Blind TDD gate: a fresh agent writes failing tests from the spec alone (path-guard hook blocks implementation reads), the implementer makes them pass, a blind runner verifies green, and an arbiter rules on challenges.
Plugin blind-tdd from marketplace themis in dscherm/themis. Commands read from the repo's manifest — 19 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
/blind-tdd:security-pack-setupInterview the operator to build a project-specific security AC pack (explores the repo first, drafts concrete criteria, installs via pack_wizard).
/blind-tdd:setupConfigure which tasks the blind-TDD gate engages on (writes themis.config.json routing).
blind-arbiterBlind TDD arbiter (Agent #3): rules upheld/rejected/ambiguous on a challenge to a blind test. No Bash, no Edit; Write scoped to the ruling file by the path guard.
blind-runnerBlind TDD test runner (Agent #2): executes the hash-locked tests and produces a verified green report. Bash restricted to test commands; Write scoped to the green report by the path guard; stays blind to implementation via the path-guard + bash-guard hooks.
blind-writerBlind TDD test writer (Agent #1): writes failing tests from a task's acceptance_criteria alone, before any implementation exists. Cannot read src/ (PreToolUse path-guard blocks it). No Bash.
python "${CLAUDE_PLUGIN_ROOT}/hooks/blind_tdd_path_guard.py"
python "${CLAUDE_PLUGIN_ROOT}/hooks/blind_tdd_bash_guard.py"
python "${CLAUDE_PLUGIN_ROOT}/hooks/blind_tdd_audit.py"
Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling
19 skills
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
1 command · 6 agents
Build, preview, and test UI components with Storybook.
7 skills
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Install the "AAS QA & Test Automation" editorial skill bundle for Claude Code.
14 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.