Generate content with awareness of the agent's current reasoning state — goal analysis, situation context, character orientation. Like generate-note but informed by internal planner state.
Scanned 6/6/2026
Install via CLI
openskills install bdambrosio/Cognitive_workbench---
name: generate-reflective-note
type: python
description: "Generate content with awareness of the agent's current reasoning state — goal analysis, situation context, character orientation. Like generate-note but informed by internal planner state."
---
# generate-reflective-note
LLM-based content generation with access to the agent's internal reasoning state.
Like `generate-note`, but the LLM prompt includes the planner's Stage 1 context
(character orientation, goal analysis, tool selection, situation awareness) as
background, enabling state-aware or reflective generation.
## Input
- `prompt`: Generation instruction (required)
- `style`: `"code"` or `"text"` (optional, default: `"text"`)
- `target_tokens`: Integer (optional). Target output length in tokens. Overrides default max_tokens when provided via OUTPUT GUIDANCE.
## Output
Success (`status: "success"`):
- `value`: Generated content informed by agent state
Failure (`status: "failed"`):
- `reason`: Error description
## Behavior
- Automatically retrieves the planner's reasoning snapshot (if available)
- Includes it as `## Internal Reflective State` context in the LLM prompt
- The prompt is the actual query; the reflective state is background
- Falls back to regular generation if no planner state is available
## Planning Notes
- Use when the agent needs to generate content that reflects its current understanding,
orientation, or reasoning about the goal and situation
- Use `generate-note` for plain generation without agent state awareness
- Typical uses: self-assessments, progress reflections, situation reports,
agent-perspective summaries, epistemic status notes
## Examples
```json
{"type":"generate-reflective-note","prompt":"Assess your current understanding of the user's goals and any gaps","out":"$assessment"}
{"type":"generate-reflective-note","prompt":"What aspects of this task are you most uncertain about?","out":"$uncertainty"}
{"type":"generate-reflective-note","prompt":"Summarize what you know about the current situation from the agent's perspective","out":"$sitrep"}
```
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', ...
**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. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.