New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Corgispec QA CLI

by ricoyudog in ricoyudog/Coding_Corgi_flow

CLI walkthrough — terminal-based verification of commands, flags, exit codes, pipes, and help output.

MITAuto-check passedTesting & QA

Install Corgispec QA CLI

skills CLI
$ npx skills add ricoyudog/Coding_Corgi_flow --skill corgispec-qa-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ricoyudog/Coding_Corgi_flow corgispec-qa-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ 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-cli .claude/skills/corgispec-qa-cli && rm -rf skills-src

Use ~/.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/

Facts

Skill name
corgispec-qa-cli
GitHub stars
104
Token cost
~1.9k tokens
SKILL.md length
667 words
Files
2
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

CLI walkthrough — terminal-based verification of commands, flags, exit codes, pipes, and help output.

  • Works in 10 steps: Discover commands and subcommands → Verify --help completeness → Read qa-testcases.md (if present) → …
  • Testing & QA work in your project
  • SKILL.md covers Overview, When to Use, Preconditions and Steps, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Corgispec QA CLI is an agent skill from ricoyudog/Coding_Corgi_flow. CLI walkthrough — terminal-based verification of commands, flags, exit codes, pipes, and help output.

Its SKILL.md is about 1.9k 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 terminal environment with Bash tool access.

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-cli”

Requirements

  • Compatibility (from SKILL.md): Requires a terminal environment with Bash tool access.

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Discover commands and subcommands
  2. Verify --help completeness
  3. Read qa-testcases.md (if present)
  4. Execute normal (happy path) scenarios
  5. Execute error scenarios
  6. Verify flag combinations
  7. Verify exit codes
  8. Verify environment variable overrides
  9. Verify pipe and redirect behavior
  10. Report results

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 bash).

    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 terminal environment with Bash tool access.

    From compatibility in the SKILL.md frontmatter.

Context cost

Corgispec QA CLI loads about 1.9k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 667 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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). 667 words, ~1,902 tokens.

Download SKILL.mdSave it as .claude/skills/corgispec-qa-cli/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
corgispec-qa-cli
description
CLI walkthrough — terminal-based verification of commands, flags, exit codes, pipes, and help output.
compatibility
Requires a terminal environment with Bash tool access.
license
MIT
metadata.author
corgispec
metadata.version
1.0
metadata.generatedBy
1.0.0

Terminal-based verification of CLI commands, subcommands, flags, exit codes, and help output.

Overview

This skill guides systematic QA walkthrough of a CLI tool. It covers:

  • Command and subcommand execution (happy path and error paths)
  • Flag combinations (required, optional, conflicting)
  • stdout/stderr recording and validation
  • --help completeness checks
  • Exit code verification
  • Environment variable overrides
  • Pipe and redirect behavior

Use this skill to verify that a CLI tool behaves correctly before release or after changes.

When to Use

  • After implementing or modifying CLI commands
  • Before releasing a CLI tool version
  • When verifying that documented behavior matches actual behavior
  • When a qa-testcases.md file exists and needs execution

Do not use this skill for API testing, UI testing, or non-terminal verification.

Preconditions

  • The CLI tool is installed or runnable in the current environment
  • Terminal/Bash access is available
  • (Optional) A qa-testcases.md file exists with test scenarios

Steps

1. Discover commands and subcommands

Run the CLI's top-level help to enumerate all available commands:

bash
<cli> --help

For each subcommand discovered, also run:

bash
<cli> <subcommand> --help

Record:

  • All commands and subcommands listed
  • Synopsis/usage line for each
  • Whether help output is complete (descriptions, flag docs, examples)
2. Verify --help completeness

For each command and subcommand, check that --help output includes:

ElementPresent?
Usage/synopsis line
Description
All flags documented
Required vs optional clearly marked
Default values shown
Examples section
Exit codes documented

Report any missing elements.

3. Read qa-testcases.md (if present)

If a qa-testcases.md file exists in the project (check docs/, tests/, or project root), read it to obtain structured test scenarios. Each scenario typically includes:

  • ID: Unique test case identifier
  • Command: The exact command to run
  • Input: Any stdin, files, or env vars required
  • Expected stdout: Pattern or exact match
  • Expected stderr: Pattern or exact match
  • Expected exit code: Numeric value
  • Tags: Categories (e.g., happy-path, error, edge-case)

Use these scenarios as the primary test plan. Execute them in order and record pass/fail for each.

