Invoke a user-authored skill; returns its full `SKILL.md` body for the next model request to follow. Skills are listed in the system prompt under `# Skills`, each with a trigger description. - `skill` -- name from the `# Skills` list. - `args` -- optional text forwarded to the skill. When a skill matches the request or current direction of work, invoke it before answering or taking other actions. Don't re-invoke a skill whose instructions are already active in the conversation.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add rekursiv-ai/sagent --skill default --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Default?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/rekursiv-ai-default)More formats (shields.io, HTML) on the badges page.
Invoke a user-authored skill; returns its full `SKILL.md` body for the next model request to follow.
Skills are listed in the system prompt under `# Skills`, each with a trigger description.
- `skill` -- name from the `# Skills` list.
- `args` -- optional text forwarded to the skill.
When a skill matches the request or current direction of work, invoke it before answering or taking other actions. Don't re-invoke a skill whose instructions are already active in the conversation.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
