reproduce-bug-report

Name: reproduce-bug-report
Author: warpdotdev

13kinstalls1forks

How to install reproduce-bug-report?

warpdotdev/common-skills/reproduce-bug-report

$npx -y skills add warpdotdev/common-skills --skill reproduce-bug-report

Installs into the current project.

Summary

Launch Oz cloud agents with computer use to reproduce UI-focused bug reports, capture visual evidence, and report reproduction findings. Use when investigating a specific interactive or visual bug from an issue, ticket, support report, or prompt.

Files · 1

View on GitHub

SKILL.md

1	# Reproduce bug report
2
3	Use this skill when the current context is a GitHub issue, support report, Linear ticket, or user prompt describing a specific bug that may be reproduced through visible application behavior. It is primarily for UI, rendering, windowing, settings, editor, terminal-display, onboarding, or other interactive bugs where screenshots or recordings make the result more actionable.
4
5	The parent agent should not try to manually reproduce the UI bug locally unless the user explicitly asks. Launch one or more Oz cloud agents with computer use enabled so they can run the relevant app, interact with it, and capture visual evidence.
6
7	## Parent workflow
8
9	1. Read the bug report carefully and extract:
10	- reported behavior
11	- expected behavior
12	- reproduction steps, if provided
13	- OS, app version/build/channel, shell, feature flags, account state, or other environment constraints when relevant
14	- attached screenshots, videos, logs, or comments that narrow the repro path
15	2. Decide whether this skill applies:
16	- Use it for UI-visible bugs, interaction bugs, rendering/layout bugs, onboarding bugs, and bugs where screenshot evidence would be useful.
17	- Do not use it for purely backend, CI, build, dependency, or text-only code issues unless the prompt specifically asks for visual reproduction.
18	- If the report requires credentials, private account state, or another capability not available to the repro environment, report that constraint clearly instead of guessing.
19	3. If the reproduction path is straightforward, launch one Oz cloud agent with computer use.
20	4. If there are multiple plausible repro paths, launch several Oz cloud agents in one `run_agents` batch. Give each child a distinct hypothesis or environment variant, such as:
21	- different OS or desktop environment
22	- fresh first-run state vs an already-initialized local state
23	- stable vs dev build
24	- fresh settings vs existing settings
25	- different shells, prompts, pane layouts, or settings toggles
26	5. If steps are incomplete, use codebase knowledge to propose likely app states and assign children to investigate those states. Do not invent facts about the original reporter's environment.
27	6. Wait for all children to report before summarizing. Distinguish confirmed reproduction, partial reproduction, non-reproduction, blockers, and untested hypotheses.
28
29	## Version and app setup
30
31	- Prefer reproducing against the exact app version/build/channel reported by the user when a suitable runnable artifact exists.
32	- Do not silently substitute the latest available build when a closer reporter-matched artifact can be installed.
33	- Prefer a released or packaged runnable artifact over a source build when that better matches the reporter's environment and the repository-specific guidance allows it.
34	- If the exact version/build cannot be found or installed, report that clearly, explain what was attempted, and use the closest justified fallback only when it is useful for continuing the investigation.
35	- Record the requested reporter version, the installed test version, the artifact source, and any fallback decision in the manifest and final report.
36
37	## Repository-specific guidance
38
39	The consuming repository may ship a companion `reproduce-bug-report-local` skill. When that companion is available or referenced in the prompt, read it and apply its repository-specific scope, app setup, environment, and workflow guidance as supplemental instructions. The local companion may narrow scope or specialize setup, but it should not redefine the evidence, artifact, reporting, or safety expectations in this core skill.
40
41	Use a `run_agents` call shaped like this:
42
43	```text
44	summary: Launching Oz cloud computer-use agents to reproduce the reported UI bug and collect screenshots.
45	remote.computer_use_enabled: true
46	agent_run_configs:
47	- name: "repro-primary"
48	prompt: the primary repro prompt
49	- name: "repro-variant"
50	prompt: optional variant prompt when useful
51	base_prompt: the shared child prompt below
52	```
53
54	Omit extra children when they would duplicate the same steps. Omit `model_id` unless the user requested a specific model.
55
56	## Shared child prompt
57
58	Give every child agent these shared instructions, then append the child-specific repro path or hypothesis.
59
60	```text
61	You are trying to reproduce a reported UI bug using Oz cloud computer use.
62
63	Goal:
64	- Reproduce the reported behavior as faithfully as possible.
65	- Capture screenshots before and after each meaningful interaction.
66	- If the provided steps are unclear or incomplete, use codebase and product knowledge to identify plausible app states that could produce the reported behavior, then test the assigned hypothesis.
67	- Report clear

