When to invoke this skill

Proper 1in margins, intelligent page breaks, page numbers, cover pages, running headers, curly quotes and em dashes, clickable TOC, diagonal DRAFT watermark. Not a draft artifact — a finished artifact. Use when asked to "make a PDF", "export to PDF", "turn this markdown into a PDF", or "generate a document".

Voice triggers (speech-to-text aliases): "make this a pdf", "make it a pdf", "export to pdf", "turn this into a pdf", "turn this markdown into a pdf", "generate a pdf", "make a pdf from", "pdf this markdown".

Preamble (run first)

_UPD=$(~/.claude/skills/bstack/bin/bstack-update-check 2>/dev/null || .claude/skills/bstack/bin/bstack-update-check 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
mkdir -p ~/.bstack/sessions
touch ~/.bstack/sessions/"$PPID"
_SESSIONS=$(find ~/.bstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
find ~/.bstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
_PROACTIVE=$(~/.claude/skills/bstack/bin/bstack-config get proactive 2>/dev/null || echo "true")
_PROACTIVE_PROMPTED=$([ -f ~/.bstack/.proactive-prompted ] && echo "yes" || echo "no")
_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
echo "BRANCH: $_BRANCH"
_SKILL_PREFIX=$(~/.claude/skills/bstack/bin/bstack-config get skill_prefix 2>/dev/null || echo "false")
echo "PROACTIVE: $_PROACTIVE"
echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
echo "SKILL_PREFIX: $_SKILL_PREFIX"
source <(~/.claude/skills/bstack/bin/bstack-repo-mode 2>/dev/null) || true
REPO_MODE=${REPO_MODE:-unknown}
echo "REPO_MODE: $REPO_MODE"
_SESSION_KIND=$(~/.claude/skills/bstack/bin/bstack-session-kind 2>/dev/null || echo "interactive")
case "$_SESSION_KIND" in spawned|headless|interactive) ;; *) _SESSION_KIND="interactive" ;; esac
echo "SESSION_KIND: $_SESSION_KIND"
# Conductor host: AskUserQuestion is unreliable here (native disabled, MCP
# variant flaky), so skills render decisions as prose instead of calling the
# tool. Gated on !headless so an eval/CI run INSIDE Conductor (BSTACK_HEADLESS)
# still BLOCKs rather than rendering prose to nobody.
if [ "$_SESSION_KIND" != "headless" ] && { [ -n "${CONDUCTOR_WORKSPACE_PATH:-}" ] || [ -n "${CONDUCTOR_PORT:-}" ]; }; then
  echo "CONDUCTOR_SESSION: true"
fi
_ACTIVATED=$([ -f ~/.bstack/.activated ] && echo "yes" || echo "no")
_FIRST_LOOP_SHOWN=$([ -f ~/.bstack/.first-loop-tip-shown ] && echo "yes" || echo "no")
echo "ACTIVATED: $_ACTIVATED"
echo "FIRST_LOOP_SHOWN: $_FIRST_LOOP_SHOWN"
# First-run project detection: run the detector ONLY on the first-ever skill run
# (ACTIVATED=no, interactive) so it stays off the hot path for every run after.
_FIRST_TASK=""
if [ "$_ACTIVATED" = "no" ] && [ "$_SESSION_KIND" != "headless" ]; then
  _FIRST_TASK=$(~/.claude/skills/bstack/bin/bstack-first-task-detect 2>/dev/null || true)
fi
echo "FIRST_TASK: $_FIRST_TASK"
_LAKE_SEEN=$([ -f ~/.bstack/.completeness-intro-seen ] && echo "yes" || echo "no")
echo "LAKE_INTRO: $_LAKE_SEEN"
_RUN_START=$(date +%s)
_SESSION_ID="$$-$(date +%s)"
_EXPLAIN_LEVEL=$(~/.claude/skills/bstack/bin/bstack-config get explain_level 2>/dev/null || echo "default")
if [ "$_EXPLAIN_LEVEL" != "default" ] && [ "$_EXPLAIN_LEVEL" != "terse" ]; then _EXPLAIN_LEVEL="default"; fi
echo "EXPLAIN_LEVEL: $_EXPLAIN_LEVEL"
_QUESTION_TUNING=$(~/.claude/skills/bstack/bin/bstack-config get question_tuning 2>/dev/null || echo "false")
echo "QUESTION_TUNING: $_QUESTION_TUNING"
mkdir -p ~/.bstack/analytics
echo '{"skill":"make-pdf","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(_repo=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null | tr -cd 'a-zA-Z0-9._-'); echo "${_repo:-unknown}")'"}'  >> ~/.bstack/analytics/skill-usage.jsonl 2>/dev/null || true
for _PF in $(find ~/.bstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
  if [ -f "$_PF" ]; then
    rm -f "$_PF" 2>/dev/null || true
  fi
  break
done
eval "$(~/.claude/skills/bstack/bin/bstack-slug 2>/dev/null)" 2>/dev/null || true
_LEARN_FILE="${BSTACK_HOME:-$HOME/.bstack}/projects/${SLUG:-unknown}/learnings.jsonl"
if [ -f "$_LEARN_FILE" ]; then
  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
    ~/.claude/skills/bstack/bin/bstack-learnings-search --limit 3 2>/dev/null || true
  fi
else
  echo "LEARNINGS: 0"
fi
~/.claude/skills/bstack/bin/bstack-timeline-log '{"skill":"make-pdf","event":"started","branch":"'"$_BRANCH"'","session":"'"$_SESSION_ID"'"}' 2>/dev/null &
_HAS_ROUTING="no"
if [ -f CLAUDE.md ] && grep -q "## Skill routing" CLAUDE.md 2>/dev/null; then
  _HAS_ROUTING="yes"
fi
_ROUTING_DECLINED=$(~/.claude/skills/bstack/bin/bstack-config get routing_declined 2>/dev/null || echo "false")
echo "HAS_ROUTING: $_HAS_ROUTING"
echo "ROUTING_DECLINED: $_ROUTING_DECLINED"
_VENDORED="no"
if [ -d ".claude/skills/bstack" ] && [ ! -L ".claude/skills/bstack" ]; then
  if [ -f ".claude/skills/bstack/VERSION" ] || [ -d ".claude/skills/bstack/.git" ]; then
    _VENDORED="yes"
  fi
fi
echo "VENDORED_BSTACK: $_VENDORED"
echo "MODEL_OVERLAY: claude"
_CHECKPOINT_MODE=$(~/.claude/skills/bstack/bin/bstack-config get checkpoint_mode 2>/dev/null || echo "explicit")
_CHECKPOINT_PUSH=$(~/.claude/skills/bstack/bin/bstack-config get checkpoint_push 2>/dev/null || echo "false")
echo "CHECKPOINT_MODE: $_CHECKPOINT_MODE"
echo "CHECKPOINT_PUSH: $_CHECKPOINT_PUSH"
# Plan-mode hint for skills like /spec that branch behavior on plan-mode state.
# Claude Code exposes plan mode via system reminders; we detect best-effort
# from CLAUDE_PLAN_FILE (set by the harness when plan mode is active) and
# fall back to "inactive". Codex hosts and Claude execution mode both end up
# inactive, which is the safe default (defaults to file+execute pipeline).
if [ -n "${CLAUDE_PLAN_FILE:-}${BSTACK_PLAN_MODE_FORCE:-}" ]; then
  export BSTACK_PLAN_MODE="active"
elif [ "${BSTACK_PLAN_MODE:-}" = "active" ]; then
  export BSTACK_PLAN_MODE="active"
else
  export BSTACK_PLAN_MODE="inactive"
fi
echo "BSTACK_PLAN_MODE: $BSTACK_PLAN_MODE"
[ -n "$OPENCLAW_SESSION" ] && echo "SPAWNED_SESSION: true" || true

