Agent skill

Phase6 Smoke Test

by PersonalJarvis in PersonalJarvis/PersonalJarvis

A skill your agent uses to run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop.

Apache-2.0Auto-check passedTesting & QA

Install Phase6 Smoke Test

skills CLI
$ npx skills add PersonalJarvis/PersonalJarvis --skill phase6-smoke-test -a claude-code

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

GitHub CLI
$ gh skill install PersonalJarvis/PersonalJarvis phase6-smoke-test --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/PersonalJarvis/PersonalJarvis.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/phase6-smoke-test .claude/skills/phase6-smoke-test && 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
phase6-smoke-test
GitHub stars
166
Token cost
~725 tokens
SKILL.md length
232 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses to run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop.

  • Works in 4 steps: Check prerequisites → Run the smoke-test script (already… → Test run with the test-runner subagent… → …
  • Run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop
  • SKILL.md covers When to use, Steps, Strictly forbidden and Edge cases
  • Calls python and pytest

What it does

Phase6 Smoke Test is an agent skill from PersonalJarvis/PersonalJarvis. Use to run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop. Spawns a mock-task through the full pipeline (Mission-spawn → Worker-stub → Critic-verdict → Kontrollierer signature → Bus-event trace) and reports a pass/fail with structured output. Use after Phase-6 modifications or before merging changes that touch jarvis/missions/.

Its SKILL.md is about 730 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, covering QA and bug reports and Structured output and tool calling. The repository describes itself as: Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows, macOS, Linux. The licence is Apache-2.0.

When your agent uses it

  • Run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop
  • Tasks that involve QA and bug reports
  • Tasks that involve Structured output and tool calling

Example prompts

  • “/phase6-smoke-test”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Check prerequisites
  2. Run the smoke-test script (already exists under scripts/smoke_phase6_p1.py, scripts/smoke_phase6_p2.py, scripts/smoke_phase6_p3.py)
  3. Test run with the test-runner subagent against tests/missions/, asking
  4. Generate the report

What it can do on your machine

Read from SKILL.md and the folder at commit a7397da. 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

    Shell commands in SKILL.md call:

    • python
    • pytest

    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

Phase6 Smoke Test loads about 725 tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 232 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~725

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 PersonalJarvis/PersonalJarvis at commit a7397da, republished under its Apache-2.0 licence (© PersonalJarvis). 232 words, ~725 tokens.

Download SKILL.mdSave it as .claude/skills/phase6-smoke-test/SKILL.md (or your agent's skills folder).
name
phase6-smoke-test
description
Use to run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop. Spawns a mock-task through the full pipeline (Mission-spawn → Worker-stub → Critic-verdict → Kontrollierer signature → Bus-event trace) and reports a pass/fail with structured output. Use after Phase-6 modifications or before merging changes that touch jarvis/missions/.

Phase-6 Smoke-Test

This skill runs a fast end-to-end smoke test against the Phase-6 pipeline. It is not as exhaustive as the real test suite, but in under 30s it delivers a confidence check that the mission pipeline runs through without hanging.

When to use

  • After changes to jarvis/missions/manager.py, critic/, kontrollierer/, workers/, isolation/.
  • Before a merge PR to main, so that pipeline integrity is confirmed.
  • When you suspect a Mission-Manager hang (reattach, concurrency).

Steps

  1. Check prerequisites:

    • python -c "from jarvis.missions.manager import MissionManager" — an ImportError catches drift early.
    • pytest tests/missions/ --collect-only -q — lists the tests, catches collection errors.
  2. Run the smoke-test script (already exists under scripts/smoke_phase6_p1.py, scripts/smoke_phase6_p2.py, scripts/smoke_phase6_p3.py):

    bash
    python scripts/smoke_phase6_p1.py    # Foundation: Bus + Store + Manager
    python scripts/smoke_phase6_p2.py    # Worker-Layer: Job-Object + Worktree
    python scripts/smoke_phase6_p2_jobkill.py  # Job-Kill-Pfad
    python scripts/smoke_phase6_p3.py    # Critic-Loop + Kontrollierer

    If a script is missing — mark it as MISSING in the report and continue.

  3. Test run with the test-runner subagent against tests/missions/, asking it for the JSON body:

    pytest tests/missions/ -v --tb=short --no-header --maxfail=15
  4. Generate the report:

    ## Phase-6 Smoke-Test — <timestamp>
    
    ### Smoke scripts
    - p1 Foundation: <PASS|FAIL — short>
    - p2 Worker-Layer: <PASS|FAIL>
    - p2 Job-Kill: <PASS|FAIL>
    - p3 Critic-Loop: <PASS|FAIL>
    
    ### Test suite
    - Tests: <N total, M green, K red>
    - Failures: <if present, top 3 with test name>
    
    ### Verdict
    <SMOKE PASS | SMOKE FAIL — N Failures>

Strictly forbidden

  • NO modifying mission code to repair it — the smoke test is diagnostic, not reactive.
  • NO "skipping over" tests when they are red — the report shows it.
  • NO re-run on flaky — the output shows the behavior exactly as it is.

Edge cases

  • Smoke scripts missing: if all four scripts/smoke_phase6_*.py are missing, Phase 6 is probably not installed. Report with PHASE_6_NOT_INSTALLED.
  • Tests collect 0: either Phase 6 is not there yet, or the pytest path is wrong. Report with NO_TESTS_COLLECTED.
  • Smoke script hangs > 30s: time cap violated — report it as MAJOR.

© PersonalJarvis, Apache-2.0. 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 .agents/skills/phase6-smoke-test of PersonalJarvis/PersonalJarvis.

