f1-test-drive
Skill902 starsChanged 53 days agoApache-2.0View on GitHub
Assess F1 applicability, then validate changed product workflows or the F1 harness end-to-end. Skip drives and reports when no relevant workflow behavior changes.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ceedaragents/cyrusword for word, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- ceedaragents/cyrus★ 888100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- packages/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- googleSkill
- release-core-testSkill
- cyrus-setup-claude-authSkill
- cyrus-setup-endpointSkill
- cyrus-setup-githubSkill
- cyrus-setup-gitlabSkill
- cyrus-setup-launchSkill
- cyrus-setup-linearSkill
- cyrus-setup-prerequisitesSkill
- cyrus-setup-repositorySkill
- cyrus-setupSkill
- cyrus-setup-slackSkill
- debugSkill
- implementationSkill
- investigateSkill
- releaseSkill
- summarizeSkill
- verify-and-shipSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
If F1 is not applicable, stop this protocol before setup and reporting.
- Distinctive: line 62
Create a fresh test repository (if needed):
- Distinctive: line 88
Verify issue ID and issue creation response.
- Very specific: line 109
Use when validating the Slack → ChatSessionHandler → ClaudeRunner path.
- Distinctive: line 120
Verify shared auto-memory wiring:
- Distinctive: line 125
Verify per-thread workspace isolation alongside shared memory:
- Distinctive: line 149
Stop background server process.
- Very specific: line 153
Only after an applicable F1 drive, write a report under apps/f1/test-drives/.
- Distinctive: line 207
no activities after reasonable wait
- Very specific: line 213
Prefer fixed port 3600 unless already in use.
- Distinctive: line 214
Use fresh test repos per drive.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
F1 Test Drive
Applicability (required before setup)
This is the canonical F1 applicability policy. Inspect the actual diff against the PR base and identify the behavior that needs validation before starting F1, selecting a fixture, or creating a report. Task size, issue labels, filenames, and a generic request to verify/ship are not sufficient reasons to run F1.
- Required: product/runtime changes exercised by F1 (issue tracking, authentication, routing, runner/session lifecycle, activity rendering), and functional changes to the F1 harness itself. Choose scenarios with assertions that exercise the changed behavior; a generic health check or unrelated fixture does not establish correctness.
- Not applicable: documentation, agent instructions, CI/release tooling, installer/build/packaging metadata, or other changes with no relevant product workflow behavior. Run appropriate documentation, script, unit, integration, build, package inspection, or isolated install smoke checks instead. Do not run F1 or create, attach, or commit an F1 test-drive report. A brief PR note stating why F1 is not applicable and what checks passed is enough.
- Mixed changes: exercise only the relevant functional portion with F1; validate other portions with their targeted checks. A docs, infrastructure, or metadata path is never an exemption for a real runtime behavior change (including dependencies, generated prompts, or installed defaults).
- Actual releases: assess the entire released payload against the previous
release, not merely the version-bump PR. Runtime-bearing payloads retain
relevant F1 validation. Payloads with no F1-covered behavior change use the
non-F1 release verification described in
apps/cli/RELEASING.md. Editing release tooling is not itself preparing or publishing a functional release.
If F1 is not applicable, stop this protocol before setup and reporting. If it is applicable but blocked, report the missing coverage and blocker honestly; do not relabel it as not applicable or substitute an unrelated passing drive. Preserve historical reports.
| Actual change | Validation choice |
| PR #1502 artifact workflow and isolated installer tooling, without the separate agent-identity feature | Workflow/script tests, bundle integrity, isolated install and CLI smoke checks; no unrelated identity F1 fixture or report. |
| README wording or instruction-only policy such as CYPACK-1537 | Review consistency, links, and policy examples; no F1 report. Release-validator edits use proportionate verification; retain tests for consequential evidence-acceptance failures. |
| Runtime routing fix plus documentation | F1 scenario asserting changed routing; documentation checks for the rest. |
| EdgeWorker auth, routing, or session lifecycle | Relevant F1 scenarios asserting identity isolation, selected repository, or session continuation/termination as changed. |
| F1 RPC command, fixture execution, or activity renderer behavior | Exercise the changed harness path end-to-end and its unit/integration tests. Editing only F1 documentation still uses documentation checks. |
| Release PR changing only versions but shipping an unreleased session fix | Assess since the previous release; run relevant session F1 validation. |
| Release shipping only infrastructure/docs changes with no relevant workflow behavior | Record payload assessment and targeted checks as non-F1 release verification; no artificial F1 report. |
Mission (when applicable)
Validate the changed workflow through the relevant issue-tracker, EdgeWorker, and activity output paths. Name the scenario, expected behavior, and assertions before setup. Use the phases below as building blocks; include only paths needed for that scenario, plus setup and cleanup.
