Agent skill

Corgispec QA Exploratory

by ricoyudog in ricoyudog/Coding_Corgi_flow

SBTM-style exploratory testing session — charter-driven, tour-guided, time-boxed human investigation

MITAuto-check passedTesting & QA

Install Corgispec QA Exploratory

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

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

GitHub CLI
$ gh skill install ricoyudog/Coding_Corgi_flow corgispec-qa-exploratory --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-exploratory .claude/skills/corgispec-qa-exploratory && 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-exploratory
GitHub stars
104
Token cost
~1.5k tokens
SKILL.md length
606 words
Files
2
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

SBTM-style exploratory testing session — charter-driven, tour-guided, time-boxed human investigation

  • Works in 5 steps: Read the Charter → Select Tours (2–4) → Explore Systematically → …
  • Tasks that involve QA and bug reports
  • SKILL.md covers Overview, Session Structure (45–75…, The 12 Test Tours and Steps, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Corgispec QA Exploratory is an agent skill from ricoyudog/Coding_Corgi_flow. SBTM-style exploratory testing session — charter-driven, tour-guided, time-boxed human investigation

Its SKILL.md is about 1.5k 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: Universal. Works with any codebase or platform.

It sits in Testing & QA, covering QA and bug reports. The repository describes itself as: OpenSpec GitFlow — structured AI engineering workflows with issue tracking. The licence is MIT.

When your agent uses it

  • Tasks that involve QA and bug reports

Example prompts

  • “/corgispec-qa-exploratory”

Requirements

  • Compatibility (from SKILL.md): Universal. Works with any codebase or platform.

Workflow steps

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

  1. Read the Charter
  2. Select Tours (2–4)
  3. Explore Systematically
  4. Record Findings with Severity
  5. Assemble Debrief

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

    Universal. Works with any codebase or platform.

    From compatibility in the SKILL.md frontmatter.

Context cost

Corgispec QA Exploratory loads about 1.5k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 606 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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). 606 words, ~1,523 tokens.

Download SKILL.mdSave it as .claude/skills/corgispec-qa-exploratory/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
corgispec-qa-exploratory
description
SBTM-style exploratory testing session — charter-driven, tour-guided, time-boxed human investigation
compatibility
Universal. Works with any codebase or platform.
license
MIT
metadata.author
corgispec
metadata.version
1.0.0
metadata.generatedBy
1.0.0

Exploratory Testing — SBTM Session

Overview

Session-Based Test Management (SBTM), developed by James Bach and Michael Bolton, structures exploratory testing into accountable, time-boxed sessions. Each session has a charter (mission), uses one or more Test Tours to guide exploration, and produces a debrief report with findings and coverage notes.

Exploratory testing is simultaneous learning, test design, and test execution. It is not ad-hoc — it is disciplined investigation guided by heuristics and documented in real time.

Session Structure (45–75 minutes)

PhaseDurationActivity
Charter5 minDefine mission, scope, and success criteria
Explore30–55 minSystematic investigation using selected tours
NoteContinuousRecord observations, findings, questions as they occur
Debrief10–15 minSummarize coverage, findings, and next steps

The 12 Test Tours

Select 2–4 tours per session based on the change context.

#TourDescriptionWhen to Recommend
1Business DistrictExercise key business flows end-to-endAll changes — validates core value paths
2MoneyProbe revenue-related features (payments, subscriptions, pricing)Payment/billing changes
3Bad NeighborhoodFocus on historically buggy areasHistorically buggy modules
4HistoricalRevisit past bug clusters and regressionsLegacy code changes
5FedExTrack data as it flows through the entire systemFull-stack or integration changes
6Rained-OutExplore failure modes, error handling, edge casesAll changes — validates resilience
7Obsessive-CompulsiveRepeat operations rapidly, vary sequencesLoops, batch processing, concurrency
8Garbage CollectorTest cleanup, boundaries, limits, resource exhaustionCRUD operations, resource management
9IntellectualChallenge complex logic with tricky inputs and edge casesAlgorithms, business rules, calculations
10Couch PotatoTake the minimal effort path, use defaults onlyUX flows, onboarding, happy paths
11LandmarkNavigate via key features and integration pointsNew features, UI navigation
12MuseumExamine help docs, examples, error messages, tooltipsSDK, library, or API documentation

Steps

1. Read the Charter

If called from a molecule (e.g., corgispec-qa-session), read the charter provided. Otherwise, define your own charter:

  • Mission: What are you investigating?
  • Scope: Which areas/features are in-bounds?
  • Out of scope: What to explicitly avoid this session?
Show full SKILL.md (275 more words)Show less
2. Select Tours (2–4)

Choose 2 to 4 tours from the table above based on the change context. Different scenarios call for different Tour strategies:

  • Bug fix → apply Bad Neighborhood Tour + Historical Tour + Rained-Out Tour
  • New feature → apply Landmark Tour + Business District Tour + Couch Potato Tour
  • Refactor → apply FedEx Tour + Obsessive-Compulsive Tour + Intellectual Tour
  • Payment change → apply Money Tour + Rained-Out Tour + Business District Tour
  • Full-stack change → apply FedEx Tour + Business District Tour + Rained-Out Tour
  • CRUD/management → apply Garbage Collector Tour + Obsessive-Compulsive Tour + Museum Tour
3. Explore Systematically

For each selected tour:

  1. State which tour you are executing
  2. Identify specific test ideas within that tour's lens
  3. Execute tests, varying inputs and sequences
  4. Note observations immediately — do not defer
4. Record Findings with Severity

Classify each finding:

SeverityDefinition
BlockerPrevents core functionality, no workaround
CriticalMajor feature broken, workaround exists but unacceptable
MajorSignificant issue affecting user experience
MinorSmall defect, cosmetic, or low-impact behavioral issue
TrivialNitpick, suggestion, or style concern
5. Assemble Debrief

Compile the session report (see Reporting format below).

