• SKILL.md (this document) — The "constitution" of workflows and disciplines
• Deterministic Execution (managed by llmw CLI,

  llmw.content

  ) — This skill has zero code. All deterministic tools in the original scripts/ (lint/ fixtures check/ ingest detection/ mechanical writing) are consolidated into

  llmw

  subcommands:

  llmw wiki lint / check-fixtures / ingest-diff / write

  (see workflow sections for details). High-frequency deterministic tasks are solidified in the CLI, and agents only handle parts requiring judgment.
• references/ — Load on demand: detailed processes for each operation (ingest/ query/ lint/ upgrade), page templates (page-templates.md), lint-checklist, external-repo (access + cross-host reconstruction). Skeleton templates + fixtures (CLI byte-level comparison golden standard) are built into CLI package assets (detected via

  llmw wiki check-fixtures

  ), and upgrade-workflow.md §6 (semantic merge rules, the basis for agents when following upgrade plans)

• setup → Completed by workspace CLI (rendered from templates in the CLI package), this skill does not implement creation logic; products include directory structure + AGENTS.md (SSOT) + CLAUDE.md (thin shell) + wiki/index.md + wiki/log.md + MEMORY/MEMORY.md + .gitignore
• ingest → Add/update

  wiki/sources/<slug>.md

  + sync entity/concept pages + append entries to

  log.md

  + update

  index.md

• query → Provide answers in the conversation (with references), optionally archive answers as

  wiki/comparisons/

  or

  wiki/syntheses/<slug>.md

• lint → Report in

  log

  : whether raw/ has been modified, orphan pages, broken cross-references, outdated summaries, missing frontmatter, log.md format issues
• upgrade →

  llmw wiki upgrade

  (dry-run →

  --apply --yes

  ) fixes the skeleton (byte/block/header-owned + legacy paths); legacy frontmatter of content pages is fixed via

  lint --check-version --apply

  to get

  actions[]

  , and agents modify according to upgrade-workflow.md §6; see §5 Upgrade for details

Operation Preprocessing (orient ritual, applicable to all operations): Before starting any ingest/ query/ lint operation, do not rely on symlinks — read the four components in the following order before taking action:

1. Confirm

   <wiki-root>/AGENTS.md

   is in context (loaded via thin shell CLAUDE.md or natively — persistent in the session;

   CLAUDE.md

   is a thin shell of

   @AGENTS.md

   and does not hold disciplines) — obtain the wiki's topic name and "current configuration" table ("Wiki Format Version" row). The full MEMORY content is already in context via the top

   @MEMORY/MEMORY.md

   @import

   ; tag whitelist is in

   wiki/tags.md

   (see §Core Principles §6)

2. Read <$LLM_WIKI_ROOT>/wiki/index.md

   — Know which pages exist and their categories, avoid duplicate creation/ missing cross-references

3. Read <$LLM_WIKI_ROOT>/wiki/log.md

   (last ~30 lines are sufficient) — Review recent activities, avoid duplicate ingest/ missing archiving of old work

4. Read <$LLM_WIKI_ROOT>/scripts/SCRIPTS.md

   (as needed) — Confirm whether this wiki has a complete section contract for project-level extended scripts (usage scenarios/ calling conventions/ functions/ preconditions); not mandatory (wiki may not have scripts/), but must check before triggering non-standard workflows (the

   @scripts/SCRIPTS.md

   @import

   at the top of AGENTS.md has loaded the full content)

Do not write any wiki content if any of the four components are not read. For wikis with 100+ pages, also run

Grep "<topic>"

across the entire

wiki/

directory — relying solely on index.md may miss reference relationships between entity/concept pages.

