Persist an explicitly requested non-binding fact, observation, caveat, or small rationale in Haft project memory. Do not auto-persist ordinary reasoning.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add m0n0x41d/haft --skill h-note --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of H Note?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/m0n0x41d-h-note-haft)More formats (shields.io, HTML) on the badges page.
---
name: h-note
description: Persist an explicitly requested non-binding fact, observation, caveat, or small rationale in Haft project memory. Do not auto-persist ordinary reasoning.
---
# h-note — Save a lightweight fact
Use `haft_note` only when the operator asks to remember/save something or a
current Work supplies a concrete operator-named or agent-inferred receiving
use that needs an addressable fact. Keep observations atomic, state
why they matter, and anchor them to relevant artifacts and stable implementation
files. A note is not a choice, ProblemCard, evidence verdict, approval, or
WorkPlan.
Tool arguments and generated references are not proof that the operator asked
to persist. Use `task_context` only to correlate the saved fact with its
receiving task, not as an authority receipt. Set `valid_until` when the fact has
a known expiry or review boundary.
When the exact current concern is known, include `entity_ref` with
`ref_kind_id="U.EntityRef"` plus `bounded_context_ref`. Preserve the returned
`Haft.ProjectRecordRef` exactly for later typed relations; never derive a
record ID from the note artifact ID. Without exact concern basis, the note may
persist while typed projection remains underdetermined.
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.