Skip to content
Back to search

agentic-qe-preview-marketplace

MarketplaceWorks with Claude CodeGitHub

Agentic QE Preview: report-only Claude Code skills for test generation, project context, and failure triage.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/cognify-analytics--agentic-qe-preview/badge.svg)](/listings/cognify-analytics--agentic-qe-preview)

HTML

<a href="/listings/cognify-analytics--agentic-qe-preview"><img src="/api/listings/cognify-analytics--agentic-qe-preview/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

You need [Claude Code](https://code.claude.com) installed. Then, in a Claude Code session:

/plugin marketplace add Cognify-Analytics/Agentic-QE-Preview
/plugin install agentic-qe-preview@agentic-qe-preview-marketplace

Check it worked: type `/agentic-qe-preview:` and the four skills should be listed.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines
  1. {
  2. "name": "agentic-qe-preview-marketplace",
  3. "owner": {
  4. "name": "Cognify Analytics",
  5. "url": "https://github.com/Cognify-Analytics"
  6. },
  7. "description": "Agentic QE Preview: report-only Claude Code skills for test generation, project context, and failure triage.",
  8. "plugins": [
  9. {
  10. "name": "agentic-qe-preview",
  11. "source": "./",
  12. "description": "Report-only skills that write unit tests, document a codebase, run the tests, and triage failures.",
  13. "version": "0.1.0"
  14. }
  15. ]
  16. }
README.md · README · 128 lines
  1. # Agentic QE Preview
  2. Claude Code skills that write unit tests, document a codebase, run the
  3. tests, and decide what each failure means: a mistake in the test, or a real
  4. bug in the code. Everything runs on your machine inside Claude Code. It
  5. never pushes, merges, or writes to GitHub.
  6. This is the **report-only preview** of
  7. [Agentic QE](https://github.com/Cognify-Analytics/Agentic-QE). The full
  8. plugin adds filing issues and opening pull requests on GitHub, an opt-in
  9. bug-fix mode, follow-up on maintainers' replies, run history with cost
  10. tracking, and a GitHub Action that runs the pipeline on every pull request.
  11. ## Skills
  12. | Command | What it does |
  13. |---|---|
  14. | `/agentic-qe-preview:generate-tests [file or folder]` | Writes unit tests for a target, matching the repo's own conventions, runs them, and reports coverage |
  15. | `/agentic-qe-preview:build-context` | Builds or updates `.qa/context.md`, a living overview of the project: what it does, its data schema, architecture, test coverage, and the test tooling it needs |
  16. | `/agentic-qe-preview:triage-tests` | Runs the suite and classifies every failure as a bad test or a real bug. Fixes simple mistakes in tests the pipeline wrote, and drafts a GitHub issue for each suspected bug |
  17. | `/agentic-qe-preview:test-pipeline [file or folder]` | Runs generate-tests, build-context and triage-tests in sequence, checking each stage's output before the next one starts |
  18. With no target, `generate-tests` and `test-pipeline` rank the whole repo
  19. and pick what most needs tests.
  20. ## What it will and won't do
  21. - **Never changes production code.** If a test fails because the code is
  22. wrong, that is reported as a suspected bug, with the evidence, and left
  23. for a person to decide.
  24. - **Never edits a test a person wrote.** Only tests the pipeline itself
  25. generated (marked `generated_by_qa: true` in `.qa/test-inventory.json`)
  26. are ever fixed.
  27. - **Never edits manifests or build files.** If the repo is missing a test
  28. tool (a test runner, a coverage provider), the run says exactly what to
  29. install and skips what needs it.
  30. - **Drafts issues, doesn't file them.** Each suspected bug comes with a
  31. complete issue (title, evidence, code owners from `CODEOWNERS`) in the
  32. run's report. File the ones you agree with yourself.
  33. ## Supported languages
  34. The pipeline works out a repo's language and test setup from its manifest
