cpuchip

When a task is handed off to you — especially unsupervised or "I give you stewardship over this" — carry it through to completion. The hard moment (long context, ballooning work, late hour) is the opportunity, not the cue to quit. Don't beg off — you have durable externalized memory; compact and continue. A handoff weighs more than a normal task. Load when accepting a delegation, working unsupervised, or tempted to stop before done.

Design and write antagonists with motivation that makes sense from the inside. Politics, ideology, ambition, wound — never 'evil for evil's sake.' Load when designing villains, faction antagonists, or morally complicated NPCs.

Quick intent articulation discipline before starting a new task. Names purpose, beneficiary, success criteria, and non-goals upfront so the agent has a target to optimize for when instructions run out. Klarna-failure prevention. Load before any non-trivial new task.

Automate browser interactions, test web pages and work with Playwright tests.

Open a location or moment by painting it through the senses so it becomes immersive and real. Load when narrating a new scene, room, or environment.

Shape a session or arc so each beat causes the next and the character returns changed. Load when planning a session arc, a campaign, or any multi-beat story.

Ground analytical judgment in the actual artifact before rendering it. Load before producing OR dispatching a review, critique, evaluation, assessment, or "is this right / this is the bug" verdict — anywhere a conclusion could be pattern-matched from a role instead of read from the thing. Named for D&C 9:8.

Apply Edward Tufte's principles to any data visualization, chart, dashboard, or infographic. Use when the user asks to produce, design, critique, or improve a chart, graph, dashboard, KPI tile, table-with-data, sparkline, small multiple, time series, distribution plot, choropleth, or any other visual that communicates quantitative or categorical information. Also triggers on words like "visualize", "viz", "data viz", "chart", "graph", "dashboard", "infographic", "Tufte". Outputs Tufte-compliant designs in either self-contained HTML/SVG or React (Recharts/D3). Defaults to Tufte rules; user can opt out per chart.

Verify scripture and talk quotes against actual source files. Enforces read-before-quoting, the cite count rule, and the pre-publish checklist. Load when writing ANY document that cites scriptures, conference talks, transcripts, or other verifiable sources — studies, evaluations, lessons, guides, docs, everything.

Look up which General Conference talks, Journal of Discourses entries, and other sources cite a particular scripture verse using the BYU Scripture Citation Index (scriptures.byu.edu). Use when you want to know who has taught about a verse, how frequently a verse appears in conference, or to discover that a verse has surprisingly little modern commentary.

Stress-test the study's arguments, assumptions, and gaps before finalizing. Asks 'what are we missing?', 'where are we overreaching?', and 'does the text actually say what we think it says?' Use between gap analysis and first draft to sharpen the study.

Telescope into a specific scripture passage or narrow topic. Follow every footnote, trace every cross-reference, read full chapters for context. Produces intermediate findings in a working document. Use for focused, depth-first study on a single text or concept.

Six text-checkable properties for evaluating non-canonical sources (books, articles, transcripts, web content) before citing or recommending them. Loaded passively whenever the agent is asked to assess, summarize, recommend, or quote from a source outside the LDS canon. Names what the agent CAN check (correspondence, coherence, canonical fit, pillars-rhetoric, mark-keeping, steelman) and what only the user with the Spirit can check (witness, soul-fruit, animating spirit, personal stewardship-fit, override). Grounded in study/discernment-and-the-comprehending-eye.md.

Run the publish script to convert study documents to public HTML, then git add, commit, and push. Use when the user says publish, commit, push, or asks to share their work.

Externalize verified quotes and observations to a scratch file as you read, so they survive context compaction. Use during any study session to build a durable working document alongside source reading. This skill exists because files are durable — context is not.

Format scripture and conference talk links using workspace-relative paths. Covers path conventions, link examples, and file verification. Load when creating or editing study documents, lessons, talks, evaluations, or any markdown that references scriptures.

Parallelize a large task across many subagents — when the work is independent per-unit (verify / research / generate, the same operation across N files or items) it is a fan-out shape, and parallel fresh-eyes-per-unit beats one tiring serial operator. Use to triage whether a long task should be fanned out, and to run the fan-out safely under an active presiding watch (e.g., a 62-file audit fanned to 6 agents finished in ~15 min and was more thorough than the serial walk that preceded it).

The orchestration pattern for staffing implementation across cheaper model seats — the boss (the orchestrating agent) writes specs and constitutions, dispatches, blind-verifies, keeps a liveness watch, and rules on disputes, but never implements. Includes the audition oracle for hiring seats, merge-train discipline (post-merge build oracle on main), and watch-what-you-order review. Load for any arc with several independent implementation units, or any grindable, oracle-covered build.

The green-light triage for any long or autonomous work — ask "what's the oracle?" AND "is it grindable?" before committing to the shape. Use at the moment of green-lighting any overnight or unattended run, fan-out, "keep marching" arc, soak, migration walk, bulk verification, or agent-loop dispatch. Also triggers when sizing why an autonomous run underperformed. Companion to fan-out (the parallel shape) and foreman (the staffing pattern).

Ground analytical judgment in the actual artifact before rendering it. Load before producing OR dispatching a review, critique, evaluation, assessment, or "is this right / this is the bug" verdict — anywhere a conclusion could be pattern-matched from a role instead of read from the thing.

When the user hands off a task — especially unsupervised or "I give you stewardship over this" — carry it through to completion. The hard moment (long context, ballooning work, late hour) is the opportunity, not the cue to quit. You have durable memory; compact and continue. A handoff weighs more than a normal task. Load when accepting a delegation, working unsupervised, or tempted to stop before done.

Stress-test your own practice against your principles before claiming them as strengths. Named for Ben, who observed "Your AI is very complimentary. Perhaps too complimentary?" Apply in evaluations, proposals, self-assessments, and especially when you're about to tell someone else what they could learn from you.

Software isn't permanent — code is cheap and git walks anything back. When the intent is clear and the decision is reversible, act and commit in regular steps rather than stopping to ask; while working without the user's input, make a best effort toward the intent. Use when deciding whether to act vs. ask, and when working unsupervised. Generalizes beyond code.

When must the human be in the loop, vs. when can the agent discern and act on its own? The decision rubric for autonomy scope — four bins (act / act-and-report / surface-first / always-theirs), built on the dave-rule's reversibility lean plus a judgment-source test. Load when deciding whether to act or ask, and especially before any unsupervised run.

Verify scripture and talk quotes against actual source files. Enforces read-before-quoting, the cite count rule, and the pre-publish checklist. Load when writing ANY document that cites scriptures, conference talks, transcripts, or other verifiable sources — studies, evaluations, lessons, guides, docs, everything.