4. Execute normal (happy path) scenarios

For each command, run it with valid inputs and verify:

  1. Exit code is 0 (or documented success code):

    bash
    <cli> <command> <valid-args>
echo "Exit code: $?"

  2. stdout contains expected output — capture and validate:

    bash
    <cli> <command> <valid-args> 2>/dev/null

  3. stderr is empty or contains only expected warnings:

    bash
    <cli> <command> <valid-args> >/dev/null

  4. Side effects occur — files created, state changed, etc.

5. Execute error scenarios

For each command, trigger known error conditions:

  1. Missing required flags:

    bash
    <cli> <command>  # omit required flags
echo "Exit code: $?"

    Expect: non-zero exit code, helpful error on stderr.

  2. Invalid flag values:

    bash
    <cli> <command> --flag=invalid-value
echo "Exit code: $?"

  3. Conflicting flags (if any documented):

    bash
    <cli> <command> --flag-a --flag-b  # mutually exclusive
echo "Exit code: $?"

  4. Unknown commands/flags:

    bash
    <cli> nonexistent-command
echo "Exit code: $?"

  5. Missing dependencies or prerequisites: Simulate missing files, unreachable services, etc.

Verify each error scenario produces:

  • A non-zero exit code (document which code)
  • A human-readable error message on stderr
  • No partial/corrupt output on stdout
Show full SKILL.md (237 more words)Show less
6. Verify flag combinations

Test flags in combination:

CombinationTypeExpected
All required flags onlyMinimal validSuccess
Required + each optional flagAdditiveSuccess with modified behavior
Short flags (-v) vs long flags (--verbose)EquivalenceSame behavior
Repeated flags (--flag --flag)DuplicationLast wins or error
Conflicting flagsMutual exclusionClear error message
Flag with = vs space separatorSyntaxBoth accepted
7. Verify exit codes

Document and verify all exit codes the CLI uses:

Exit CodeMeaningVerified?
0Success
1General error
2Usage/argument error
(others)(tool-specific)

Run scenarios that trigger each code and confirm with echo $?.

8. Verify environment variable overrides

If the CLI respects environment variables:

bash
# Test env var takes effect
ENV_VAR=value <cli> <command>

# Test env var vs flag precedence (flag should win)
ENV_VAR=env-value <cli> <command> --flag=flag-value

# Test unset env var uses default
unset ENV_VAR && <cli> <command>

Document which env vars are supported and their precedence relative to flags and config files.

9. Verify pipe and redirect behavior

Test that the CLI works correctly in pipelines:

bash
# stdout is pipeable
<cli> <command> | grep "pattern"

# stdin is accepted (if applicable)
echo "input" | <cli> <command>

# stderr separate from stdout
<cli> <command> > stdout.txt 2> stderr.txt

# Exit code propagates correctly in pipes
<cli> <command> | false
echo "${PIPESTATUS[0]}"

Check that:

  • Output is not corrupted when piped
  • Progress indicators / spinners are suppressed when stdout is not a TTY
  • Colors are disabled when not a TTY (or --no-color works)
10. Report results

Produce a summary in this format:

## CLI QA Walkthrough Report

**Tool**: <cli-name> <version>
**Date**: <today>
**Test cases**: N total, P passed, F failed, S skipped

### Results

| ID | Command | Expected | Actual | Status |
|----|---------|----------|--------|--------|
| 1 | `<cmd>` | exit 0, output "OK" | exit 0, output "OK" | PASS |
| 2 | `<cmd>` | exit 1, stderr error | exit 0, no error | FAIL |
| ... | ... | ... | ... | ... |

### Failures Detail

#### [ID] <brief description>
- **Command**: `<full command>`
- **Expected**: <what should happen>
- **Actual**: <what happened>
- **Severity**: critical / major / minor

### --help Completeness

| Command | Complete? | Missing |
|---------|-----------|---------|
| `<cmd>` | Yes | — |
| `<sub>` | No | Examples, exit codes |

### Environment Variables

| Variable | Documented? | Works? | Precedence correct? |
|----------|-------------|--------|---------------------|
| `VAR_X` | Yes | Yes | Yes |

### Summary

- **Overall**: PASS / FAIL
- **Blockers**: <count and brief list>
- **Recommendations**: <brief list>

Common Mistakes

  • Not capturing stderr separately from stdout (use 2> redirects)
  • Forgetting to check exit codes (always run echo $? after)
  • Testing only happy paths without error scenarios
  • Not verifying flag precedence over environment variables
  • Assuming TTY behavior when output is piped
  • Not testing with --help on every subcommand
  • Skipping conflicting flag combinations
  • Not recording the exact commands run (makes failures non-reproducible)

© 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-cli of ricoyudog/Coding_Corgi_flow.

