Web Application Testing
anthropics/skills
Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.
Backend logic walkthrough — traces call chain from real entry points, verifies data integrity across layers
Install Corgispec QA Backend
$ npx skills add ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ricoyudog/Coding_Corgi_flow corgispec-qa-backend --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/ricoyudog/Coding_Corgi_flow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/atoms/corgispec-qa-backend .claude/skills/corgispec-qa-backend && 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 "corgispec-qa-backend" agent skill from https://github.com/ricoyudog/Coding_Corgi_flow/tree/master/.claude/skills/atoms/corgispec-qa-backend into .claude/skills/corgispec-qa-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "corgispec-qa-backend", 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/ricoyudog/Coding_Corgi_flow/tree/master/.claude/skills/atoms/corgispec-qa-backendType 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 ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ricoyudog/Coding_Corgi_flow corgispec-qa-backend --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ricoyudog/Coding_Corgi_flow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/atoms/corgispec-qa-backend .agents/skills/corgispec-qa-backend && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "corgispec-qa-backend" agent skill from https://github.com/ricoyudog/Coding_Corgi_flow/tree/master/.claude/skills/atoms/corgispec-qa-backend into .agents/skills/corgispec-qa-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "corgispec-qa-backend", 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 ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ricoyudog/Coding_Corgi_flow corgispec-qa-backend --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ricoyudog/Coding_Corgi_flow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/atoms/corgispec-qa-backend .cursor/skills/corgispec-qa-backend && 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 "corgispec-qa-backend" agent skill from https://github.com/ricoyudog/Coding_Corgi_flow/tree/master/.claude/skills/atoms/corgispec-qa-backend into .cursor/skills/corgispec-qa-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "corgispec-qa-backend", 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/ricoyudog/Coding_Corgi_flow.git --path .claude/skills/atoms/corgispec-qa-backend--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 ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ricoyudog/Coding_Corgi_flow corgispec-qa-backend --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ricoyudog/Coding_Corgi_flow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/atoms/corgispec-qa-backend .gemini/skills/corgispec-qa-backend && 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 "corgispec-qa-backend" agent skill from https://github.com/ricoyudog/Coding_Corgi_flow/tree/master/.claude/skills/atoms/corgispec-qa-backend into .gemini/skills/corgispec-qa-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "corgispec-qa-backend", 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 ricoyudog/Coding_Corgi_flow corgispec-qa-backendInstalls 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 ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ricoyudog/Coding_Corgi_flow.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/atoms/corgispec-qa-backend .github/skills/corgispec-qa-backend && 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 "corgispec-qa-backend" agent skill from https://github.com/ricoyudog/Coding_Corgi_flow/tree/master/.claude/skills/atoms/corgispec-qa-backend into .github/skills/corgispec-qa-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "corgispec-qa-backend", 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 ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ricoyudog/Coding_Corgi_flow corgispec-qa-backend --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ricoyudog/Coding_Corgi_flow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/atoms/corgispec-qa-backend .opencode/skills/corgispec-qa-backend && 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 "corgispec-qa-backend" agent skill from https://github.com/ricoyudog/Coding_Corgi_flow/tree/master/.claude/skills/atoms/corgispec-qa-backend into .opencode/skills/corgispec-qa-backend/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "corgispec-qa-backend", 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
corgispec-qa-backend- GitHub stars
- 104
- Token cost
- ~1.6k tokens
- SKILL.md length
- 615 words
- Files
- 2
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- MIT
At a glance
Backend logic walkthrough — traces call chain from real entry points, verifies data integrity across layers
- Works in 6 steps: Identify the entry point → Trace the call chain (3-layer depth) → Verify the happy path → …
- Testing & QA work in your project
- SKILL.md covers Overview, When to Use, Preconditions and Walkthrough Procedure, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Corgispec QA Backend is an agent skill from ricoyudog/Coding_Corgi_flow. Backend logic walkthrough — traces call chain from real entry points, verifies data integrity across layers
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `skill.meta.json`). Compatibility notes: Requires a backend codebase with identifiable entry points (routes, handlers, commands).
It sits in Testing & QA. The repository describes itself as: OpenSpec GitFlow — structured AI engineering workflows with issue tracking. The licence is MIT.
When your agent uses it
- Testing & QA work in your project
Example prompts
- “/corgispec-qa-backend”
Requirements
- Compatibility (from SKILL.md): Requires a backend codebase with identifiable entry points (routes, handlers, commands).
Workflow steps
6 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 461555c. 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 (its code samples are markdown).
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.
Compatibility
Requires a backend codebase with identifiable entry points (routes, handlers, commands).
From compatibility in the SKILL.md frontmatter.
Context cost
Corgispec QA Backend loads about 1.6k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 615 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 ricoyudog/Coding_Corgi_flow at commit 461555c, republished under its MIT licence (© ricoyudog). 615 words, ~1,621 tokens.
