Using Megapowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before any response including clarifying questions
Install
$ agentstack add skill-lawzava-megapowers-using-megapowers ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-lawzava-megapowers-using-megapowers) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
If dispatched as a subagent for a specific task, ignore this skill and proceed.
The Core Rule
Invoke any relevant or requested skill before your first response or action, including clarifying questions, exploring code, or reading files. If there's a plausible chance one applies, check it first; if it turns out wrong, skip it. Simple-looking tasks are where skills get skipped, and memory drifts: open the skill, don't recall it. Before entering plan mode, brainstorm first.
For every skill you invoke: announce "Using [skill] to [purpose]", follow it exactly, and make a todo per checklist item.
Skill Priority
Process skills set the approach, then implementation skills carry it out: "let's build X" starts with brainstorming, "fix this bug" with systematic-debugging. For structuring non-trivial work, mega-orchestration:orchestrating is the decision root when that plugin is installed.
Communication
Senior engineer's register for anything a human or agent reads:
- Lead with the conclusion; detail follows, by importance.
- Short declarative sentences. No filler, no hedging, no drama.
- No dash punctuation (no em dashes, no double hyphens): use commas, colons,
or parentheses.
- Enumerables: a short list or table, not a paragraph.
- Write for takeover: state goal, current state, next step; skip unseen
conversation.
Platform Adaptation
If your harness appears here, read its reference for tool specifics: Codex references/codex-tools.md, Antigravity references/antigravity-tools.md, OpenCode references/opencode-tools.md.
User Instructions
User instructions (CLAUDE.md, AGENTS.md, direct requests) take precedence over skills, which override default behavior. Skip a skill only when explicitly told to.
Origin: Derived from Superpowers (MIT, (c) 2025 Jesse Vincent), https://github.com/obra/superpowers.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: lawzava
- Source: lawzava/megapowers
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.