{"id":34979217,"url":"https://github.com/ali5ter/claude-cli-ux-skill","last_synced_at":"2026-04-14T06:32:40.340Z","repository":{"id":329821947,"uuid":"1120221652","full_name":"ali5ter/claude-cli-ux-skill","owner":"ali5ter","description":"🔬 Expert UX testing skill for CLIs and developer tools. Automatically evaluates command-line interfaces for usability, accessibility, and developer experience in Claude Code.","archived":false,"fork":false,"pushed_at":"2026-04-03T19:11:42.000Z","size":123,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-03T21:04:41.664Z","etag":null,"topics":["accessibility","api-design","claude-code","claude-skill","cli","cli-testing","command-line","developer-experience","developer-productivity","developer-tools","terminal","testing","usability","ux"],"latest_commit_sha":null,"homepage":"","language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ali5ter.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-20T18:33:39.000Z","updated_at":"2026-04-03T19:11:38.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ali5ter/claude-cli-ux-skill","commit_stats":null,"previous_names":["ali5ter/claude-cli-ux-skill"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/ali5ter/claude-cli-ux-skill","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ali5ter%2Fclaude-cli-ux-skill","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ali5ter%2Fclaude-cli-ux-skill/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ali5ter%2Fclaude-cli-ux-skill/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ali5ter%2Fclaude-cli-ux-skill/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ali5ter","download_url":"https://codeload.github.com/ali5ter/claude-cli-ux-skill/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ali5ter%2Fclaude-cli-ux-skill/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31785552,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T02:24:21.117Z","status":"ssl_error","status_checked_at":"2026-04-14T02:24:20.627Z","response_time":153,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["accessibility","api-design","claude-code","claude-skill","cli","cli-testing","command-line","developer-experience","developer-productivity","developer-tools","terminal","testing","usability","ux"],"created_at":"2025-12-27T00:51:45.622Z","updated_at":"2026-04-14T06:32:40.333Z","avatar_url":"https://github.com/ali5ter.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CLI UX Tester\n\nA Claude Code plugin that provides expert UX evaluation for command-line interfaces, developer tools, and APIs.\nInstall via the Claude Code plugin system (`/plugin install cli-ux-tester@ali5ter`).\n\n## Features\n\n- 11-criteria UX framework with 1-5 scoring per dimension (8 core + 3 extended criteria)\n- Active testing by executing real commands and capturing output\n- Parallel evaluation agents for thorough, unbiased analysis\n- Persistent memory across evaluations for cross-project pattern tracking\n- Comprehensive output artifacts: evaluation report, remediation plan, metrics, and test scripts\n- Language-agnostic: evaluates user-facing behavior regardless of implementation\n\n## Repository structure\n\n```text\nagents/\n  cli-ux-tester.md                 # Agent definition — synthesizes results into scored artifacts\nskills/\n  cli-ux-tester/\n    SKILL.md                       # Skill — detects CLI, spawns evaluation agents, invokes synthesizer\n    testing-checklist.md           # Comprehensive testing checklist (11 criteria)\n    test-scenarios.md              # Common CLI testing scenarios\n    scripts/\n      example-test.sh              # Template for automated testing\n.claude-plugin/\n  plugin.json                      # Plugin manifest\nmigrate                            # Migration script for v1.x and v2.x users\nREADME.md\nLICENSE\n```\n\n## Install\n\nInside Claude Code, run:\n\n```text\n/plugin marketplace add ali5ter/claude-plugins\n/plugin install cli-ux-tester@ali5ter\n```\n\n## Migrating from v1.x or v2.x\n\nIf you previously installed via `./install.sh` or an earlier version of this plugin, run the migration script:\n\n```bash\n./migrate\n```\n\nThen reinstall via the plugin commands above.\n\n## Usage\n\nAfter installation, ask Claude to evaluate any CLI in your session:\n\n```text\nReview this CLI for UX issues\nTest the error messages in this tool\nCheck if this API is developer-friendly\nEvaluate the help system\n```\n\nThe skill detects which CLI to evaluate from the current directory or your message, then runs the evaluation\nautomatically.\n\n### What gets evaluated\n\nThe plugin applies an 11-criteria framework, rating each dimension 1–5 with specific evidence:\n\n**Core criteria (1–8):**\n\n1. **Discovery \u0026 Discoverability** — Can users find features?\n2. **Command \u0026 API Naming** — Are names intuitive and consistent?\n3. **Error Handling \u0026 Messages** — Are errors clear and actionable?\n4. **Help System \u0026 Documentation** — Is help comprehensive and accessible?\n5. **Consistency \u0026 Patterns** — Do similar operations follow patterns?\n6. **Visual Design \u0026 Output** — Is output readable and well-formatted?\n7. **Performance \u0026 Responsiveness** — Does the CLI feel fast?\n8. **Accessibility \u0026 Inclusivity** — Can diverse developers use it?\n\n**Extended criteria (9–11):**\n\n1. **Integration \u0026 Interoperability** — Does it compose with shell pipelines and standard tools?\n2. **Security \u0026 Safety** — Are destructive operations guarded and credentials handled safely?\n3. **User Guidance \u0026 Onboarding** — Does it guide new users toward their first success?\n\n### Output artifacts\n\nAll results go into a timestamped directory in the evaluated project:\n\n```text\nCLI_UX_EVALUATION_\u003cYYYYMMDD_HHMMSS\u003e/\n├── EVALUATION.md          # Full report with scores and evidence\n├── REMEDIATION_PLAN.md    # Prioritized action items with effort estimates\n├── metrics.json           # Machine-readable scores for tracking over time\n└── test.sh                # Automated regression test script\n```\n\nClean up with: `rm -rf CLI_UX_EVALUATION_*/`\n\n### Scope\n\n**In scope (UX/DX):**\n\n- User-facing behavior: help text, error messages, output formatting\n- Developer experience: discoverability, learnability, consistency\n- Accessibility and inclusivity\n- Exit codes and signal handling as they affect UX\n\n**Out of scope (code quality):**\n\n- Internal code architecture or style\n- Language-specific best practices unrelated to UX\n- Performance internals (though responsiveness is evaluated)\n\n## How it works\n\nThe plugin provides two components:\n\n- **Skill** (`cli-ux-tester`) — detects the target CLI, asks clarifying questions if needed, spawns three\n  evaluation agents in parallel (an Explore agent for codebase mapping and two test agents for help/discovery\n  and error handling), then passes all collected results to the synthesizer agent\n- **Agent** (`cli-ux-tester:cli-ux-tester`) — receives pre-collected test data and synthesizes it into a\n  scored 11-criteria evaluation, producing all four output artifacts\n\nThe skill handles parallel evaluation directly because the platform does not support sub-agents spawning\nfurther sub-agents. The agent runs in `acceptEdits` permission mode to auto-approve artifact writes, and\nuses persistent `user`-scoped memory to accumulate cross-evaluation patterns over time.\n\n## Safety and quality notes\n\n- The evaluation agents execute commands in the current directory to observe real behavior.\n- All generated files use a timestamped directory for easy cleanup.\n- The synthesizer agent uses `permissionMode: acceptEdits` — file writes are auto-approved, but `Bash`\n  commands still prompt for permission.\n\n## License\n\nMIT License, Copyright (c) 2026 Alister Lewis-Bowen.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fali5ter%2Fclaude-cli-ux-skill","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fali5ter%2Fclaude-cli-ux-skill","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fali5ter%2Fclaude-cli-ux-skill/lists"}