bootstrap-agent-identity
SolidConsistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who it is and what it was doing from evidence rather than memory. Use at the start of every new session, after a session interruption or crash, when agent behavior feels inconsistent with prior sessions, or when persistent memory and current context appear contradictory.
Install
Quality Score: 81/100
Skill Content
Details
- Author
- pjt222
- Repository
- pjt222/agent-almanac
- Created
- 1 years ago
- Last Updated
- today
- Language
- R
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
bootstrap
Initialize minimal AgentOps documentation and verdict storage without taking over repository workflow. Triggers: "bootstrap AgentOps", "initialize AgentOps docs".
new-project
Full project bootstrap - interviews the developer (name, description, stack, components), then scaffolds directory structure, CLAUDE.md, config files, hooks, skills, and first commit.
project-bootstrap
Bootstraps or standardizes the full AI-agent workspace for any project - analyzes the existing source first, then generates/reconciles the complete .claude folder (agents incl. orchestrator, rules, commands, hooks, skills, settings.json), the standardized docs tree (specs/requirements/architecture/tasks/context/templates), CLAUDE.md + AGENTS.md + README.md, and relevant skills - so the repo runs under orchestrator-driven task control. Use when the user asks to "set up base", "thiet lap base coding", "chuan hoa claude folder", "chuan hoa source thanh claude ready", "khoi tao workspace cho AI agents", or starts/adopts a project that should follow the standard structure.