Web Application Testing
anthropics/skills
Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.
Structured error recovery for failed or ineffective browser actions.
Install Recovery
$ npx skills add MigoXLab/webqa-agent --skill recovery -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MigoXLab/webqa-agent recovery --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MigoXLab/webqa-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/webqa_agent/executor/flash/skills/recovery .claude/skills/recovery && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "recovery" agent skill from https://github.com/MigoXLab/webqa-agent/tree/main/webqa_agent/executor/flash/skills/recovery into .claude/skills/recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recovery", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MigoXLab/webqa-agent/tree/main/webqa_agent/executor/flash/skills/recoveryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MigoXLab/webqa-agent --skill recovery -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MigoXLab/webqa-agent recovery --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MigoXLab/webqa-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/webqa_agent/executor/flash/skills/recovery .agents/skills/recovery && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "recovery" agent skill from https://github.com/MigoXLab/webqa-agent/tree/main/webqa_agent/executor/flash/skills/recovery into .agents/skills/recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recovery", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MigoXLab/webqa-agent --skill recovery -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MigoXLab/webqa-agent recovery --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MigoXLab/webqa-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/webqa_agent/executor/flash/skills/recovery .cursor/skills/recovery && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "recovery" agent skill from https://github.com/MigoXLab/webqa-agent/tree/main/webqa_agent/executor/flash/skills/recovery into .cursor/skills/recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recovery", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MigoXLab/webqa-agent.git --path webqa_agent/executor/flash/skills/recovery--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MigoXLab/webqa-agent --skill recovery -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MigoXLab/webqa-agent recovery --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MigoXLab/webqa-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/webqa_agent/executor/flash/skills/recovery .gemini/skills/recovery && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "recovery" agent skill from https://github.com/MigoXLab/webqa-agent/tree/main/webqa_agent/executor/flash/skills/recovery into .gemini/skills/recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recovery", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MigoXLab/webqa-agent recoveryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MigoXLab/webqa-agent --skill recovery -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MigoXLab/webqa-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/webqa_agent/executor/flash/skills/recovery .github/skills/recovery && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "recovery" agent skill from https://github.com/MigoXLab/webqa-agent/tree/main/webqa_agent/executor/flash/skills/recovery into .github/skills/recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recovery", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MigoXLab/webqa-agent --skill recovery -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MigoXLab/webqa-agent recovery --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MigoXLab/webqa-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/webqa_agent/executor/flash/skills/recovery .opencode/skills/recovery && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "recovery" agent skill from https://github.com/MigoXLab/webqa-agent/tree/main/webqa_agent/executor/flash/skills/recovery into .opencode/skills/recovery/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recovery", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
recovery- GitHub stars
- 232
- Token cost
- ~1.1k tokens
- SKILL.md length
- 534 words
- Files
- 4 (incl. references)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Structured error recovery for failed or ineffective browser actions.
- Works in 3 steps: OBSERVE → DIAGNOSE → RECOVER
- Testing & QA work in your project
- SKILL.md covers When to Use, Recovery Loop, Loop Control and Available References
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Recovery is an agent skill from MigoXLab/webqa-agent. Structured error recovery for failed or ineffective browser actions.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/error-taxonomy.md`, `references/recovery-strategies.md` and `references/verification-patterns.md`).
It sits in Testing & QA. The repository describes itself as: Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 网站自主评估测试 Agent，支持 GUI/CLI 一键完成性能、功能使用与交互体验的测试评估. The licence is Apache-2.0.
When your agent uses it
- Testing & QA work in your project
Example prompts
- “/recovery”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit aa156d4. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Recovery loads about 1.1k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 19 tokens; SKILL.md has 534 words of instructions outside code blocks.
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
Auto-check passed
The automated check found no risky patterns in SKILL.md.
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 MigoXLab/webqa-agent at commit aa156d4, republished under its Apache-2.0 licence (© MigoXLab). 534 words, ~1,098 tokens.
