dogfood

Name: dogfood
Author: mvschwarz

56stars9forks

How to install dogfood?

mvschwarz/openrig/dogfood

$npx -y skills add mvschwarz/openrig --skill dogfood

Installs into the current project.

Summary

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report

Files · 1

View on GitHub

SKILL.md

1	# Dogfood
2
3	Systematically explore a web application, find issues, and produce a report with full reproduction evidence for every finding.
4
5	## Setup
6
7	Only the Target URL is required. Everything else has sensible defaults -- use them unless the user explicitly provides an override.
8
9	\| Parameter \| Default \| Example override \|
10	\|-----------\|---------\|-----------------\|
11	\| Target URL \| _(required)_ \| `vercel.com`, `http://localhost:3000` \|
12	\| Session name \| Slugified domain (e.g., `vercel.com` -> `vercel-com`) \| `--session my-session` \|
13	\| Output directory \| `./dogfood-output/` \| `Output directory: /tmp/qa` \|
14	\| Scope \| Full app \| `Focus on the billing page` \|
15	\| Authentication \| None \| `Sign in to user@example.com` \|
16
17	If the user says something like "dogfood vercel.com", start immediately with defaults. Do not ask clarifying questions unless authentication is mentioned but credentials are missing.
18
19	Always use `agent-browser` directly -- never `npx agent-browser`. The direct binary uses the fast Rust client. `npx` routes through Node.js and is significantly slower.
20
21	## Workflow
22
23	```
24	1. Initialize Set up session, output dirs, report file
25	2. Authenticate Sign in if needed, save state
26	3. Orient Navigate to starting point, take initial snapshot
27	4. Explore Systematically visit pages and test features
28	5. Document Screenshot + record each issue as found
29	6. Wrap up Update summary counts, close session
30	```
31
32	### 1. Initialize
33
34	```bash
35	mkdir -p {OUTPUT_DIR}/screenshots {OUTPUT_DIR}/videos
36	```
37
38	Copy the report template into the output directory and fill in the header fields:
39
40	```bash
41	cp {SKILL_DIR}/templates/dogfood-report-template.md {OUTPUT_DIR}/report.md
42	```
43
44	Start a named session:
45
46	```bash
47	agent-browser --session {SESSION} open {TARGET_URL}
48	agent-browser --session {SESSION} wait --load networkidle
49	```
50
51	### 2. Authenticate
52
53	If the app requires login:
54
55	```bash
56	agent-browser --session {SESSION} snapshot -i
57	# Identify login form refs, fill credentials
58	agent-browser --session {SESSION} fill @e1 "{EMAIL}"
59	agent-browser --session {SESSION} fill @e2 "{PASSWORD}"
60	agent-browser --session {SESSION} click @e3
61	agent-browser --session {SESSION} wait --load networkidle
62	```
63
64	For OTP/email codes: ask the user, wait for their response, then enter the code.
65
66	After successful login, save state for potential reuse:
67
68	```bash
69	agent-browser --session {SESSION} state save {OUTPUT_DIR}/auth-state.json
70	```
71
72	### 3. Orient
73
74	Take an initial annotated screenshot and snapshot to understand the app structure:
75
76	```bash
77	agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/initial.png
78	agent-browser --session {SESSION} snapshot -i
79	```
80
81	Identify the main navigation elements and map out the sections to visit.
82
83	### 4. Explore
84
85	Read [references/issue-taxonomy.md](references/issue-taxonomy.md) for the full list of what to look for and the exploration checklist.
86
87	Strategy -- work through the app systematically:
88
89	- Start from the main navigation. Visit each top-level section.
90	- Within each section, test interactive elements: click buttons, fill forms, open dropdowns/modals.
91	- Check edge cases: empty states, error handling, boundary inputs.
92	- Try realistic end-to-end workflows (create, edit, delete flows).
93	- Check the browser console for errors periodically.
94
95	At each page:
96
97	```bash
98	agent-browser --session {SESSION} snapshot -i
99	agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/{page-name}.png
100	agent-browser --session {SESSION} errors
101	agent-browser --session {SESSION} console
102	```
103
104	Use your judgment on how deep to go. Spend more time on core features and less on peripheral pages. If you find a cluster of issues in one area, investigate deeper.
105
106	### 5. Document Issues (Repro-First)
107
108	Steps 4 and 5 happen together -- explore and document in a single pass. When you find an issue, stop exploring and document it immediately before moving on. Do not explore the whole app first and document later.
109
110	Every issue must be reproducible. When you find something wrong, do not just note it -- prove it with evidence. The goal is that someone reading the report can see exactly what happ

