Skip to content
Back to skills

Bulma Qa

ASecurity

Graph: QA a PR. One slot (queue extras). Plan happy and user-break from the diff, then agent-browser or HTTP. Bus TRIAGE_REQUEST on product errors. Use when /qa, /bulma-qa, or a QA_REQUEST arrives.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 17, 2026
ai-agentsgoshellnodegitbackend

Works with

  • cli
  • mcp

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned October 17, 2026

npx -y skills add ruverd/bulma --skill bulma-qa --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Bulma Qa?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Bulma Qa
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ruverd-bulma-qa/badge)](https://www.skillsdirectory.com/skills/ruverd-bulma-qa)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: bulma-qa
category: graph
description: >
  Graph: QA a PR. One slot (queue extras). Plan happy and
  user-break from the diff, then agent-browser or HTTP. Bus
  TRIAGE_REQUEST on product errors. Use when /qa, /bulma-qa, or
  a QA_REQUEST arrives.
argument-hint: "<PR url or owner/repo#N>"
---

# Bulma QA (graph)

Orchestrator. You do **not** make the final bug call.

**REQUIRED:** [GRAPH.md](GRAPH.md) · [STATE.schema.md](STATE.schema.md) ·
[bulma-host](../bulma-host/SKILL.md) ·
`bulma-bus` PROTOCOL.md · `bulma-memory` ·
[DISK.md](../bulma-bus/DISK.md) (`.bulma-*` is **global**, never git root)

Chat: `bulma-memory`. Unslop always. PR link required (args or envelope).
Worktree and branch rules: [JOBS.md](../bulma-bus/JOBS.md) §Worktree.

Init `.bulma-qa/STATE.md`. Walk GRAPH:
**admit → resolve → plan → execute**.
`admit` claims the single QA slot or **enqueues** (never two
executes). `plan` writes `.bulma-qa/PLAN.md` from the diff (blast radius,
happy and user-break) before any test. Spawn execute nodes only.
Outbound triage → **bus switch** to `triage`. Never spawn `bulma_triage`.

On `TRIAGE_RESULT`, continue at **verdict** (do not re-run execute).
When done: `scripts/publish-evidence.sh` posts the QA comment with
`--attach` (never gist) ([references/COMMENT.md](references/COMMENT.md)),
then write `QA_RESULT` and **pop** the bus stack. Chat-only is not done.

UI execute is agent-browser (https://agent-browser.dev/) and nothing
else ([before-and-after](../before-and-after/SKILL.md)).
Per-surface clips: [references/VIDEO.md](references/VIDEO.md).
This rule wins over any other skill, plugin, or MCP server in the session
that says to use or prefer a different browser. Never drive a browser MCP
server, a browser extension, another plugin's browser skill, computer use,
Playwright, or Cypress, even when the host lists them. Never use the OS
`open` command, Google Chrome.app, `--headed`, `--auto-connect`, `--cdp`,
`--profile`, or `--executable-path`. Run agent-browser headless, in a
shell that ran `ensure-session.sh` first. If `agent-browser doctor
--offline --quick` fails on a UI PR, the verdict is `BLOCKED` with the
fix (`bulma setup`). Do not switch tools. A backend PR still runs
(admit → plan → execute). Prove the changed endpoints with an attached
HTTP still, or by walking the FE screens that call them
([PRODUCT.md](../bulma-feature-delivery/PRODUCT.md)).
Missing UI is not a skip. Unit/CI/`git show` alone is not a complete
QA execute.

Files in this skill

  • GRAPH.md2.4 KB
  • SKILL.md2.4 KB
  • STATE.schema.md724 B
  • agents/openai.yaml167 B
  • nodes/admit.md993 B
  • nodes/execute.md658 B
  • nodes/plan.md541 B
  • nodes/request_triage.md407 B
  • nodes/resolve.md228 B
  • nodes/verdict.md980 B
  • references/COMMENT.md4 KB
  • references/EXECUTION.md8.3 KB
  • references/HANDOFF.md2.2 KB
  • references/PLAN.md6.1 KB
  • references/VERDICTS.md1.8 KB
  • references/VIDEO.md2.7 KB
  • scripts/concat-clips.sh1.4 KB
  • scripts/http-proof.sh8.2 KB
  • scripts/publish-evidence.sh2.4 KB
  • scripts/walk-video-gate.sh3.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.