v0.4.20

Name: claude-skills
Author: Jeffallan

Jeffallan/claude-skillsv0.4.20Oct 16, 2026by github-actions[bot]

Upgrading?

AI Summary

This release introduces a test-first workflow for the `execute-ticket` command, ensuring agents write failing tests before production code. It also resolves blocking issues in the plugin directory by replacing hardcoded values with angle-bracket placeholders across multiple skills.

Key Highlights

Test-first execution workflow for `execute-ticket` Phase 2 and Execution Checklist.
Agents now write failing tests (RED) for acceptance criteria before refactoring.
Replacement of 15 hardcoded value stand-ins with angle-bracket placeholders.
Updated documentation for workflow commands and execution steps.
Fixes blocking issues in `kubernetes-specialist` and other skill directories.

New Features

Test-first execution mode for ticket handling.
Stand-in check validators for tickets without code names.
Logging of RED results in completion summaries.

Full Release Notes


### Changed
- `execute-ticket`: Phase 2 and the Execution Checklist now run test-first. The agent writes a failing test for the ticket's acceptance criteria before touching production code, records that it fails for the reason the ticket describes (a test that passes early or fails for another reason is rewritten), makes it pass, then refactors with tests green. Tests live in the repo and run in CI; ad hoc scripts count only as extra evidence. Tickets with no code name a stand-in check (validator, grep, fixture run) and record its RED result too. The completion summary lists each test's RED result, and `docs/WORKFLOW_COMMANDS.md` and `docs/workflow/execution-execute-ticket.md` match the new order, closing #252

### Fixed
- Skill references: replaced 15 remaining value stand-ins with angle-bracket placeholders, since the Claude plugin directory still blocked `kubernetes-specialist/references/configuration.md` after 0.4.19. Covers SealedSecret ciphertext stubs in `kubernetes-specialist` (`<sealed-ciphertext>`), the dummy vLLM `api_key`, mock password encodings and hashes in `spring-boot-engineer` and `php-pro`, a mock Shopify webhook HMAC, base64 pagination cursors in `api-designer`, and a sample SHA-256 in `legacy-modernizer`. The detection regexes in `security-reviewer/references/secret-scanning.md` are unchanged

---

**Documentation:** https://jeffallan.github.io/claude-skills/

Related Repositories

public-apis/public-apis★ 491,193

A collective list of free APIs

NousResearch/hermes-agent★ 256,048

The agent that grows with you

yt-dlp/yt-dlp★ 200,218

A feature-rich command-line audio/video downloader

microsoft/markitdown★ 191,539

Python tool for converting files and office documents to Markdown.

Significant-Gravitas/AutoGPT★ 187,701

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.