Download SKILL.mdSave it as
.claude/skills/corgispec-qa-backend/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- corgispec-qa-backend
- description
- Backend logic walkthrough — traces call chain from real entry points, verifies data integrity across layers
- compatibility
- Requires a backend codebase with identifiable entry points (routes, handlers, commands).
- license
- MIT
- metadata.author
- corgispec
- metadata.version
- 1.0.0
- metadata.generatedBy
- 1.0.0
Backend logic walkthrough for QA verification.
Overview
This skill guides a structured walkthrough of backend logic by tracing the call chain from a real entry point (route handler, CLI command, event listener) down through service, repository, and data layers. It verifies data integrity, auth enforcement, and error handling at each layer.
When to Use
- Verifying a new or modified backend feature works correctly end-to-end
- QA review of a pull request's backend changes
- Investigating whether auth, validation, and error paths are complete
- Confirming DB read/write operations match expected behavior
Do not use this skill for frontend-only changes, infrastructure/CI changes, or pure refactors with no behavioral change.
Preconditions
- Target feature or endpoint is identified
- Codebase is accessible and readable
-
qa-testcases.mdexists in the change directory (if reporting results)
Walkthrough Procedure
1. Identify the entry point
Find the root function for the feature under test:
- Route handler (e.g.,
POST /api/users) - Event listener (e.g.,
onOrderCreated) - CLI command handler
- Scheduled job entry
Record: file path, function name, HTTP method + path (if applicable).
2. Trace the call chain (3-layer depth)
Walk through exactly 3 layers from the entry point:
| Layer | Typical Role | What to Record |
|---|---|---|
| L1 — Controller/Handler | Request parsing, input validation, auth check | Input shape, auth requirement, early returns |
| L2 — Service/Use-case | Business logic, orchestration | Transformations, conditional branches, side effects |
| L3 — Repository/Data | DB queries, external API calls | Query shape, write operations, return shape |
At each layer record:
- Function signature (params + return type)
- Input values that reach this layer (trace from caller)
- Return values passed back to caller
- Side effects (DB writes, events emitted, external calls)
3. Verify the happy path
Trace one successful request end-to-end:
- Construct a valid input at L1
- Follow the data through L2 transformations
- Confirm L3 performs the expected DB write/read
- Verify the response returned to the caller matches expected shape
Record: input → each layer's transformation → final output.
4. Verify one error path
Choose the most critical error scenario:
- Invalid input (400)
- Unauthorized access (401/403)
- Resource not found (404)
- Business rule violation (409/422)
Trace the error from point of detection back to the response:
- Where is the error detected? (which layer, which condition)
- How does it propagate? (thrown exception, error return, early return)
- What response does the caller receive? (status code, error body)
Show full SKILL.md (239 more words)Show less
5. Auth pyramid verification
Check auth enforcement at each level of the pyramid:
| Level | Check | Pass Criteria |
|---|---|---|
| Unauthenticated | No token/session | Returns 401 |
| Authenticated | Valid token, wrong role | Returns 403 (if role-gated) |
| Authorized | Valid token, correct role, wrong resource | Returns 403 or 404 |
| Admin | Admin token | Full access confirmed |
For each level, confirm the check happens BEFORE any business logic or DB access.
6. DB write/read verification
For every DB operation found in L3:
- Writes: Confirm the written shape matches the schema. Confirm no partial writes on error (transaction or rollback).
- Reads: Confirm query filters are correct (no over-fetching, no missing tenant/owner scoping).
- Ordering: If the operation is read-after-write in the same flow, confirm consistency.
Reading qa-testcases.md
If qa-testcases.md exists in the change directory, read it before starting the walkthrough. It contains pre-defined test scenarios that MUST be covered:
## Format of qa-testcases.md
### <Feature Name>
| ID | Scenario | Input | Expected | Priority |
|----|----------|-------|----------|----------|
| TC-001 | ... | ... | ... | P0 |Map each test case to a walkthrough path. After completing the walkthrough, report coverage:
- Which test cases were verified via trace
- Which test cases could NOT be verified (and why)
Reporting Format
After completing the walkthrough, produce a summary in this structure:
## QA Backend Walkthrough: <Feature Name>
### Entry Point
- **Path**: `<file>:<line>`
- **Function**: `<name>`
- **Route**: `<METHOD /path>` (if applicable)
### Call Chain
| Layer | File | Function | Input | Output | Side Effects |
|-------|------|----------|-------|--------|--------------|
| L1 | ... | ... | ... | ... | ... |
| L2 | ... | ... | ... | ... | ... |
| L3 | ... | ... | ... | ... | ... |
### Happy Path
- Input: ...
- Flow: L1 → L2 → L3
- DB Operation: ...
- Response: ...
- **Status: PASS / FAIL**
### Error Path (<which error>)
- Trigger: ...
- Detection point: L<n>, condition: ...
- Propagation: ...
- Response: status=<code>, body=...
