beer-sakthai/sak-family-agent/sakjules-superpowers

Claude Code and agent skill by beer-sakthai/sak-family-agent

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Superpowers development methodology: plan execution, subagent-driven-development, and programmatic verification (TDD).

Install

npx vskill@latest install beer-sakthai/sak-family-agent/sakjules-superpowers

SKILL.md

Superpowers Workflow

Use this skill when executing complex multi-step features or implementing an existing PLAN.md or .hermes/plans/*.md file.

1. Core Strategies

A. Subagent-Driven Development (Recommended)

Use this strategy for highly interactive, task-by-task execution where user oversight and feedback are valuable:

  1. Isolate the task: Take a single bite-sized task from the plan (typically 2-5 minutes of work).
  2. Spawn a subagent: Use the invoke_subagent tool with the self model to run the specific task in a clean branch or inherit context.
  3. Task Prompt: Write a precise task description including target file paths, expected changes, and verification commands.
  4. Review: Once the subagent reports completion, verify the output (tests, diff, linter) before marking the task complete in PLAN.md.
B. Plan Execution (Batch)

Use this strategy for highly autonomous execution of a sequential task plan:

  1. State Tracking: Keep track of progress directly in PLAN.md using the checkboxes (- [ ] -> - [/] -> - [x] YYYY-MM-DD).
  2. Batch Run: Sequentially execute the tasks, running tests and verification commands after every code edit.
  3. Commit often: Make a clean git commit after each task passes verification.

2. Objective Verification & TDD

Never rely on self-certification. You must prove code correctness:

  1. Write/Update Tests First: When implementing or fixing code, add or modify a test in tests/ that reproduces the behavior/failure.
  2. Run and Verify Failure: Execute the test command and verify it fails as expected.
  3. Implement Fix: Write the minimal code required to pass the test.
  4. Run and Verify Pass: Confirm the test suite runs and passes cleanly.
  5. Run Lint and Security Checks: Execute Ruff formatting and Bandit security scans to ensure codebase hygiene before committing.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
1
Repository forks
1
7-day trend score
8

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/beer-sakthai/sak-family-agent/sakjules-superpowers/badge)](https://verified-skill.com/skills/beer-sakthai/sak-family-agent/sakjules-superpowers)

Something wrong with this skill or its page? Tell us.