Download SKILL.mdSave it as
.claude/skills/recovery/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- recovery
- description
- Structured error recovery for failed or ineffective browser actions.
- when_to_use
- When a tool returns an error, an action produces no visible effect, or page state diverges from expectation.
Recovery Skill
Structured recovery for browser automation failures. Covers execution errors, semantic failures, state divergence, tool limitations, and environmental blockers.
When to Use
Load this skill when any of these occur:
- A tool returns an error (
is_errorin tool result). - A post-action screenshot shows no change or an unexpected change.
- A verification step (snapshot / verify) contradicts the expected state.
- An action succeeded but the effect is wrong (filled wrong field, clicked wrong element, upload didn't trigger, text truncated).
- An unexpected element blocks progress (modal, banner, CAPTCHA, cookie consent).
Recovery Loop
Follow three phases in order. Do not skip OBSERVE.
Step 1 — OBSERVE
Re-perceive the actual page state before making any recovery decision.
Batch these read-only tools in a single turn (the engine runs them concurrently):
take_snapshot— current DOM / accessibility tree.take_screenshot— current visual state.list_console_messages— JS errors that may explain the failure.list_network_requests— failed API calls or unexpected redirects.
Before / after comparison: Compare the current state against what the page looked like before the failed action. Ask:
- What changed? (anything at all — URL, DOM, visual layout)
- What should have changed but didn't?
- Are there new elements that weren't there before (modals, errors)?
Step 2 — DIAGNOSE
Classify the failure and assess progress.
Error classification — load the error-taxonomy reference for the
full list:
load_skill(skill_name="recovery", reference="error-taxonomy")
Key questions:
- Is this an execution error (tool reported failure) or a semantic error (tool succeeded but wrong effect)?
- Is the root cause a tool limitation, a wrong selector, a page state change, or an environmental blocker?
Progress assessment — did the action make any progress toward the goal?
- Partial progress (e.g. 3 of 5 fields filled): preserve what worked, recover only the failed part.
- Zero progress (nothing changed): the approach itself may be wrong; escalate sooner.
- Negative progress (broke something): undo if possible
(
evaluate_script({ code: "history.back()" })or navigate to the previous URL), then re-observe.
Show full SKILL.md (224 more words)Show less
Step 3 — RECOVER
Load the recovery-strategies reference for concrete playbooks:
load_skill(skill_name="recovery", reference="recovery-strategies")
Escalation ladder — try in order, move to the next level when the current one fails:
- Retry with modification — alternative selector, corrected input, adjusted timing.
- Alternative approach — different tool (e.g.
evaluate_scriptinstead of MCPfill), different interaction pattern. - Replan — fundamentally different path to the same goal (e.g. direct URL navigation when menu path is broken).
- Skip and record — preserve partial progress, log what failed and why, move to the next planned step.
After every recovery action, return to OBSERVE to verify the fix worked before continuing the plan.
Loop Control
- Per-step limit: max 2 recovery attempts on the same step before escalating to the next level.
- Cross-step pattern: same error pattern 3+ times across different steps → treat as systemic; skip and record.
- Replan depth: max 1 replan per original step. If the replanned approach also fails, skip.
- Fatal errors: never attempt recovery. Report and stop. Fatal types: PAGE_CRASHED, SESSION_EXPIRED, PERMISSION_DENIED, UNSUPPORTED_PAGE.
- After recovery: always continue the plan. One failed step does not end the entire task.
Available References
Load on demand: load_skill(skill_name="recovery", reference="<name>")
error-taxonomy— 9 error categories with identification traits, causes, and recovery guidancerecovery-strategies— concrete recovery playbooks with tool examples and escalation patternsverification-patterns— concrete verification examples with MCP tools (useful during OBSERVE phase for comprehensive state checks)
© MigoXLab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in webqa_agent/executor/flash/skills/recovery of MigoXLab/webqa-agent.