- **Status: PASS / FAIL**
### Auth Pyramid
| Level | Tested | Result |
|-------|--------|--------|
| Unauthenticated | Yes/No | PASS/FAIL |
| Authenticated | Yes/No | PASS/FAIL |
| Authorized | Yes/No | PASS/FAIL |
| Admin | Yes/No | PASS/FAIL |
### DB Integrity
| Operation | Table | Verified | Notes |
|-----------|-------|----------|-------|
| INSERT | ... | Yes/No | ... |
| SELECT | ... | Yes/No | ... |
### Test Case Coverage (from qa-testcases.md)
| ID | Covered | Method | Notes |
|----|---------|--------|-------|
| TC-001 | Yes/No | Trace/Manual | ... |
### Verdict
- [ ] Happy path verified
- [ ] Error path verified
- [ ] Auth pyramid complete
- [ ] DB integrity confirmed
- **Overall: PASS / FAIL / PARTIAL**Tips
- If the codebase uses middleware for auth, trace through the middleware FIRST before entering the handler.
- For microservices, treat inter-service calls as an L3 boundary (record request/response shape).
- If you cannot reach 3 layers (e.g., thin handler directly calling DB), note the collapsed layers and verify what exists.
- Prefer reading actual code over documentation — docs may be stale.
© ricoyudog, MIT. 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 1 other file in .claude/skills/atoms/corgispec-qa-backend of ricoyudog/Coding_Corgi_flow.
- SKILL.md
- skill.meta.json
Open the folder on GitHubat commit 461555c
Compare with similar skills
Corgispec QA Backend 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 |
|---|---|---|---|---|---|---|
| Corgispec QA Backend this skillricoyudog/Coding_Corgi_flow | 104 | — | ~1.6k | Automated safety check: Pass | MIT | |
| 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 ricoyudog/Coding_Corgi_flow
All 18 skills in this repoCorgispec Propose
ricoyudog/Coding_Corgi_flow
Create or complete one RFC-first CorgiSpec planning package from an accepted unbound RFC Slice or a closed maintenance exemption.
Corgispec Update
ricoyudog/Coding_Corgi_flow
Reconcile an existing CorgiSpec planning package after intent, requirements, scenarios, design, or task sequencing changes.
Corgispec Ask
ricoyudog/Coding_Corgi_flow
Answer pending Obsidian questions from CorgiSpec Memory/Wiki with early-stop retrieval, source citations, and a strict file budget.
Corgispec Install
ricoyudog/Coding_Corgi_flow
A skill your agent uses when installing, updating, or verifying this repo's project-local Corgi GitFlow assets in a target project.
Corgispec Lint
ricoyudog/Coding_Corgi_flow
Validate CorgiSpec v4 Memory/Wiki structure, freshness, source integrity, delivery extraction, bridge drift, and legacy preservation.
Corgispec Rfc
ricoyudog/Coding_Corgi_flow
Guide a human-authored CorgiSpec RFC through isolated draft creation, validation, explicit interactive approval, merge effectiveness, collision renumbering, and amendments.
Related
Categories
Questions about Corgispec QA Backend
What does Corgispec QA Backend do?
Backend logic walkthrough — traces call chain from real entry points, verifies data integrity across layers. Corgispec QA Backend is an agent skill from ricoyudog/Coding_Corgi_flow.
When should I use Corgispec QA Backend?
Corgispec QA Backend fits situations like: testing & QA work in your project.
How do I install Corgispec QA Backend in Claude Code?
Run `npx skills add ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a claude-code`. Or copy the skill folder (.claude/skills/atoms/corgispec-qa-backend in ricoyudog/Coding_Corgi_flow) into .claude/skills/corgispec-qa-backend in your project. Claude Code loads it when a task matches its description.
How do I install Corgispec QA Backend in Codex?
Run `npx skills add ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a codex`. Or copy the skill folder (.claude/skills/atoms/corgispec-qa-backend in ricoyudog/Coding_Corgi_flow) into .agents/skills/corgispec-qa-backend in your project. Codex loads it when a task matches its description.
Can I use Corgispec QA Backend 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 ricoyudog/Coding_Corgi_flow --skill corgispec-qa-backend -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/corgispec-qa-backend, .gemini/skills/corgispec-qa-backend, .github/skills/corgispec-qa-backend and .opencode/skills/corgispec-qa-backend in your project.
What does Corgispec QA Backend need to run?
SKILL.md names no scripts, command-line tools or credentials: Corgispec QA Backend is instructions for the agent only. Compatibility (from SKILL.md): Requires a backend codebase with identifiable entry points (routes, handlers, commands)..
Does Corgispec QA Backend 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 Corgispec QA Backend 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 Corgispec QA Backend use?
Corgispec QA Backend is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Corgispec QA Backend use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Corgispec QA Backend?
Skills that share tags, products or a category with Corgispec QA Backend: 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 Corgispec QA Backend?
ricoyudog (a GitHub user) maintains it in ricoyudog/Coding_Corgi_flow, which has 104 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on August 19, 2026.
Source: ricoyudog/Coding_Corgi_flow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.