MAKE-PDF SETUP (run this check BEFORE any make-pdf command)

_ROOT=$(git rev-parse --show-toplevel 2>/dev/null)
P=""
[ -n "$MAKE_PDF_BIN" ] && [ -x "$MAKE_PDF_BIN" ] && P="$MAKE_PDF_BIN"
[ -z "$P" ] && [ -n "$_ROOT" ] && [ -x "$_ROOT/.claude/skills/bstack/make-pdf/dist/pdf" ] && P="$_ROOT/.claude/skills/bstack/make-pdf/dist/pdf"
[ -z "$P" ] && P="$HOME/.claude/skills/bstack/make-pdf/dist/pdf"
if [ -x "$P" ]; then
  echo "MAKE_PDF_READY: $P"
  alias _p_="$P"   # shellcheck alias helper (not exported)
  export P   # available as $P in subsequent blocks within the same skill invocation
else
  echo "MAKE_PDF_NOT_AVAILABLE (run './setup' in the bstack repo to build it)"
fi

If MAKE_PDF_NOT_AVAILABLE is printed: tell the user the binary is not built. Have them run ./setup from the bstack repo, then retry.

If MAKE_PDF_READY is printed: $P is the binary path for the rest of the skill. Use $P (not an explicit path) so the skill body stays portable.

Core commands:

• $P generate <input.md> [output.pdf] — render markdown to PDF (80% use case)
• $P generate --cover --toc essay.md out.pdf — full publication layout
• $P generate --watermark DRAFT memo.md draft.pdf — diagonal DRAFT watermark
• $P preview <input.md> — render HTML and open in browser (fast iteration)
• $P setup — verify browse + Chromium + pdftotext and run a smoke test
• $P --help — full flag reference

Output contract:

• stdout: ONLY the output path on success. One line.
• stderr: progress (Rendering HTML... Generating PDF...) unless --quiet.
• Exit 0 success / 1 bad args / 2 render error / 3 Paged.js timeout / 4 browse unavailable.

Plan Mode Safe Operations

In plan mode, allowed because they inform the plan: $B, $D, codex exec/codex review, writes to ~/.bstack/, writes to the plan file, and open for generated artifacts.

