---

name: to-wiki description: > Use when turning a transcribed source — a thesis, paper, standard, manual, or a folder of Markdown chapters under docs/references — into a Karpathy-style LLM wiki knowledge base: interlinked concept, entity, source, and synthesis pages with an index.md, an append-only log.md, and a schema file, where every claim must trace back to the raw text. Use when the user says build a wiki, knowledge base, karpathy wiki, ingest this source, or asks to query or lint an existing docs/wiki. Also use when a wiki someone else built needs a quality gate before handover.

Source → LLM Wiki

Overview

A wiki is a second layer over an immutable raw source. Raw stays verbatim in docs/references/. The wiki holds hand-written pages that summarize, cross-link, and synthesize, and every fact in it points at the raw line it came from.

Core principle: the wiki may only know what the source says. If a fact is not in the raw text, the wiki does not state it. The only place an absent topic may appear is a ## Not covered by the source list at the end of a concept page. That list is the valve that keeps writer knowledge out.

A wiki built without that valve fills with plausible outside facts within pages. Measured in the baseline for this skill: the writer defined a Background tag, "true, standard, and not in the source", and used it on the first method page.

When to Use

• Raw source already transcribed to Markdown (use to-markdown first if not).
• Output will be queried by agents and people later, and will grow as more sources are ingested.
• Someone will trust a number or a claim from a wiki page without reopening the raw file.
• An existing wiki needs an ingest, a query answered from it, a lint, or a pre-handover review.

When NOT to use: one-off question about a document → read it and answer. Notes for one session → a scratch file. Source not yet in Markdown → to-markdown first.

The Output Contract

Not guidelines. The shape of the deliverable.

Part	Content
AGENTS.md	Schema: layout, hard rules, link paths, frontmatter, page templates, index and log formats, ingest / query / lint workflows, frozen slug list
index.md	One line per page, grouped by type, alphabetical. Loaded first by any agent
log.md	Append-only, dated entries: ingest, query, lint. Newest at bottom
sources/	One page per raw document, plus one per chapter. Section-by-section map with anchors, equations table, figures table, numbers table, citations table
concepts/	One idea per page. Ends with mandatory ## Not covered by the source
entities/	People, orgs, hardware, software, papers, deployments. An index into the source: ## Every mention bullets, not an encyclopedia article
syntheses/	Cross-page answers: comparisons, equation index, figure index, key numbers, lessons, contributions map, open problems

Page rules that are non-negotiable, in the schema and on every page:

1. Every claim sentence carries an inline relative link to its raw section anchor. A page-level "Source lines" footer is not enough. Baseline: one footer-only page had 96 unanchored sentences and one invented count ("five of six") that the footer could not have caught.
2. A citation clause is all you get. If the source gives a cited work only a number and a clause, the wiki gets only that clause. No method summary from memory.
3. Numbers exact, with units. Equations copied byte-exact with the source's own tag.
4. Cross-link on first mention. At least 3 outgoing wiki links per page. Relative Markdown links only.
5. Figures link into raw assets. Never copy images.
6. Where the source is silent, write "the source does not say". Where the wiki draws a connection the source does not draw, label it "wiki reading".
7. Pages hold latest state. History goes to log.md.
8. Entity threshold. An entity page exists only for a work, person, or thing the source describes in more than one clause or gives a role. A work cited once stays a row in the source page's citations table. On a review with ~180 references this rule removes most stub pages.

Template for the schema file, ready to adapt: references/schema-template.md.

Process

digraph wiki {
    rankdir=TB;
    "Read the whole source" [shape=box];
    "Inventory pages + gap-check" [shape=box];
    "Write schema + skeleton" [shape=box];
    "Parallel writers by provenance" [shape=box];
    "Own review pass vs raw" [shape=box];
    "Index, log, lint" [shape=box];
    "Gate: one reviewer per dimension" [shape=box];
    "Defects?" [shape=diamond];
    "Editors on disjoint folders" [shape=box];
    "Handover" [shape=box];

    "Read the whole source" -> "Inventory pages + gap-check" -> "Write schema + skeleton";
    "Write schema + skeleton" -> "Parallel writers by provenance" -> "Own review pass vs raw";
    "Own review pass vs raw" -> "Index, log, lint" -> "Gate: one reviewer per dimension" -> "Defects?";
    "Defects?" -> "Editors on disjoint folders" [label="yes"];
    "Editors on disjoint folders" -> "Index, log, lint";
    "Defects?" -> "Handover" [label="no"];
}

1. Read the whole source yourself. All chapters, bibliography, reference cards. The inventory you design next is only as good as your recall of what is in the text.

2. Inventory the pages, then gap-check the inventory. Choose the shape for this kind of source first, with references/structure-selection.md: what earns an entity page, which syntheses are mandatory, how the concept template changes, which gate lenses run. Then draft slugs per type. Then dispatch one planning agent with the draft and the raw paths, and ask for: topics the source states that no page covers, pages to merge (too thin) or split (too fat), pages that will tempt outside knowledge, and a batch split by chapter provenance. In the run that produced this skill the gap-check added 10 pages (a method step, test setup, dataset, committee members, a cited-work entity), merged 6, split 2, and named 10 risk pages that later got sentence-by-sentence review.

