anyoneanderson/agent-skills

1

spec-generator Specification Generator — Generate project requirements, design documents, and task lists. A skill for generating st…

anyoneanderson/agent-skills

57

2

spec-to-issue Create GitHub Issue from spec documents — Auto-generate structured Feature Issues from specifications. Analyzes spec…

anyoneanderson/agent-skills

45

3

spec-implement Specification-driven implementation orchestrator — Coordinate spec-code, spec-review, and spec-test to implement from…

anyoneanderson/agent-skills

44

4

spec-inspect Specification quality checker for spec-generator documents. Validates requirement.md, design.md, tasks.md for consis…

anyoneanderson/agent-skills

41

5

spec-workflow-init Development workflow generator — Generate issue-to-pr-workflow.md for your project. Creates a project-specific devel…

anyoneanderson/agent-skills

39

6

spec-rules-init Coding rules generator — Extract and generate coding-rules.md from project conventions. Scans CLAUDE.md, AGENTS.md, …

anyoneanderson/agent-skills

35

7

cmux-fork Fork the current Claude Code conversation into a new cmux pane or workspace. Default: split right. Supports down and …

anyoneanderson/agent-skills

28

8

cmux-delegate Delegate a task to another AI agent in a separate cmux pane or workspace. Supports Claude Code, Codex, Gemini CLI, an…

anyoneanderson/agent-skills

26

9

cmux-second-opinion Get a second opinion on code or specifications from a different AI agent via cmux. Default reviewer: Codex (or Claude…

anyoneanderson/agent-skills

26

10

handover Create, install, inspect, and boot from local session handover files for AI agent continuity. Writes structured hand…

anyoneanderson/agent-skills

25

11

mcp-convert MCP config converter for agent CLIs. Converts Claude Code MCP settings into Codex CLI MCP configuration, copying env…

anyoneanderson/agent-skills

24

12

skill-suggest Auto-detect project tech stack and suggest optimal skills from skills.sh registry. Analyzes manifest files (package.…

anyoneanderson/agent-skills

21

13

spec-code Implement a single task from spec documents autonomously. Reads requirement.md, design.md, and tasks.md to understan…

anyoneanderson/agent-skills

21

14

spec-review Structured code review against review_rules.md and coding-rules.md. Performs rule-by-rule, file-by-file matrix revie…

anyoneanderson/agent-skills

21

15

spec-test Create and run tests for a spec task implementation. Reads task completion criteria from tasks.md, detects existing …

anyoneanderson/agent-skills

21

16

harness-init Install a Harness Engineering control loop into the current project. Hears environment settings once, then generates …

anyoneanderson/agent-skills

16

17

harness-loop Run the GAN control loop for one epic: for each sprint, negotiate the contract, iterate Generator ⇄ Evaluator to rubr…

anyoneanderson/agent-skills

16

18

harness-plan Plan an epic for /harness: draft product-spec.md interactively, derive roadmap.md with sprint decomposition and bundl…

anyoneanderson/agent-skills

16

19

spec-evaluate Run a black-box acceptance test plan (test.md) against a finished implementation and produce a structured pass/fail r…

anyoneanderson/agent-skills

15

20

agent-delegate Delegate a task to, or get an adversarial review from, the other AI agent (Codex from Claude Code, or Claude Code fro…

anyoneanderson/agent-skills

14

21

spec-orchestrate End-to-end pipeline orchestrator — drive a GitHub Issue or a human request from specification through adversarial rev…

anyoneanderson/agent-skills

14

22

spec-writing Write and revise requirements, designs, task plans, and test plans with concrete process descriptions, traceable reas…

anyoneanderson/agent-skills

7

23

magi Put a hard question to three independent LLM CLIs from different vendors and return a tallied verdict (decision mode)…

anyoneanderson/agent-skills

6

24

ja-humanizer Write, rewrite and check Japanese prose so it reads like the writer, not a language model. Removes Japanese-specific …

anyoneanderson/agent-skills

2