  35. files and never assumes one. Every language gets the shared rules in
  36. `rules/general/`. Four languages also have their own rules:
  37. | Language | Test frameworks | Framework-specific rules | Coverage read from |
  38. |---|---|---|---|
  39. | Python | pytest | Web backends (FastAPI, Starlette, Flask, Django) | pytest-cov (Cobertura) |
  40. | JavaScript / TypeScript | Jest, Vitest, `node:test` | React, Next.js, Node backends (Express, Fastify, NestJS, Koa, Hono) | Cobertura or LCOV |
  41. | Java | JUnit 5 (JUnit 4 when that's all there is), AssertJ, Mockito | Spring Boot | JaCoCo (Maven, Gradle) |
  42. | Kotlin | JUnit 5, Kotest, MockK (or Mockito via mockito-kotlin), coroutines | Spring Boot | JaCoCo or Kover |
  43. Go, C#, Rust, Ruby, PHP, Elixir, Scala and Swift are detected and get the
  44. general rules, their default test location and their build commands, but
  45. no language-specific rules yet.
  46. To see what your repo needs, open section 5, "Test tooling requirements",
  47. of `.qa/context.md`. For each stack it lists every tool the pipeline needs,
  48. whether the repo has it, the version that fits, and a ready-to-paste
  49. install command.
  50. ## Install
  51. You need [Claude Code](https://code.claude.com) installed. Then, in a
  52. Claude Code session:
  53. ```
  54. /plugin marketplace add Cognify-Analytics/Agentic-QE-Preview
  55. /plugin install agentic-qe-preview@agentic-qe-preview-marketplace
  56. ```
  57. Check it worked: type `/agentic-qe-preview:` and the four skills should be
  58. listed.
  59. ## Run it
  60. From the root of the repo you want to test (it must be a git repo):
  61. ```
  62. /agentic-qe-preview:test-pipeline # whole repo
  63. /agentic-qe-preview:test-pipeline src/pricing.py # one target
  64. ```
  65. The skills don't pre-approve anything beyond reading files, so Claude Code
  66. asks before it writes a file or runs a command (your test command, `git`).
  67. Choose "always allow" for the ones you're happy with, or add them to your
  68. [permission settings](https://code.claude.com/docs/en/settings).
  69. ## What a run leaves behind
  70. | Path | What it is | Commit it? |
  71. |---|---|---|
  72. | `.qa/test-inventory.json` | Every module, its tests, coverage, and which tests the pipeline wrote | Yes |
  73. | `.qa/context.md` | The project overview from `build-context` | Yes |
  74. | The new and fixed test files | Wherever the repo keeps its tests | Yes, after you review them |
  75. | `.claude-pipeline/` | Scratch files for the current run, including the triage report with the drafted issues | No (added to `.gitignore` for you) |
  76. At the end of a run, the summary lists exactly which files to commit.
  77. ## Privacy
  78. Agentic QE Preview has no server of its own. Nothing is sent to Cognify
  79. Analytics, and Cognify does not receive or keep any of your data.
  80. **What it reads.** Your repository's source, tests, docs and build files,
  81. and its `CODEOWNERS` file, which can contain GitHub usernames, team names
  82. and email addresses.
  83. **What it stores, and where.** Only in your own repository: `.qa/` (the
  84. project context document and the test inventory), the test files it
  85. writes, and `.claude-pipeline/` (scratch files, git-ignored). The drafted
  86. issues in `.claude-pipeline/` can include owners named in `CODEOWNERS`.
  87. **What it sends, and to whom.** Nothing. The plugin makes no network
  88. requests of its own and never contacts GitHub. Running your test suite can
  89. contact whatever your tests or build tool reach (for example, a package
  90. registry while Maven or Gradle resolves dependencies).
  91. Claude reads your code while running the skills, as it does for any
  92. Claude Code session. That is covered by your agreement with Anthropic.
  93. ## License
  94. MIT. See [LICENSE](LICENSE). Use of the plugin is also covered by the
  95. [Terms of Service](TERMS.md).
  96. Support: [business@cogniify.ai](mailto:business@cogniify.ai)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.