1. raw/ is controlled by users, LLM has read-only access — Two write permission exceptions (

   raw/external/

   symlink access +

   raw/discussions/

   collaborative drafts) cannot be extended; see

   references/external-repo.md

   /

   references/ingest-workflow.md §10

   for operation details
2. Standard write operations =

   llmw wiki write

   series — Append logs via

   write log

   , create new pages via

   write new

   , clear the

   reviewed

   timestamp after editing approved pages via

   write touch

   , add new MEMORY entries via

   write memory add

   , add index entries via

   write index add

   ; format +

   LOG_RETENTION_LIMIT

   truncation are guaranteed by scripts, and lint only handles manual modifications outside the standard path. Escape hatch: Manual Edit/Write is allowed for formats not supported by scripts, with lint as a fallback — scripts are the default path, not a gatekeeper
3. Every page must have YAML frontmatter — create new pages via

   llmw wiki write new

   (5 required fields + recommended

   description

   ). Authoritative definitions (values of

   type

   / reserved fields/

   sources

   specialization/ credibility signals) are in

   references/page-templates.md

   §1; exception list (index/ log/ MEMORY/ MEMORY*) is in the same section
4. LLM must clear the

   reviewed

   timestamp when modifying approved pages — Run

   llmw wiki write touch

   after each edit; canonical lifecycle rules are in the "Credibility and Cognitive Quality Signals" section of

   page-templates.md

   ; lint uses

   reviewed-stale

   as a fallback
5. MEMORY/ is the private memory of LLM agents — Add new entries via

   llmw wiki write memory add

   ; only modify

   MEMORY/MEMORY.md

   (no copy drift). Its physical location in

   <wiki-root>/

   instead of

   wiki/

   means it is naturally kept as a private layer and not published during publishing; see Workflow §4 for writing process
6. Tag whitelist is in

   wiki/tags.md

   — Canonical values/ parsing/ audit cycle are explained in the header block of the fixture (read immediately after being written to disk); lint semantics are in

   lint-checklist.md §11

• Do not bypass

  AGENTS.md

  to create custom conventions — If AGENTS.md does not specify, ask the user first before writing

Other boundary disciplines are subject to

AGENTS.md

in the wiki root (automatically loaded, persistent in the session).

• Cross-wiki references without updating the index of the target wiki (synchronization is the user's responsibility)

Other anti-patterns are subject to

AGENTS.md

in the wiki root +

references/external-repo.md

§5.

This skill is a discipline-based skill (contains multiple "must/ forbidden/ not" + sections starting with "not"). Discipline-based prohibitions may be bypassed by the LLM under pressure with various rationalizations — the triad only blocks one type: rationalized violations. Unrationalized violations (directly ignoring rules) mean the anti-pattern list itself is incomplete, and are unrelated to the triad.

Baseline actual run records: 3 RED runs — ① Disciplined ingest task: fully compliant with zero excuses; ② Undisciplined ingest task (Iron Law creation scenario): still compliant (the model has built-in knowledge of the规范); ③ Disciplined + user-pressured task ("Just jot it down/ hurry up"): produced one real excuse (row 1 in the table below) + one silent omission (missing required

tags

field in frontmatter, omitted directly without excuse).

tags

Inclusion Rule: Entries in the table are only collected from actual run transcripts (pre-written excuses = noise + signal interference; consistent with the "anti-rationalization" principle). The table currently has only 1 row (3 RED runs produced only 1 real excuse + 1 silent omission); new excuses from future actual runs will be added to the table, and no entries will be added if they do not appear.

• Changing

  Edit

  /

  Write

  to

  Read

  + manually generating new content then

  Write

  — does not bypass the prohibition of "using tools other than Read for automatic modification", using Write as the operation tool still counts
• Interpreting "do not delete wiki pages" as "copy the content out first, then

  rm

  , then write it back" — does not bypass the no-deletion prohibition, the state effect is exactly the same
• Interpreting "raw/ is controlled by users, LLM has read-only access" as "I

  cp

  into raw/ then immediately

  rm

  , I read the content in the window = equivalent to read-only" — does not, writing occurs in the first step

• "The user said 'Just jot it down/ hurry up/ don't be too formal' — disciplines can be relaxed" (actual run observation)
• "I think this step is unnecessary for the current case"
• "The user didn't explicitly ask me to do this step"
• "This is faster/ saves more tokens/ is more efficient"
• "The convention doesn't prohibit it"
• "I've done something equivalent" / "Same effect doesn't count as a violation"
• "Leave it like this for now, I'll fix it later"
• "Generating fields myself is more flexible than writing strictly according to frontmatter"
• "Skip the log entry this time, it's a wiki not git anyway"
• "The user modifies raw/ every day, I'll help out"
• "Lint reported a lot of issues, but they're all warnings so they don't count as errors"

There is no progression of "thought list = violation" — having a thought is a signal, and continuing to act will lead to a violation. But continuing after having a thought = assuming responsibility for violating the spirit.

