Feature Testing

What it does

When your agent uses it

• Tasks that involve Browser testing
• Tasks that involve End-to-end testing
• Tasks that involve MCP servers

Example prompts

• “/feature-testing”

Requirements

• Python 3
• Docker
• A credential in BREEZE_API_KEY
• A credential in AUTH_TOKEN

Workflow steps

8 steps, taken from the step headings in SKILL.md.

1. 1Classify Feature
2. 2Environment Check
3. 3Build & Deploy (Agent Only)
4. 4UI Verification (Playwright MCP)
5. 5API Verification
6. 6Agent Log Verification (Agent Only)
7. 7Record Results
8. 8Tear Down

What it can do on your machine

Read from SKILL.md and the folder at commit 1f72bb7. 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:

  • make
  • curl
  • python3
  • docker
  • pnpm

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl, docker and pnpm, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • E2E_ADMIN_PASSWORD
  • BREEZE_API_KEY
  • AUTH_TOKEN
  • REDIS_PASSWORD

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Feature Testing loads about 3k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 951 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~62

When it runs · the whole SKILL.md, loaded when a task matches

~3k

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

• NoteMentions a .env fileSKILL.md:14

  code credentials. Always read from root `.env` using the `E2E_*` variables (`E2E_BASE_URL`, `E2E_API_URL`, `E2E_ADMIN_EM

• NoteMentions a .env fileSKILL.md:29

  ### Required .env Variables

• NoteMentions a .env fileSKILL.md:31

  Read the root `.env` file and confirm these are set:

• NoteMentions a .env fileSKILL.md:38

  MIN_PASSWORD` | Login password | (set in .env) |

• NoteMentions a .env fileSKILL.md:66

  redis-cli -a "$(grep '^REDIS_PASSWORD=' .env | cut -d= -f2)" --no-auth-warning EVAL "local k=redis.call('KEYS','login:*

• NoteMentions a .env fileSKILL.md:80

  Reads defaults from `../.env.dev` (gitignored):

• NoteMentions a .env fileSKILL.md:337

  & make dev-push                    # Use .env.dev defaults

• NoteMentions a .env fileSKILL.md:345

  redis-cli -a "$(grep '^REDIS_PASSWORD=' .env | cut -d= -f2)" --no-auth-warning EVAL "local k=redis.call('KEYS','login:*

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 LanternOps/breeze at commit 1f72bb7, republished under its AGPL-3.0 licence (© LanternOps). 951 words, ~2,957 tokens.

name

feature-testing

description

Post-implementation end-to-end feature verification. Use after implementing a feature to verify it works across UI, API, and agent layers using Playwright MCP tools, make dev-push, diagnostic logs API, and structured test logging.

docker compose ps --format "table {{.Name}}\t{{.Status}}" | grep -E "api|web|postgres|redis"

curl -sf "${E2E_API_URL}/api/v1/devices/${E2E_MACOS_DEVICE_ID}" \
  -H "X-API-Key: ${BREEZE_API_KEY}" | python3 -c "import sys,json; d=json.load(sys.stdin); print(f'{d[\"hostname\"]} — {d[\"status\"]}')"

docker exec breeze-redis redis-cli -a "$(grep '^REDIS_PASSWORD=' .env | cut -d= -f2)" --no-auth-warning EVAL "local k=redis.call('KEYS','login:*'); for _,v in ipairs(k) do redis.call('DEL',v) end; return #k" 0

cd agent
make dev-push

curl -sf "${E2E_API_URL}/api/v1/devices/${DEVICE_ID}" \
  -H "X-API-Key: ${BREEZE_API_KEY}" | python3 -c "import sys,json; d=json.load(sys.stdin); print(f'version={d.get(\"agentVersion\",\"?\")} status={d[\"status\"]}')"

1. browser_navigate → ${E2E_BASE_URL}/login
2. browser_snapshot → confirm login form rendered
3. browser_fill_form → email + password fields
4. browser_click → submit button
5. browser_wait_for → URL changes away from /login (timeout 10s)
6. browser_snapshot → confirm dashboard loaded

curl -sf -X POST "${E2E_API_URL}/api/v1/auth/login" \
  -H "Content-Type: application/json" \
  -d "{\"email\":\"${E2E_ADMIN_EMAIL}\",\"password\":\"${E2E_ADMIN_PASSWORD}\"}" \
  | python3 -c "import sys,json; print(json.load(sys.stdin)['tokens']['accessToken'])"

# Example: verify a new endpoint returns expected data
TOKEN=$(curl -sf -X POST "${E2E_API_URL}/api/v1/auth/login" \
  -H "Content-Type: application/json" \
  -d "{\"email\":\"${E2E_ADMIN_EMAIL}\",\"password\":\"${E2E_ADMIN_PASSWORD}\"}" \
  | python3 -c "import sys,json; print(json.load(sys.stdin)['tokens']['accessToken'])")

curl -sf "${E2E_API_URL}/api/v1/<endpoint>" \
  -H "Authorization: Bearer ${TOKEN}" | python3 -m json.tool

curl -sf "${E2E_API_URL}/api/v1/devices/${DEVICE_ID}/diagnostic-logs?level=error,warn&since=$(date -u -v-5M +%Y-%m-%dT%H:%M:%SZ)" \
  -H "Authorization: Bearer ${TOKEN}" | python3 -m json.tool

docker exec breeze-postgres-dev psql -U breeze -d breeze -c "
  SELECT timestamp, level, component, message, agent_version
  FROM agent_logs
  WHERE device_id = '${DEVICE_ID}'
    AND timestamp > now() - interval '5 minutes'
  ORDER BY timestamp DESC LIMIT 30;"

{
  "type": "set_log_level",
  "payload": { "level": "debug", "durationMinutes": 30 }
}

## [Feature Name] — YYYY-MM-DD

**Branch:** `branch-name`
**Commit:** `abc1234`
**Tested by:** Claude / Human
**Result:** PASS / PARTIAL / FAIL

### What was tested
- [ ] UI: description of UI verification
- [ ] API: description of API verification
- [ ] Agent: description of agent verification

### Evidence
- Screenshot: (path or description)
- API response: (summary)
- Agent logs: (relevant excerpt)

### Issues Found
- (none, or describe issues)

### Notes
- (any additional context)

pnpm wt-stack down       # dev stack (drops volumes)
pnpm test-stack down     # integration pg+redis
docker compose ls -a     # confirm nothing from this run is still listed

cd agent && make dev-push                    # Use .env.dev defaults
cd agent && make dev-push DEVICE=<uuid>      # Override device
cd agent && make dev-push API_URL=<url>      # Override API URL

docker exec breeze-redis redis-cli -a "$(grep '^REDIS_PASSWORD=' .env | cut -d= -f2)" --no-auth-warning EVAL "local k=redis.call('KEYS','login:*'); for _,v in ipairs(k) do redis.call('DEL',v) end; return #k" 0

© LanternOps, AGPL-3.0. 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 .claude/skills/feature-testing of LanternOps/breeze.

Open the folder on GitHubat commit 1f72bb7