Use when the user wants to "fill in this letter for each person", "mail merge", "generate letters for this list", "turn this filled letter into a template", or hands over a template plus a list. Bulk-fills ONE master template — a Word (.docx) letter/form or an Excel (.xlsx) form — from a data table, one filled file per row (mail-merge); or the reverse: extract a reusable tokenised .docx template + data-table skeleton from a filled example document, confirm the mapping, then fill. Reads the master, proposes a TOKENISED version (varying parts become {{tokens}}), confirms the mapping, then regenerates one output per data row, preserving the master's layout exactly. Data is an .xlsx or .csv (one row per output); outputs are one named file per record. Never invents: a token with no data is a VISIBLE flag, never a silent blank. Runs fully local and generates files only — it does not send, post or sign. Extract is .docx only this round (not .xlsx). Not a substitute for a hand-crafted single letter.

Use when input token spend needs explaining and fixing.

Use when an article or media piece needs rhetorical or technique-focused analysis — detects rhetorical tools (loaded language, cherry-picking, source selection bias, framing, omission, emotional appeals, false balance) in articles and produces a structured analysis report. Identifies specific techniques without labeling political positions.

Use when communicating, deciding, or reporting as a senior operator — 8 behavioral modules from Anthropic's Fable prompting guide. Not capability — pure behavior. Load for user-facing text quality.

Use when a converted PDF→EPUB misclassifies lines or covers, e.g. 'footnote links broken', 'page numbers became endnotes', 'cover came out as texture fragment', 'chapter headings resolve to wrong pages', 'endnote links dangle'. Calibration threshold rules for the pdf2epub pipeline: folio/fnref/footnote classification, endnote-section books, caption handling, front-matter language.

Pattern for standalone RAG indexes that live inside a skill directory — portable, no external DB or MCP dependency.

Use when a recurring cross-session digest should be produced and delivered via Hermes cron — aggregates session activity, cron job outputs, memory changes, and tool usage stats into a compact summary for delivery via messaging platforms. Surfaces outstanding tasks and cross-session context that's invisible on chat platforms.

Use when tracking upstream drift and syncing adapted skill libraries.

BM25-based skill retrieval plugin for Hermes Agent. Replaces the full skill list in the system prompt with a names-only compact view (~2K tokens) and injects top-K relevant skill descriptions per turn via BM25 retrieval (~300 tokens). Saves ~9K tokens/turn. Use when system prompt token overhead from skills is a concern, or when skill discovery quality matters.

Use when the user says "brief this task", "scope this properly", "what do you need from me", "improve my prompt", "help me get better output", or hands over a SUBSTANTIAL task — multi-step, multi-document, or a deliverable someone else will read — as a thin one-line request. Compile a task brief BEFORE starting substantial work — pin down the goal (what "done" looks like), context, constraints (standing rules included automatically), and tooling — confirm with the user, then execute against it. Asks at most 2-3 clarifying questions, only where the answer would change the output; otherwise states assumptions in the brief and proceeds. Not for quick one-step asks — answer those directly.