Responsibility Boundary: This skill only handles the growth phase of the wiki (ingest/ query/ lint). The creation and deletion of wiki repositories are handled by the workspace CLI — the command is

llmw

(maintained in the same repository as this skill, see its built-in documentation for command names and parameters); the "birth form" of the wiki repository is determined by template rendering in the CLI package — detected via

llmw wiki check-fixtures

. See §Input/Output Operation Products for product forms.

1. Verify CLI deployment — Read

   <wiki-root>/AGENTS.md

   to confirm the topic name and date are replaced correctly;

   wiki/index.md

   /

   wiki/log.md

   exist and have complete frontmatter;

   <wiki-root>/CLAUDE.md

   is a thin shell
2. Run the orient ritual (see the quoted block at the top of §Execution Principles / Boundaries)
3. Ask the user if they want to do the first ingest — if yes, provide the path of the first material to the agent

raw/

llmw wiki ingest-diff

references/ingest-workflow.md

references/external-repo.md

1. Run

   llmw wiki ingest-diff

   (add

   --check-stale

   for daily use) to find the list of uningested/ re-ingestable files
2. Verify key points for single files — Only for interactive single-file or small-scale scenarios: confirm topic direction/ key cross-referenced entities/ user's judgment on what to retain
3. For each file: Read the full text → Extract metadata → Create a skeleton via

   llmw wiki write new --type=source ...

   → Write the body (use Edit instead of Write overwrite for stale-raw) → Sync entity/concept pages (only append the "Sources" section) →

   llmw wiki write index add

   →

   llmw wiki write log --op=ingest

   → Run

   llmw wiki write touch

   for edited pages
4. commit (only when git is enabled): Rhythm is determined by the user/agent, do not auto-commit

1. Check index.md first — Find candidate pages by keywords/ categories
2. Read relevant pages (do not read raw/ — raw/ has already been digested in source pages)
3. Cross-page synthesis — Include source links in reference format; explicitly mark contradictions: "A states X (Source: ...), B states Y (Source: ...), further research is needed"
4. Display answer + ask about archiving — If the answer has the nature of "comparison/ synthesis/ discovering connections", ask the user: "Is this answer suitable for archiving back to the wiki as comparisons/

   <slug>

   .md?"
5. Archive after user approval — Use the

   comparison

   or

   synthesis

   template from references/page-templates.md + append a log entry

references/query-workflow.md

1. Run

   llmw wiki lint

   for deterministic checks
2. Script coverage (major categories below, authoritative list in

   references/lint-checklist.md

   ): raw immutability/ frontmatter fields/ orphan pages/ broken links/ log.md format/ outdated summaries/ page volume/ cognitive quality and credibility signals (

   reviewed

   /

   contested

   /

   contradictions

   ) /

   raw/external/

   symlink ↔ anchor association (external-repo.md)/ fixture consistency (see the "Fixture Consistency Check" section below)
3. After script output, agents must also perform semi-qualitative checks: contradictory claims/ missing cross-references/ suggestions for new ingest directions
4. Report + ask the user which fixes to implement

references/lint-checklist.md

• Encountering pitfalls (e.g., frequent OCR errors in raw/ PDFs, ask the user to convert the format first next time)
• Discovering user preferences (e.g., user prefers tabular comparisons, dislikes prose-style summaries)
• Cross-ingest associations (two source pages point to different chapters of the same paper)
• Recurring patterns in lint reports (every lint reports missing fields for a certain type)

MEMORY/

AGENTS.md

memory-index.txt

1. Decide if it's worth writing — Will it make future agent work smoother?
2. Determine entry form: Full (includes why+how context) → Create a file + index entry via

   llmw wiki write memory add --slug=... --title=...

   , then Edit to write the body; Short (pure reminder) → Directly add an index line to

   MEMORY/MEMORY.md

3. Write the body — Record specific experience, including context/ solution steps/ how to avoid it in the future
4. Do not append log entries/ do not list in wiki/index.md (MEMORY does not follow the single-entry constraint)

• Do not delete any MEMORY files — Pitfall records are preserved
• Retain the original

  created

  field when writing new files; only update

  updated

• Users do not directly edit MEMORY/ — If the user wants to add content, inform the agent first and let the agent write it