Plugin marketplace
Secure, resilient, rugged engineering skills — adversarial testing, structured planning, and production-grade software workflows.
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Review a UX flow, agentic handoff point, or delegation-boundary decision for agency risks and articulation barriers before implementation — advocating for the user's intent map, not the screen in front of you
1 skill · 1 agent
Tidy the files a PR or branch changed against its base, or all tracked source on the default branch or with whole-repo: autonomous coach-first Stage-B refactor by default (may change behavior), then SOLID tidy with no further behavior change. Opt out with solid-only / no-behavior-change / prune-comments-only. Tests document behavior, comments earn their place
1 skill
Rewrite a pull request's commits into a coherent release story that semantic-release can publish, without changing file contents
1 skill
Turn customer evidence into auditable personas, journeys, progression hypotheses, and product-strategy opportunity maps
1 skill
Turn feature requests, PRDs, and backlog issues into an EARS-format spec file or one new GitHub issue
1 skill
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
test-only fake GitHub MCP server
1 MCP server
Guide Go development with tests: smallest test first, start from public behavior, keep IO out of decision packages
1 skill
Author or revise durable agent-facing instruction prose so priority, rationale, and scope survive the edit
1 skill
Rewrite a GitHub issue into session-sized child issues, with dependencies only where work actually blocks
1 skill
Uncover test coverage gaps by applying semantic mutations to production TypeScript, Go, or Python code
1 skill
Turn a fuzzy or overly broad request into a concise task prompt fitted to the current model, agent harness, and effort level
1 skill
Convert approved specs, master plans, or GitHub epics into native GitHub Issue dependency graphs with sub-issues and blocking relationships
1 skill
Generate adversarial, negative, and chaos tests for TypeScript code — boundary conditions, fuzzing, injection scenarios
1 skill
Rigorously review, validate, and lint Agent Skills SKILL.md files for any agent platform
1 skill
Adversarially review feature specifications and implementation plans — expose gaps, contradictions, ambiguity before coding
1 skill
Draft, review, and derive tests from EARS requirements without inventing behavior — the canonical EARS contract other planning skills share
1 skill
Triage and analyze PR review comments — classify concerns, verify claims against actual code, evaluate trade-offs
1 skill
Shows how many plugins this repo ships, and links here.