People who liked this also viewed

6 picks

Type

dogfood

56stars9forks

View on GitHub

How to install dogfood?

mvschwarz/openrig/dogfood

$npx -y skills add mvschwarz/openrig --skill dogfood

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Dogfood
2
3	Systematically explore a web application, find issues, and produce a report with full reproduction evidence for every finding.
4
5	## Setup
6
7	Only the Target URL is required. Everything else has sensible defaults -- use them unless the user explicitly provides an override.
8
9	\| Parameter \| Default \| Example override \|
10	\|-----------\|---------\|-----------------\|
11	\| Target URL \| _(required)_ \| `vercel.com`, `http://localhost:3000` \|
12	\| Session name \| Slugified domain (e.g., `vercel.com` -> `vercel-com`) \| `--session my-session` \|
13	\| Output directory \| `./dogfood-output/` \| `Output directory: /tmp/qa` \|
14	\| Scope \| Full app \| `Focus on the billing page` \|
15	\| Authentication \| None \| `Sign in to user@example.com` \|
16
17	If the user says something like "dogfood vercel.com", start immediately with defaults. Do not ask clarifying questions unless authentication is mentioned but credentials are missing.
18
19	Always use `agent-browser` directly -- never `npx agent-browser`. The direct binary uses the fast Rust client. `npx` routes through Node.js and is significantly slower.
20
21	## Workflow
22
23	```
24	1. Initialize Set up session, output dirs, report file
25	2. Authenticate Sign in if needed, save state
26	3. Orient Navigate to starting point, take initial snapshot
27	4. Explore Systematically visit pages and test features
28	5. Document Screenshot + record each issue as found
29	6. Wrap up Update summary counts, close session
30	```
31
32	### 1. Initialize
33
34	```bash
35	mkdir -p {OUTPUT_DIR}/screenshots {OUTPUT_DIR}/videos
36	```
37
38	Copy the report template into the output directory and fill in the header fields:
39
40	```bash
41	cp {SKILL_DIR}/templates/dogfood-report-template.md {OUTPUT_DIR}/report.md
42	```
43
44	Start a named session:
45
46	```bash
47	agent-browser --session {SESSION} open {TARGET_URL}
48	agent-browser --session {SESSION} wait --load networkidle
49	```
50
51	### 2. Authenticate
52
53	If the app requires login:
54
55	```bash
56	agent-browser --session {SESSION} snapshot -i
57	# Identify login form refs, fill credentials
58	agent-browser --session {SESSION} fill @e1 "{EMAIL}"
59	agent-browser --session {SESSION} fill @e2 "{PASSWORD}"
60	agent-browser --session {SESSION} click @e3
61	agent-browser --session {SESSION} wait --load networkidle
62	```
63
64	For OTP/email codes: ask the user, wait for their response, then enter the code.
65
66	After successful login, save state for potential reuse:
67
68	```bash
69	agent-browser --session {SESSION} state save {OUTPUT_DIR}/auth-state.json
70	```
71
72	### 3. Orient
73
74	Take an initial annotated screenshot and snapshot to understand the app structure:
75
76	```bash
77	agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/initial.png
78	agent-browser --session {SESSION} snapshot -i
79	```
80
81	Identify the main navigation elements and map out the sections to visit.
82
83	### 4. Explore
84
85	Read [references/issue-taxonomy.md](references/issue-taxonomy.md) for the full list of what to look for and the exploration checklist.
86
87	Strategy -- work through the app systematically:
88
89	- Start from the main navigation. Visit each top-level section.
90	- Within each section, test interactive elements: click buttons, fill forms, open dropdowns/modals.
91	- Check edge cases: empty states, error handling, boundary inputs.
92	- Try realistic end-to-end workflows (create, edit, delete flows).
93	- Check the browser console for errors periodically.
94
95	At each page:
96
97	```bash
98	agent-browser --session {SESSION} snapshot -i
99	agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/{page-name}.png
100	agent-browser --session {SESSION} errors
101	agent-browser --session {SESSION} console
102	```
103
104	Use your judgment on how deep to go. Spend more time on core features and less on peripheral pages. If you find a cluster of issues in one area, investigate deeper.
105
106	### 5. Document Issues (Repro-First)
107
108	Steps 4 and 5 happen together -- explore and document in a single pass. When you find an issue, stop exploring and document it immediately before moving on. Do not explore the whole app first and document later.
109
110	Every issue must be reproducible. When you find something wrong, do not just note it -- prove it with evidence. The goal is that someone reading the report can see exactly what happ

People who liked this also viewed

6 picks

Type