Menu
Save important information, architectural decisions, patterns, or project knowledge to Cognis persistent memory.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Persistent memory and context for AI agents using Cognis by Lyzr. Use this skill when the user mentions "remember this", "what did I work on", "save this for later", "team knowledge", "project context", "recall", "memory", or needs long-term memory across sessions. Also use when the user asks about past decisions, preferences, or prior conversations. Supports personal memory (per-user), team memory (shared across repo contributors), semantic search, and automatic context assembly.
Persistent memory and context for AI agents using Cognis by Lyzr. Use this skill when the user mentions "remember this", "what did I work on", "save this for later", "team knowledge", "project context", "recall", "memory", or needs long-term memory across sessions. Also use when the user asks about past decisions, preferences, or prior conversations. Supports personal memory (per-user), team memory (shared across repo contributors), semantic search, and automatic context assembly.
Search your memory for past work, previous sessions, architectural decisions, and team knowledge stored in Cognis.
| name | cognis-save |
| description | Save important information, architectural decisions, patterns, or project knowledge to Cognis persistent memory. |
| version | 1.0.0 |
Use this skill when the user wants to preserve architectural decisions, important patterns, conventions, or project knowledge for future sessions.
Determine what the user wants to save.
Format the content clearly with context — include enough detail that the memory will be useful in future sessions.
Determine the scope:
save-project-memory.cjsadd-memory.cjsSave the memory using a bash command:
For personal memory:
node "${CLAUDE_PLUGIN_ROOT}/scripts/add-memory.cjs" "CONTENT HERE"
For team/project memory:
node "${CLAUDE_PLUGIN_ROOT}/scripts/save-project-memory.cjs" "CONTENT HERE"
For long content (over ~2000 chars), pipe via stdin instead:
echo "LONG CONTENT HERE" | node "${CLAUDE_PLUGIN_ROOT}/scripts/add-memory.cjs"
save-project-memory.cjs "We use JWT for authentication..."add-memory.cjs "User prefers tabs over spaces"save-project-memory.cjs "Payment API requires idempotency keys..."