reproduce-bug-report

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

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, well-structured orchestration skill with executable prompt templates, strong sequencing, and safety gating. It is slightly long for a single inlined file and repeats the screen-recording emphasis, but the guidance is highly actionable.

Suggestions

Consolidate the 'screen recording by default' guidance into one canonical statement to remove repetition across the goal, artifact-workflow, and reproduction-workflow sections.

Consider moving the large shared child prompt block and the three child-prompt patterns into a references/ file so SKILL.md reads as a concise overview that points one level deep to the prompt templates.

Tighten the version/app-setup section, which overlaps with the same version-matching instructions restated inside the shared child prompt's reproduction workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient instruction content that assumes Claude's competence, but the 'screen recording by default' emphasis recurs across the goal, artifact, and reproduction-workflow sections and could be tightened slightly.	4 / 5
Actionability	Provides copy-paste-ready templates — a concrete run_agents call shape, a full shared child prompt, three named child patterns (primary/variant/code-path), and a summary format — covering the common reproduction cases.	5 / 5
Workflow Clarity	Sequenced parent workflow (steps 1-6) and reproduction workflow (steps 1-11) with explicit feedback loops (test hypothesis if steps fail, at most two targeted variations, report blockers) plus a success-criteria checklist.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a clearly signaled one-level reference to the optional companion skill, but at ~190 lines all guidance is inlined in SKILL.md with no bundle files, so it is not a clean overview-pointing-to-details split.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and pairs them with an explicit, synonym-rich 'Use when' trigger. It cleanly answers what the skill does and when to invoke it with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Launch Oz cloud agents with computer use to reproduce', 'capture visual evidence (a screen recording by default)', 'report reproduction findings' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (launch agents, reproduce, capture evidence, report) and 'when' via a concrete 'Use when investigating a specific interactive or visual bug from an issue, ticket, support report, or prompt' clause.	5 / 5
Trigger Term Quality	Natural trigger terms 'bug', 'interactive or visual bug', 'issue, ticket, support report, or prompt' cover the synonyms a user would actually say when needing reproduction.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Oz cloud computer-use agents reproducing UI-focused bugs) with distinct triggers and minimal overlap risk against generic debugging skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: warpdotdev/common-skills
Path: .agents/skills/reproduce-bug-report/SKILL.md
Commit: 69b4753

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.