- SKILL.md
- references/error-taxonomy.md
- references/recovery-strategies.md
- references/verification-patterns.md
Open the folder on GitHubat commit aa156d4
Compare with similar skills
Recovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Recovery this skillMigoXLab/webqa-agent | 232 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Web Application Testinganthropics/skills | 180k | 51 repos | ~966 | Automated safety check: Pass | Apache-2.0 | |
| Diagnosing Bugsfossasia/eventyay-interpretation | 1.6k | 32 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| TDDpietheinstrengholt/rssmonster | 564 | 30 repos | ~906 | Automated safety check: Pass | MIT | |
| TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph | 112 | 11 repos | ~2.4k | Automated safety check: Pass | None | |
| TDDsanity-io/sanity | 6.4k | 20 repos | ~1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Diagnosing Bugs
fossasia/eventyay-interpretation
Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.
TDD
pietheinstrengholt/rssmonster
Test-driven development. An agent skill from pietheinstrengholt/rssmonster.
TDD Workflow
hellangleZ/burn-in-cceverywhere-ralph
A skill your agent uses when writing new features, fixing bugs, or refactoring code.
- Official
TDD
sanity-io/sanity
Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.
Context Driven Development
Ibrahim-3d/orchestrator-supaconductor
A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…
More from MigoXLab/webqa-agent
UI Audit
MigoXLab/webqa-agent
UI audit for hierarchy, accessibility, and UX. An agent skill from MigoXLab/webqa-agent.
Button Check
MigoXLab/webqa-agent
Traverse all interactive elements on the page — click clickables, fill inputs — and verify no errors.
Nuclei Scan
MigoXLab/webqa-agent
Run a Nuclei security scan against the target URL and report findings by severity.
Plan
MigoXLab/webqa-agent
Decompose a task into steps with completion checkpoints. An agent skill from MigoXLab/webqa-agent.
Webqa
MigoXLab/webqa-agent
Use WebQA to test websites, web pages, URLs, login flows, search flows, forms, navigation, and core user journeys with an AI browser QA agent.
Related
Categories
Questions about Recovery
What does Recovery do?
Structured error recovery for failed or ineffective browser actions. Recovery is an agent skill from MigoXLab/webqa-agent. Structured error recovery for failed or ineffective browser actions.
When should I use Recovery?
Recovery fits situations like: testing & QA work in your project.
How do I install Recovery in Claude Code?
Run `npx skills add MigoXLab/webqa-agent --skill recovery -a claude-code`. Or copy the skill folder (webqa_agent/executor/flash/skills/recovery in MigoXLab/webqa-agent) into .claude/skills/recovery in your project. Claude Code loads it when a task matches its description.
How do I install Recovery in Codex?
Run `npx skills add MigoXLab/webqa-agent --skill recovery -a codex`. Or copy the skill folder (webqa_agent/executor/flash/skills/recovery in MigoXLab/webqa-agent) into .agents/skills/recovery in your project. Codex loads it when a task matches its description.
Can I use Recovery in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MigoXLab/webqa-agent --skill recovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recovery, .gemini/skills/recovery, .github/skills/recovery and .opencode/skills/recovery in your project.
What does Recovery need to run?
SKILL.md names no scripts, command-line tools or credentials: Recovery is instructions for the agent only.
Does Recovery access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Recovery safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Recovery use?
Recovery is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Recovery use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.6k tokens, read only when the agent opens those files.
What are the alternatives to Recovery?
Skills that share tags, products or a category with Recovery: Web Application Testing (anthropics/skills, 180k stars), Diagnosing Bugs (fossasia/eventyay-interpretation, 1.6k stars), TDD (pietheinstrengholt/rssmonster, 564 stars) and TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Recovery?
MigoXLab (a GitHub organization) maintains it in MigoXLab/webqa-agent, which has 232 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on July 2, 2026.
Source: MigoXLab/webqa-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.