Test Drive Protocol
Phase 1: Setup
- Create a fresh test repository (if needed):
cd apps/f1 ./f1 init-test-repo --path /tmp/f1-test-drive-<timestamp> - Start F1 server:
CYRUS_PORT=3600 CYRUS_REPO_PATH=/tmp/f1-test-drive-<timestamp> bun run apps/f1/server.ts & - Verify server health:
CYRUS_PORT=3600 ./f1 ping CYRUS_PORT=3600 ./f1 status
Phase 2: Issue-Tracker Verification
- Create test issue:
CYRUS_PORT=3600 ./f1 create-issue \ --title "<issue title>" \ --description "<issue description>" - Verify issue ID and issue creation response.
Phase 3: EdgeWorker Verification
- Start agent session:
CYRUS_PORT=3600 ./f1 start-session --issue-id <issue-id> - Monitor activities:
CYRUS_PORT=3600 ./f1 view-session --session-id <session-id> - Verify:
- session started
- activities appear
- agent is processing issue
Phase 3.5: Slack Chat Session Verification (optional)
Use when validating the Slack → ChatSessionHandler → ClaudeRunner path. F1 exposes a test-only endpoint /cli/dispatch-chat that injects a synthetic app_mention event without going through Slack signature verification (SlackChatAdapter no-ops Slack API calls when slackBotToken is undefined).
- Dispatch a synthetic chat event:
The response contains aCYRUS_PORT=3600 ./f1 start-chat-session \ --channel C_TEST_CHAN \ --user U_TEST_USER \ --text "hello"threadKeyof the form<channel>:<ts>. Reuse the same--thread-tsto address the same chat thread on subsequent dispatches. - Verify shared auto-memory wiring:
- The chat workspace exists at
<cyrusHome>/slack-workspaces/<sanitized-threadKey>/. - The shared auto-memory directory exists (or is lazily creatable) at
<cyrusHome>/slack-memory/. - The
claude_query_optionsevent emitted byClaudeRunnercarriescqo.settingsAutoMemoryDirectory=<cyrusHome>/slack-memory.
- The chat workspace exists at
- Verify per-thread workspace isolation alongside shared memory:
- Dispatch a second event in a different channel/thread.
- Confirm a separate
slack-workspaces/<other-thread-key>/directory exists (workspaces remain isolated). - Confirm both dispatches' telemetry resolve to the same
slack-memorypath (memory is shared).
Phase 4: Renderer Verification
- Validate activity payload quality:
- expected types (for example
thought,action,response) - timestamps present
- content well-formed and readable
- expected types (for example
- Validate pagination behavior:
CYRUS_PORT=3600 ./f1 view-session --session-id <session-id> --limit 10 --offset 0
Phase 5: Cleanup
- Stop active session:
CYRUS_PORT=3600 ./f1 stop-session --session-id <session-id> - Stop background server process.
Reporting Format
Only after an applicable F1 drive, write a report under apps/f1/test-drives/.
Record the tested commit, changed behavior, commands, assertions, results, and
limitations. Adapt this template to the relevant scenario; omit unrelated
checklists. Never create a placeholder or “not applicable” F1 report:
# Test Drive #NNN: [Goal Description]
**Date**: YYYY-MM-DD
**Goal**: [One sentence]
**Test Repo**: [Path]
## Verification Results
### Issue-Tracker
- [ ] Issue created
- [ ] Issue ID returned
- [ ] Issue metadata accessible
### EdgeWorker
- [ ] Session started
- [ ] Worktree created (if applicable)
- [ ] Activities tracked
- [ ] Agent processed issue
### Renderer
- [ ] Activity format correct
- [ ] Pagination works
- [ ] Search works
## Session Log
[commands + key outputs + pass/fail]
## Final Retrospective
[what worked, issues, recommendations]Pass/Fail Criteria
Pass only when the changed-behavior assertions pass, along with the applicable workflow checks below:
- Server starts
- Issue created successfully
- Session starts and activities appear
- Activity payloads are coherent
- Session stops cleanly
- No unhandled errors
Fail when:
- server startup fails
- issue creation fails
- session does not start
- no activities after reasonable wait
- malformed activity data
- unhandled exceptions
Important Notes
- Prefer fixed port
3600unless already in use. - Use fresh test repos per drive.
- Preserve failed state when debugging.
- For functional runner/harness changes, validate the affected path end-to-end before merge, as required by the applicability policy above.
Multi-Harness Note
This skill is intentionally harness-agnostic:
- Claude subagents can call this skill.
- Codex/OpenCode workflows can reference the same skill content.
- Harness-specific adapters should be thin wrappers around this canonical skill.
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.

