agentleFS
Sign inStart free
MyriambsMyriambs/argus-qa/skills/qa-init/SKILL.md

qa-init

Skill0 starsChanged 28 days agoMITView on GitHub

Bootstrap Argus QA memory for the current project. Scans the repo to detect stack, test frameworks, test commands, CI, app start command/URLs, environments, roles and risky areas, then writes .qa/context.md — the product knowledge every Argus agent reads first. Run once per project; re-run to refresh.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. uppadhyayraj/dq-awesomeqa★ 2same 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 repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Test frameworks and configs: playwright.config.*, cypress.config.*, jest/vitest.config.*, pytest.ini/conftest.py, karma, JUnit and similar.

    line 14
  2. Very specific:

    Test and run commands: scripts in package.json, Makefile, justfile, docker-compose*.yml, Procfile, the README

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Argus · Project bootstrap

Build the QA memory for this project. Extra notes from the user: $ARGUMENTS

Steps

  1. Detect (read-only):
    • Stack and package managers: package.json, pyproject.toml/requirements*.txt, go.mod, pom.xml/build.gradle, Gemfile, composer.json, Cargo.toml
    • Test frameworks and configs: playwright.config.*, cypress.config.*, jest/vitest.config.*, pytest.ini/conftest.py, karma, JUnit and similar. Count the test files per type.
    • Test and run commands: scripts in package.json, Makefile, justfile, docker-compose*.yml, Procfile, the README
    • CI: .github/workflows/*, .gitlab-ci.yml, Jenkinsfile. Note which tests run on PRs.
    • API contracts: openapi*.{yml,yaml,json}, swagger*, *.graphql, route files
    • Auth and roles: grep for role, permission, isAdmin, auth middleware
    • Risk hotspots: git log --since=6.months --name-only --pretty=format: | sort | uniq -c | sort -rn | head -15 (churn), plus files named payment, billing, auth, migration
    • Existing QA assets: docs/, test plans, .github/ISSUE_TEMPLATE
  2. Ask the user only about what you couldn't detect and that matters: the staging/local URL, test accounts (never store real passwords; reference env var names instead), what must never be touched, and any known flaky areas.
  3. Write .qa/context.md using this template, and create .qa/{bugs,sessions,reports,evidence,testcases}/ with a .gitkeep in each:
# QA Context: <project>
_Last updated: <date> by Argus /qa-init. Agents: append learnings, don't rewrite history._

## Product in one paragraph
## Users and roles
| Role | Can | Test account (env var) |
## Environments
| Env | URL | Safe for writes? | Notes |
## How to run
- Install: … · Start app: … · Unit: … · E2E: … · Lint/types: …
## Test landscape
| Level | Framework | Location | # files | Runs in CI? |
## Critical user journeys (money paths)
1. …
## Risk hotspots
| Area | Why risky | Evidence (churn, bugs, complexity) |
## Exit criteria (defaults, edit me)
## Never do
- No writes to production · no real emails/SMS/payments · …
## Known issues and flake patterns
## Glossary (domain terms)
  1. Suggest adding .qa/evidence/ to .gitignore (screenshots may contain data) and committing the rest so the whole team shares the QA memory.
  2. Summarize in five lines or fewer: what was detected, what's missing, and the 3 best next Argus commands for this project.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free