Use when beginning any plan, audit, investigation, modification, review, test, or expensive tool action before the primary objective and completion conditions are explicit.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ihabkhaled/AI-Psychiatry --skill task-bootstrap --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Task Bootstrap?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-task-bootstrap)More formats (shields.io, HTML) on the badges page.
---
name: task-bootstrap
description: Use when beginning any plan, audit, investigation, modification, review, test, or expensive tool action before the primary objective and completion conditions are explicit.
---
# Task Bootstrap
## Core principle
Executive control loads before planning; planning without a locked objective can become the first overthinking loop.
## Procedure
1. Read applicable platform and repository instructions.
2. State the exact primary objective and observable success condition.
3. Define the minimum finite Definition of Done, included scope, and excluded scope.
4. Name the current blocker or none, one active work item, and the next deliverable.
5. Route only task-relevant context and inspect the smallest evidence needed.
6. Create a bounded executable plan and begin the first deliverable.
## Required output
Objective, success, DoD, scope, out-of-scope, blocker, active item, nesting depth, retry count, verification state, and next deliverable.
## Limits
WIP 1; start at nesting depth 0; no broad audit unless required by the objective.
## Common mistakes
Do not write a giant plan before bootstrap or convert implementation into a repository-wide audit.
## Stop condition
Stop bootstrap when the agent can name exactly what done means and the first evidence-producing action.
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!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
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', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.