3. Write the schema and skeleton first. AGENTS.md with every rule above and the frozen slug list. Empty index.md with type headings. log.md header. Writers link against the frozen slugs, so cross-batch links do not dangle.

4. Parallel writers, split by chapter provenance, never by folder. One writer per chapter group, so no two writers need the same raw section open. Each gets the schema, the frozen slug list, its own slugs with one-line intent each, and the raw files to read. Nobody touches index.md or log.md. Each returns its index lines in its final message. Model: opus.

5. Read every page yourself against its raw anchors. Look for: numbers, outside knowledge on the risk pages, inferences stated as fact, ambiguous dropped articles, template compliance. This pass is authorship. It does not replace step 7.

6. Assemble index and log. Lint. Broken links, bad anchors, frontmatter, index coverage, title match, minimum links, Not covered present, encoding. Shell one-liners in references/lint.md. No generator scripts, no checker scripts inside the wiki.

7. Gate: one reviewer per dimension, before any handover. See below. Required.

8. Editors on disjoint folders, then lint again, then log. Style and consistency fixes are large. Two opus editors, one per folder pair, with hard rules: no fact, number, link, heading, or quoted text changes. Then re-run step 6 and append a lint entry to log.md.

The Gate

Your own read in step 5 is authorship, not review. Measured in the run that produced this skill, after a full own-read of 71 pages that fixed 9 issues, five independent reviewers found:

Dimension	Found after own review
Fidelity vs raw	1 elided caption clause in 3,300 checked claims
Outside-knowledge leaks	0 facts, 3 inferences stated as fact, 7 weak connectives
Schema compliance	5 template gaps, 1 index title mismatch, 1 unanchored claim
Reader queries (24 questions, 3 personas)	24 answered, 10 usability gaps
Style and consistency	9 ambiguous sentences, 45 long, 120 passives, 24 idioms, 1 contradiction

Not one of those was visible to lint or to the author. So the gate is a required step with a fixed shape, not a judgment call:

1. Pick dimensions from what the wiki contains. Default five above. A wiki with no equations drops the equation checks; a wiki with code adds a code lens.
2. One reviewer per dimension, read-only, opus, all dispatched in one message, each with the checklist for its dimension from references/gate-review.md.
3. Demand a report shape: CHECK n — PASS|FAIL (x issues) per checklist item, then path:line | "text" | fix per issue, then counts. A prose verdict is not a report.
4. Reports truncate. When a report ends mid-check, send the reviewer a message asking for the missing checks only, under a line budget. Do not guess the tail.
5. Triage yourself. Verify each HIGH item against raw before acting. Accept by-design duplication (entity "Every mention" pages quoting the same sentence) and record the acceptance in log.md.
6. Fix, re-lint, log, then hand over with the table of what was checked and what remains unverified.

Rationalizations that skip the gate

All heard in the baseline for this skill. All mean: run the gate.

Excuse	Reality
"I already read every page against raw"	Own read fixed 9. Reviewers then found 30+. Authorship is not review.
"Marginal find rate is low now"	Find rate of the author is low. Find rate of a fresh lens is not.
"Lint is green"	Lint sees links and headings. It cannot see an inference stated as fact.
"Writers reported 0 issues"	A producer auditing itself reports the artifact it believes in.
"Context is 80 % used"	Reviewers run in their own context. Dispatch costs one message.
"User asked only for a short summary"	The summary is shorter when the table of checks exists.

Quick Reference

Need	Where
Schema file to adapt	references/schema-template.md
Gate checklists, dispatch template, editor rules	references/gate-review.md
Structure per source kind, the six rulings, use-case table	references/structure-selection.md
Lint one-liners, encoding pitfalls, report truncation	references/lint.md
How this skill was tested	references/test-record.md

Common Mistakes

Mistake	Why it fails	Instead
A "Background" or "context" tag for facts not in the source	Outside knowledge enters with a label that looks rigorous	## Not covered by the source names the absence. Nothing else.
Provenance as a page footer	Cannot show which sentence a fact came from; invented counts hide	Inline raw anchor on every claim sentence
Writers split by folder	Two writers open the same raw section, and cross-batch links dangle	Split by chapter provenance, frozen slug list first
Detail duplicated on the hub page	Hub becomes a second copy of the source page	Hub holds definition, main numbers, and a link map
Baseline method or tool entities filled from memory	The source gives them one clause	Entity page is "Every mention" bullets and nothing more
Own full read treated as the review	Author blindness; see the gate table	Step 7, always
Reviewer report accepted after truncation	Tail held the counts and the last checks	Ask for the missing checks only
Non-ASCII replacement text through perl -CSD without -Mutf8	Double-encodes § ± τ — into §	perl -CSD -Mutf8, then grep for Â
Checker script committed inside the wiki	Tooling drifts and becomes content	One-liners live in AGENTS.md lint section and in this skill
Lint one-liner trusted on first run	An extractor written for multi-line $ blocks reports a false pass on single-line equations	Break one known item on purpose and confirm the checker flags it, then trust the empty result