People who liked this also viewed

6 picks

Type

reproduce-bug-report

13kinstalls1forks

View on GitHub

How to install reproduce-bug-report?

warpdotdev/common-skills/reproduce-bug-report

$npx -y skills add warpdotdev/common-skills --skill reproduce-bug-report

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Reproduce bug report
2
3	Use this skill when the current context is a GitHub issue, support report, Linear ticket, or user prompt describing a specific bug that may be reproduced through visible application behavior. It is primarily for UI, rendering, windowing, settings, editor, terminal-display, onboarding, or other interactive bugs where screenshots or recordings make the result more actionable.
4
5	The parent agent should not try to manually reproduce the UI bug locally unless the user explicitly asks. Launch one or more Oz cloud agents with computer use enabled so they can run the relevant app, interact with it, and capture visual evidence.
6
7	## Parent workflow
8
9	1. Read the bug report carefully and extract:
10	- reported behavior
11	- expected behavior
12	- reproduction steps, if provided
13	- OS, app version/build/channel, shell, feature flags, account state, or other environment constraints when relevant
14	- attached screenshots, videos, logs, or comments that narrow the repro path
15	2. Decide whether this skill applies:
16	- Use it for UI-visible bugs, interaction bugs, rendering/layout bugs, onboarding bugs, and bugs where screenshot evidence would be useful.
17	- Do not use it for purely backend, CI, build, dependency, or text-only code issues unless the prompt specifically asks for visual reproduction.
18	- If the report requires credentials, private account state, or another capability not available to the repro environment, report that constraint clearly instead of guessing.
19	3. If the reproduction path is straightforward, launch one Oz cloud agent with computer use.
20	4. If there are multiple plausible repro paths, launch several Oz cloud agents in one `run_agents` batch. Give each child a distinct hypothesis or environment variant, such as:
21	- different OS or desktop environment
22	- fresh first-run state vs an already-initialized local state
23	- stable vs dev build
24	- fresh settings vs existing settings
25	- different shells, prompts, pane layouts, or settings toggles
26	5. If steps are incomplete, use codebase knowledge to propose likely app states and assign children to investigate those states. Do not invent facts about the original reporter's environment.
27	6. Wait for all children to report before summarizing. Distinguish confirmed reproduction, partial reproduction, non-reproduction, blockers, and untested hypotheses.
28
29	## Version and app setup
30
31	- Prefer reproducing against the exact app version/build/channel reported by the user when a suitable runnable artifact exists.
32	- Do not silently substitute the latest available build when a closer reporter-matched artifact can be installed.
33	- Prefer a released or packaged runnable artifact over a source build when that better matches the reporter's environment and the repository-specific guidance allows it.
34	- If the exact version/build cannot be found or installed, report that clearly, explain what was attempted, and use the closest justified fallback only when it is useful for continuing the investigation.
35	- Record the requested reporter version, the installed test version, the artifact source, and any fallback decision in the manifest and final report.
36
37	## Repository-specific guidance
38
39	The consuming repository may ship a companion `reproduce-bug-report-local` skill. When that companion is available or referenced in the prompt, read it and apply its repository-specific scope, app setup, environment, and workflow guidance as supplemental instructions. The local companion may narrow scope or specialize setup, but it should not redefine the evidence, artifact, reporting, or safety expectations in this core skill.
40
41	Use a `run_agents` call shaped like this:
42
43	```text
44	summary: Launching Oz cloud computer-use agents to reproduce the reported UI bug and collect screenshots.
45	remote.computer_use_enabled: true
46	agent_run_configs:
47	- name: "repro-primary"
48	prompt: the primary repro prompt
49	- name: "repro-variant"
50	prompt: optional variant prompt when useful
51	base_prompt: the shared child prompt below
52	```
53
54	Omit extra children when they would duplicate the same steps. Omit `model_id` unless the user requested a specific model.
55
56	## Shared child prompt
57
58	Give every child agent these shared instructions, then append the child-specific repro path or hypothesis.
59
60	```text
61	You are trying to reproduce a reported UI bug using Oz cloud computer use.
62
63	Goal:
64	- Reproduce the reported behavior as faithfully as possible.
65	- Capture screenshots before and after each meaningful interaction.
66	- If the provided steps are unclear or incomplete, use codebase and product knowledge to identify plausible app states that could produce the reported behavior, then test the assigned hypothesis.
67	- Report clear

People who liked this also viewed

6 picks

Type