  • SKILL.md
  • skill.meta.json

Open the folder on GitHubat commit 461555c

Compare with similar skills

Corgispec QA CLI 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.

Corgispec QA CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Corgispec QA CLI this skillricoyudog/Coding_Corgi_flow104—~1.9kAutomated safety check: PassMIT
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
Diagnosing Bugsfossasia/eventyay-interpretation1.6k32 repos~2.1kAutomated safety check: PassApache-2.0
TDDpietheinstrengholt/rssmonster56430 repos~906Automated safety check: PassMIT
TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph11211 repos~2.4kAutomated safety check: PassNone
TDDsanity-io/sanity6.4k20 repos~1kAutomated safety check: PassMIT

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed

  • Diagnosing Bugs

    fossasia/eventyay-interpretation

    Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 32 repos~2.1k tokens
    Testing & QAAuto-check passed

  • TDD

    pietheinstrengholt/rssmonster

    Test-driven development. An agent skill from pietheinstrengholt/rssmonster.

    564 GitHub starsUsed in 30 repos~906 tokens
    Testing & QAAuto-check passed

  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed

  • TDD

    sanity-io/sanity

    Official

    Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.

    6.4k GitHub starsUsed in 20 repos~1k tokens
    Testing & QAAuto-check passed

  • 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…

    380 GitHub starsUsed in 9 repos~2.9k tokens
    Testing & QAAuto-check passed

More from ricoyudog/Coding_Corgi_flow

All 18 skills in this repo

  • Corgispec 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.

    104 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Corgispec Update

    ricoyudog/Coding_Corgi_flow

    Reconcile an existing CorgiSpec planning package after intent, requirements, scenarios, design, or task sequencing changes.

    104 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

  • 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.

    104 GitHub stars~689 tokensUpdated 1 mo ago
    Auto-check passed

  • 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.

    104 GitHub stars~4.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Corgispec Lint

    ricoyudog/Coding_Corgi_flow

    Validate CorgiSpec v4 Memory/Wiki structure, freshness, source integrity, delivery extraction, bridge drift, and legacy preservation.

    104 GitHub stars~987 tokensUpdated 1 mo ago
    Auto-check passed

  • 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.

    104 GitHub stars~777 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Corgispec QA CLI

What does Corgispec QA CLI do?

CLI walkthrough — terminal-based verification of commands, flags, exit codes, pipes, and help output. Corgispec QA CLI is an agent skill from ricoyudog/Coding_Corgi_flow. CLI walkthrough — terminal-based verification of commands, flags, exit codes, pipes, and help output.

When should I use Corgispec QA CLI?

Corgispec QA CLI fits situations like: testing & QA work in your project.

How do I install Corgispec QA CLI in Claude Code?

Run `npx skills add ricoyudog/Coding_Corgi_flow --skill corgispec-qa-cli -a claude-code`. Or copy the skill folder (.claude/skills/atoms/corgispec-qa-cli in ricoyudog/Coding_Corgi_flow) into .claude/skills/corgispec-qa-cli in your project. Claude Code loads it when a task matches its description.

How do I install Corgispec QA CLI in Codex?

Run `npx skills add ricoyudog/Coding_Corgi_flow --skill corgispec-qa-cli -a codex`. Or copy the skill folder (.claude/skills/atoms/corgispec-qa-cli in ricoyudog/Coding_Corgi_flow) into .agents/skills/corgispec-qa-cli in your project. Codex loads it when a task matches its description.

Can I use Corgispec QA CLI 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-cli -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-cli, .gemini/skills/corgispec-qa-cli, .github/skills/corgispec-qa-cli and .opencode/skills/corgispec-qa-cli in your project.

What does Corgispec QA CLI need to run?

SKILL.md names no scripts, command-line tools or credentials: Corgispec QA CLI is instructions for the agent only. Compatibility (from SKILL.md): Requires a terminal environment with Bash tool access..

Does Corgispec QA CLI 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 CLI 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 CLI use?

Corgispec QA CLI 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 CLI use?

About 1.9k tokens (SKILL.md is roughly 7.6k 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 CLI?

Skills that share tags, products or a category with Corgispec QA CLI: 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 CLI?

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.