⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
setup-engineering-workflow
Sets up the engineering workflow's per-repo context — an `## Agent skills` block in AGENTS.md/CLAUDE.md plus `docs/agents/` — capturing this repo's issue tracker (GitHub, GitLab, Linear, ClickUp, or local markdown), triage label vocabulary, domain doc layout, and delivery mode (merge / pr / local), and recording the workflow skill map derived from the installed plugins. Interactive by default; has an unattended mode that writes detected defaults marked as unconfirmed. Run before first use of the engineering workflow or its skills (`to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, `zoom-out`), when the engineering workflow's Delivery phase needs a delivery mode, or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
lespaceman/skills
A collection of Agent Skills for QA test automation, browser-driven exploration, and engineering workflows. Each skill is a self-contained folder with a SKILL.md and any references it needs. They work in any agent that supports the Agent Skills format, including Claude Code, Codex, Cursor, and others supported by the skills CLI.
Install
npx skills add lespaceman/skills # choose skills interactively
npx skills add lespaceman/skills --skill drisp-browser # install one skill
npx skills add lespaceman/skills --list # list skills without installing
npx skills add lespaceman/skills -g # install for your user, not just this project
Skills that depend on an MCP server say so in their SKILL.md. npx skills add copies only the skill files, so install those MCP servers separately (see Requirements).
Skills
Browser and runtime
| Skill | What it does |
|---|---|
drisp-browser | Drive a real browser against a live site: navigate, click, fill forms, upload files, take screenshots, extract selectors. |
drisp-guide | Operate the drisp CLI: launch and debug workflow runs, read exit codes, and follow the tracker and Turn Protocol contract. |
Exploration and test planning
| Skill | What it does |
|---|---|
map-feature-scope | Break a broad feature into bounded sub-features before deep exploration. |
capture-feature-evidence | Explore a live feature and record grounded evidence for test planning. |
plan-test-coverage | Decide what coverage a feature needs and in what order, before writing specs. |
generate-test-cases | Write TC-ID test case specifications (not code) from exploration evidence. |
review-test-cases | Review TC-ID specs for gaps, duplication, and weak assertions before automation. |
Test intent charters
| Skill | What it does |
|---|---|
define-smoke-scope | Define the smallest high-signal smoke slice for a product, feature, or release. |
define-regression-scope | Define impact-based regression scope for a release, hotfix, or changed area. |
exploratory-test-writer | Write an exploratory testing charter: what to investigate, why, and which risks to probe. |
Playwright
| Skill | What it does |
|---|---|
add-playwright-tests | End-to-end entry point: analyze, write, review, and run Playwright tests for a feature. |
playwright-analyze-test-codebase | Report on an existing Playwright setup: config, fixtures, page objects, conventions. |
write-test-code | Write or refactor Playwright tests from TC-ID specs. |
playwright-review-test-code | Review Playwright test code for brittle selectors, bad waits, and missing teardown. |
playwright-fix-flaky-tests | Root-cause and fix flaky, failing, or timing-out Playwright tests. |
Robot Framework
| Skill | What it does |
|---|---|
add-robot-tests | End-to-end entry point: analyze, write, review, and run Robot Framework (Browser library) tests. |
robot-analyze-test-codebase | Report on an existing Robot setup and emit docs/qa/conventions.yaml. |
write-robot-code | Write or refactor .robot suites from TC-ID specs. |
robot-review-test-code | Review Robot test code before execution signoff. |
review-robot-best-practices | Review Robot Framework and Python automation code against best practices. |
robot-fix-flaky-tests | Root-cause and fix flaky, failing, or timing-out Robot tests. |
Engineering workflow
| Skill | What it does |
|---|---|
setup-engineering-workflow | Set up per-repo agent context: issue tracker, triage labels, domain docs, delivery mode. |
linear | Work with Linear issues, projects, and cycles with consistent workflow discipline. |
workflow-builder | Scaffold and review Athena workflow packages (workflow.md, workflow.json, plugin pins). |
How the testing skills fit together
The QA skills are layered. Each stage writes files under docs/qa/ that the next stage reads.
map-feature-scope → capture-feature-evidence explore the live product
↓
plan-test-coverage → generate-test-cases → review-test-cases plan
↓
add-playwright-tests or add-robot-tests implement, review, run
The intent charters (define-smoke-scope, define-regression-scope, exploratory-test-writer) decide what to test before that pipeline starts. Install the whole set for the full pipeline; installing only an execution skill leaves out the exploration and planning stages.
Requirements
| Needed by | Requirement |
|---|---|
drisp-browser, exploration skills, add-*-tests | Drisp Browser MCP server: claude mcp add drisp-browser -- npx @drisp/browser-mcp@latest |
linear | Linear MCP server registered as linear |
drisp-guide | The drisp CLI |
| Playwright skills | Node.js and @playwright/test in the target project |
| Robot skills | Python, Robot Framework, and robotframework-browser in the target project |
Related skills
setup-engineering-workflow maps a wider engineering workflow that also uses skills published elsewhere: planning and triage skills such as to-prd, to-issues, triage, tdd, and diagnose (by Matt Pocock, originally from mattpocock/skills), plus clickup, sentry, shadcn-ui, and frontend-design. Install them by name from lespaceman/athena-workflow-marketplace:
npx skills add lespaceman/athena-workflow-marketplace --skill to-prd
Repository layout
skills/
<skill-name>/
SKILL.md # required: frontmatter + instructions
references/ # optional: docs loaded on demand
scripts/ # optional: helper scripts
agents/ # optional: client-specific metadata (claude.yaml, openai.yaml)
Contributing
See CONTRIBUTING.md. Run scripts/validate.sh before opening a pull request.
License
// HOW IT'S BUILT
KEY FILES