Open the folder on GitHubat commit a7397da

Compare with similar skills

Phase6 Smoke Test 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.

Phase6 Smoke Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Phase6 Smoke Test this skillPersonalJarvis/PersonalJarvis166—~725Automated safety check: PassApache-2.0
Reproduce Chat Statesdifferent-ai/openwork24k—~673Automated safety check: PassCustom licence
Dynamo Jira TicketDynamoDS/Dynamo2k—~1.1kAutomated safety check: PassApache-2.0
Moav E2EMotherofallVPNs/MoaV449—~1.9kAutomated safety check: NotesMIT
Creating A Coral TaskHuman-Agent-Society/CORAL1.1k—~2.2kAutomated safety check: PassApache-2.0
Launch Rlmarin-community/marin3.9k—~894Automated safety check: PassApache-2.0

Similar skills

  • Reproduce Chat States

    different-ai/openwork

    Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.

    24k GitHub stars~673 tokensUpdated today
    Testing & QAAuto-check passed
  • Dynamo Jira Ticket

    DynamoDS/Dynamo

    Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.

    2k GitHub stars~1.1k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Moav E2E

    MotherofallVPNs/MoaV

    Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.

    449 GitHub stars~1.9k tokensUpdated 3 days ago
    Testing & QAAuto-check: notes
  • Creating A Coral Task

    Human-Agent-Society/CORAL

    Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…

    1.1k GitHub stars~2.2k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Launch Rl

    marin-community/marin

    Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.

    3.9k GitHub stars~894 tokensUpdated today
    Testing & QAAuto-check passed
  • Actionbook Web Test

    actionbook/actionbook

    Run browser-based web tests against websites using Actionbook CLI.

    1.6k GitHub stars~9.7k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

More from PersonalJarvis/PersonalJarvis

All 12 skills in this repo
  • Skill Creator

    PersonalJarvis/PersonalJarvis

    Creates a new Jarvis skill from the user's description — the assistant writes the whole skill (name, trigger phrase, schedule, steps, spoken answer format) and files it as a draft.

    166 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Jarvis Doc Author

    PersonalJarvis/PersonalJarvis

    Authoritative skill for writing internal Personal-Jarvis docs under docs/ and sibling directories.

    166 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Drive Jarvis CLI

    PersonalJarvis/PersonalJarvis

    A skill your agent uses when you (a Claude Code / Codex session, or any terminal agent) need to control a running Personal Jarvis instance — switch the brain provider, dispatch or inspect missions…

    166 GitHub stars~945 tokensUpdated today
    Auto-check passed
  • Generate CLI Command

    PersonalJarvis/PersonalJarvis

    Use after building a feature that adds or changes a REST route in jarvis/ui/web/routes.py, as the "definition of done" before committing.

    166 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Phase6 Adr Update

    PersonalJarvis/PersonalJarvis

    A skill your agent uses when a Phase-6 architecture decision needs to be amended or a new Phase-6 ADR needs to be written (e.g.

    166 GitHub stars~893 tokensUpdated today
    Auto-check passed
  • Control API

    PersonalJarvis/PersonalJarvis

    Change Jarvis's own configuration through the local Control API instead of clicking the desktop UI or driving Computer-Use.

    159 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Phase6 Smoke Test

What does Phase6 Smoke Test do?

A skill your agent uses to run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop. Phase6 Smoke Test is an agent skill from PersonalJarvis/PersonalJarvis. Use to run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop.

When should I use Phase6 Smoke Test?

Phase6 Smoke Test fits situations like: run a quick end-to-end smoke test against the Phase-6 Mission-Manager + Critic-Loop; tasks that involve QA and bug reports; tasks that involve Structured output and tool calling.

How do I install Phase6 Smoke Test in Claude Code?

Run `npx skills add PersonalJarvis/PersonalJarvis --skill phase6-smoke-test -a claude-code`. Or copy the skill folder (.agents/skills/phase6-smoke-test in PersonalJarvis/PersonalJarvis) into .claude/skills/phase6-smoke-test in your project. Claude Code loads it when a task matches its description.

How do I install Phase6 Smoke Test in Codex?

Run `npx skills add PersonalJarvis/PersonalJarvis --skill phase6-smoke-test -a codex`. Or copy the skill folder (.agents/skills/phase6-smoke-test in PersonalJarvis/PersonalJarvis) into .agents/skills/phase6-smoke-test in your project. Codex loads it when a task matches its description.

Can I use Phase6 Smoke Test 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 PersonalJarvis/PersonalJarvis --skill phase6-smoke-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/phase6-smoke-test, .gemini/skills/phase6-smoke-test, .github/skills/phase6-smoke-test and .opencode/skills/phase6-smoke-test in your project.

What does Phase6 Smoke Test need to run?

Going by SKILL.md and its folder, Phase6 Smoke Test needs the command-line tools its instructions call (python and pytest). Our summary lists: Python 3.

Does Phase6 Smoke Test 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 Phase6 Smoke Test 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 Phase6 Smoke Test use?

Phase6 Smoke Test is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Phase6 Smoke Test use?

About 725 tokens (SKILL.md is roughly 2.9k 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 Phase6 Smoke Test?

Skills that share tags, products or a category with Phase6 Smoke Test: Reproduce Chat States (different-ai/openwork, 24k stars), Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars), Moav E2E (MotherofallVPNs/MoaV, 449 stars) and Creating A Coral Task (Human-Agent-Society/CORAL, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Phase6 Smoke Test?

PersonalJarvis (a GitHub organization) maintains it in PersonalJarvis/PersonalJarvis, which has 166 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 11, 2026.

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