Generate automated tests for completed software phases using UAT criteria.
Install
mkdir -p .claude/skills/gsd-add-tests-phorde && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14840" && unzip -o skill.zip -d .claude/skills/gsd-add-tests-phorde && rm skill.zipInstalls to .claude/skills/gsd-add-tests-phorde
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Generate tests for a completed phase based on UAT criteria and implementationKey capabilities
- →Generate unit tests for a completed phase
- →Generate E2E tests for a completed phase
- →Classify implementation files into TDD, E2E, or Skip categories
- →Present a test plan for user approval
- →Generate tests following RED-GREEN conventions
- →Commit generated test files with a specific message
How it works
The skill analyzes implementation files and uses SUMMARY.md, CONTEXT.md, and VERIFICATION.md as specifications to generate unit and E2E tests. It classifies files, presents a test plan for approval, and then generates tests.
Inputs & outputs
When to use gsd-add-tests
- →Generate feature tests
- →Verify UAT criteria
- →Create test code for implementation
About this skill
<codex_skill_adapter>
A. Skill Invocation
- This skill is invoked by mentioning
$gsd-add-tests. - Treat all user text after
$gsd-add-testsas{{GSD_ARGS}}. - If no arguments are present, treat
{{GSD_ARGS}}as empty.
B. AskUserQuestion → request_user_input Mapping
GSD workflows use AskUserQuestion (Claude Code syntax). Translate to Codex request_user_input:
Parameter mapping:
header→headerquestion→question- Options formatted as
"Label" — description→{label: "Label", description: "description"} - Generate
idfrom header: lowercase, replace spaces with underscores
Batched calls:
AskUserQuestion([q1, q2])→ singlerequest_user_inputwith multiple entries inquestions[]
Multi-select workaround:
- Codex has no
multiSelect. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.
Execute mode fallback:
- When
request_user_inputis rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.
C. Task() → spawn_agent Mapping
GSD workflows use Task(...) (Claude Code syntax). Translate to Codex collaboration tools:
Direct mapping:
Task(subagent_type="X", prompt="Y")→spawn_agent(agent_type="X", message="Y")Task(model="...")→ omit (Codex uses per-role config, not inline model selection)fork_context: falseby default — GSD agents load their own context via<files_to_read>blocks
Parallel fan-out:
- Spawn multiple agents → collect agent IDs →
wait(ids)for all to complete
Result parsing:
- Look for structured markers in agent output:
CHECKPOINT,PLAN COMPLETE,SUMMARY, etc. close_agent(id)after collecting results from each agent </codex_skill_adapter>
Analyzes implementation files, classifies them into TDD (unit), E2E (browser), or Skip categories, presents a test plan for user approval, then generates tests following RED-GREEN conventions.
Output: Test files committed with message test(phase-{N}): add unit and E2E tests from add-tests command
</objective>
<execution_context> @C:/ExtratorLaudos/.codex/get-shit-done/workflows/add-tests.md </execution_context>
<context> Phase: {{GSD_ARGS}}@.planning/STATE.md @.planning/ROADMAP.md </context>
<process> Execute the add-tests workflow from @C:/ExtratorLaudos/.codex/get-shit-done/workflows/add-tests.md end-to-end. Preserve all workflow gates (classification approval, test plan approval, RED-GREEN verification, gap reporting). </process>When not to use it
- →When the phase is not yet completed
- →When UAT criteria and implementation details are unavailable
Limitations
- →Requires a completed phase
- →Relies on SUMMARY.md, CONTEXT.md, and VERIFICATION.md for specifications
- →Requires user approval for the test plan
How it compares
This workflow automates test generation and commitment based on specific GSD phase documentation, unlike manual test creation.
Compared to similar skills
gsd-add-tests side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gsd-add-tests (this skill) | 0 | 3mo | No flags | Intermediate |
| dev | 2 | 6mo | Review | Advanced |
| overnight-development | 1 | 1mo | Review | Intermediate |
| nx-run-tasks | 1 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by phorde
View all by phorde →You might also like
dev
atopile
LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.
overnight-development
jeremylongshore
Automates software development overnight using git hooks to enforce test-driven Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
nx-run-tasks
nrwl
Helps with running tasks in an Nx workspace. USE WHEN the user wants to execute build, test, lint, serve, or run any other tasks defined in the workspace.
deepgram-ci-integration
jeremylongshore
Configure Deepgram CI/CD integration for automated testing and deployment. Use when setting up continuous integration pipelines, automated testing, or deployment workflows for Deepgram integrations. Trigger with phrases like "deepgram CI", "deepgram CD", "deepgram pipeline", "deepgram github actions", "deepgram automated testing".
ultraqa
Yeachan-Heo
QA cycling workflow - test, verify, fix, repeat until goal met
spec-driven-workflow
CafeSemCafeina
The build workflow for avaliador-tech-recruiter — risk-ordered tiers with a protected mock-mode floor, a Ready spec required before any unit is implemented, eval gates (L0 contract / L1 policy / L2 fixtures) as the merge filter, package partitioning for parallel agents, atomic Conventional Commits,