Reading qa-testcases.md

If the change directory contains qa-testcases.md, read it before starting exploration. Use the documented test cases as a baseline — your exploratory session extends beyond them, finding what structured cases miss.

Reporting Format

markdown
## Exploratory Test Session Report

- **Session ID**: ET-{YYYY-MM-DD}-{NNN}
- **Charter**: {mission statement}
- **Duration**: {actual minutes} / {planned minutes}
- **Tours Used**: {list of tours selected}

### Coverage

{Areas explored, features touched, paths taken}

### Findings

| # | Severity | Tour | Finding | Evidence |
|---|----------|------|---------|----------|
| 1 | major | FedEx | Data lost between step X and Y | screenshot/log ref |

### Oddities

{Things that aren't bugs but seem wrong, surprising, or worth investigating later}

### Debrief

- **Coverage confidence**: {low/medium/high} — {why}
- **Areas not reached**: {what was skipped and why}
- **Recommendations**: {follow-up sessions, automated tests to add, areas needing deeper review}

### Evidence

{Links to screenshots, logs, recordings, or reproduction steps}

When to Use

  • After code changes are applied and you need human-style investigation
  • When automated tests pass but confidence in quality is low
  • For areas with no existing test coverage
  • When a molecule skill requests exploratory QA

When NOT to Use

  • For writing automated test scripts (use TDD skill instead)
  • For test planning without execution (use qa-plan skill instead)
  • As a replacement for structured regression testing

© 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-exploratory of ricoyudog/Coding_Corgi_flow.

  • SKILL.md
  • skill.meta.json

Open the folder on GitHubat commit 461555c

Compare with similar skills

Corgispec QA Exploratory 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 Exploratory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Corgispec QA Exploratory this skillricoyudog/Coding_Corgi_flow104—~1.5kAutomated safety check: PassMIT
Reproduce Chat Statesdifferent-ai/openwork24k—~673Automated safety check: PassCustom licence
Dynamo Jira TicketDynamoDS/Dynamo2k—~1.1kAutomated safety check: PassApache-2.0
Moav E2EMotherofallVPNs/MoaV448—~1.9kAutomated safety check: NotesMIT
Creating A Coral TaskHuman-Agent-Society/CORAL1.1k—~2.2kAutomated safety check: PassApache-2.0
Launch Rlmarin-community/marin3.9k—~894Automated safety check: PassApache-2.0

Similar skills

  • Reproduce Chat States

    different-ai/openwork

    Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.

    24k GitHub stars~673 tokensUpdated today
    Testing & QAAuto-check passed
  • Dynamo Jira Ticket

    DynamoDS/Dynamo

    Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.

    2k GitHub stars~1.1k tokensUpdated today
    Testing & QAAuto-check passed
  • Moav E2E

    MotherofallVPNs/MoaV

    Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.

    448 GitHub stars~1.9k tokensUpdated 2 days ago
    Testing & QAAuto-check: notes
  • Creating A Coral Task

    Human-Agent-Society/CORAL

    Author a new CORAL task — the three pieces that must line up (task.yaml, seed/, a packaged grader/), the coral init → coral validate → smoke-test loop, and how to pick a grader pattern (stdout…

    1.1k GitHub stars~2.2k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Launch Rl

    marin-community/marin

    Define, validate, submit, or restart a Marin SkyRL experiment through its artifact main.

    3.9k GitHub stars~894 tokensUpdated today
    Testing & QAAuto-check passed
  • Actionbook Web Test

    actionbook/actionbook

    Run browser-based web tests against websites using Actionbook CLI.

    1.6k GitHub stars~9.7k tokensUpdated 1 mo ago
    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 Exploratory

What does Corgispec QA Exploratory do?

SBTM-style exploratory testing session — charter-driven, tour-guided, time-boxed human investigation. Corgispec QA Exploratory is an agent skill from ricoyudog/Coding_Corgi_flow.

When should I use Corgispec QA Exploratory?

Corgispec QA Exploratory fits situations like: tasks that involve QA and bug reports.

How do I install Corgispec QA Exploratory in Claude Code?

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

How do I install Corgispec QA Exploratory in Codex?

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

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

What does Corgispec QA Exploratory need to run?

SKILL.md names no scripts, command-line tools or credentials: Corgispec QA Exploratory is instructions for the agent only. Compatibility (from SKILL.md): Universal. Works with any codebase or platform..

Does Corgispec QA Exploratory 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 Exploratory 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 Exploratory use?

Corgispec QA Exploratory 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 Exploratory use?

About 1.5k tokens (SKILL.md is roughly 6.1k 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 Exploratory?

Skills that share tags, products or a category with Corgispec QA Exploratory: Reproduce Chat States (different-ai/openwork, 24k stars), Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars), Moav E2E (MotherofallVPNs/MoaV, 448 stars) and Creating A Coral Task (Human-Agent-Society/CORAL, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Corgispec QA Exploratory?

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.