single shared bridge file would silently go stale or get overwritten the moment a second project is onboarded or tested — whoever invokes a vendored skill next would read the previous project's context without any error. Keying by<KEY>makes staleness structurally impossible instead of relying on remembering to refresh a shared file. See the router → project routing for the rule that every vendored-skill invocation must point at the current ticket's file.PROJECT.mdstays the source of truth for this blueprint's own skills/hooks;.agents/qa-project-context/<KEY>.mdis a read-only-by-convention projection — regenerate it ifPROJECT.mdchanges materially rather than editing both by hand. Give it the frontmattergenerated_from:(source paths) andsource_sha:so staleness is checkable instead of remembered. Once the project has products, this file servesproject-widetickets and each product gets its own merged projection at.agents/qa-project-context/<KEY>/<PRODUCT>.md, written byonboard-product.- Confirm with the user: read the completed
PROJECT.mdback as a summary and ask them to correct anything before considering onboarding done. - Mention products exactly once, in the closing next-steps — not as a question
during the interview, which would cost every user time to serve a minority:
"Does this JIRA project cover several products with different test methods,
features, or test users? Then run
/onboard-product— this file stays the shared base and each product only records what differs." Never createproducts/yourself;onboard-productdoes that after an explicit confirmation.
What this skill never does
Invent environment URLs, test users, or pipeline names. Store an actual password
or API token in PROJECT.md (references only — see
.claude/rules/core/security.md). Treat projects/_template/ or
projects/EXAMPLE/ as real projects to test against.
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.