Skill Invocation During Plan Mode

If the user invokes a skill in plan mode, the skill takes precedence over generic plan mode behavior. Treat the skill file as executable instructions, not reference. Follow it step by step starting from Step 0; the first AskUserQuestion is the workflow entering plan mode, not a violation of it. AskUserQuestion (any variant — mcp__*__AskUserQuestion or native; see "AskUserQuestion Format → Tool resolution") satisfies plan mode's end-of-turn requirement. If AskUserQuestion is unavailable or a call fails, follow the AskUserQuestion Format failure fallback: headless → BLOCKED; interactive → the prose fallback (also satisfies end-of-turn). At a STOP point, stop immediately. Do not continue the workflow or call ExitPlanMode there. Commands marked "PLAN MODE EXCEPTION — ALWAYS RUN" execute. Call ExitPlanMode only after the skill workflow completes, or if the user tells you to cancel the skill or leave plan mode.

If PROACTIVE is "false", do not auto-invoke or proactively suggest skills. If a skill seems useful, ask: "I think /skillname might help here — want me to run it?"

If SKILL_PREFIX is "true", suggest/invoke /bstack-* names. Disk paths stay ~/.claude/skills/bstack/[skill-name]/SKILL.md.

If output shows UPGRADE_AVAILABLE <old> <new>: read ~/.claude/skills/bstack/bstack-upgrade/SKILL.md and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined).

If output shows JUST_UPGRADED <from> <to>: print "Running bstack v{to} (just updated!)". If SPAWNED_SESSION is true, skip feature discovery.

Feature discovery, max one prompt per session:

• Missing ~/.claude/skills/bstack/.feature-prompted-continuous-checkpoint: AskUserQuestion for Continuous checkpoint auto-commits. If accepted, run ~/.claude/skills/bstack/bin/bstack-config set checkpoint_mode continuous. Always touch marker.
• Missing ~/.claude/skills/bstack/.feature-prompted-model-overlay: inform "Model overlays are active. MODEL_OVERLAY shows the patch." Always touch marker.

After upgrade prompts, continue workflow.

If WRITING_STYLE_PENDING is yes: ask once about writing style:

v1 prompts are simpler: first-use jargon glosses, outcome-framed questions, shorter prose. Keep default or restore terse?

Options:

• A) Keep the new default (recommended — good writing helps everyone)
• B) Restore V0 prose — set explain_level: terse

If A: leave explain_level unset (defaults to default). If B: run ~/.claude/skills/bstack/bin/bstack-config set explain_level terse.

Always run (regardless of choice):

rm -f ~/.bstack/.writing-style-prompt-pending
touch ~/.bstack/.writing-style-prompted

Skip if WRITING_STYLE_PENDING is no.

If LAKE_INTRO is no: say "bstack uses Proportional Completeness: fully cover the approved scope, including tests, edge cases, and error paths, without expanding into unrelated work."

touch ~/.bstack/.completeness-intro-seen

Always run touch after showing the one-time explanation.

If PROACTIVE_PROMPTED is no AND TEL_PROMPTED is yes: ask once:

Let bstack proactively suggest skills, like /qa for "does this work?" or /investigate for bugs?

Options:

• A) Keep it on (recommended)
• B) Turn it off — I'll type /commands myself

If A: run ~/.claude/skills/bstack/bin/bstack-config set proactive true If B: run ~/.claude/skills/bstack/bin/bstack-config set proactive false

Always run:

touch ~/.bstack/.proactive-prompted

Skip if PROACTIVE_PROMPTED is yes.

First-run guidance (one-time)

If ACTIVATED is no (first skill run on this machine) AND the preamble printed a non-empty FIRST_TASK: value that is NOT nongit: show ONE short, project-specific line mapped from the token, as a heads-up, then CONTINUE with whatever the user actually asked — do NOT halt their task. Map the token: greenfield → "Fresh commercial idea? Clarify it with /office-hours, then decide with /preflight before /spec." code_node/code_python/code_rust/code_go/code_ruby/code_ios → "There's code here — use /preflight for new commercial work, /qa for existing behavior, or /investigate for bugs." branch_ahead → "Unshipped work on this branch — /review then /ship." dirty_default → "Uncommitted changes — /review before committing." clean_default → "For new commercial work start with /preflight; otherwise choose /investigate or /qa." Then substitute the token you saw for TASK_TOKEN and run (best-effort), and mark activated:

~/.claude/skills/bstack/bin/bstack-timeline-log '{"skill":"first-task","event":"completed","outcome":"shown","task":"TASK_TOKEN"}' 2>/dev/null || true
touch ~/.bstack/.activated 2>/dev/null || true

If ACTIVATED is no but FIRST_TASK: is empty or nongit (headless, non-git, or nothing actionable): show nothing, just run touch ~/.bstack/.activated 2>/dev/null || true.

Else if ACTIVATED is yes AND FIRST_LOOP_SHOWN is no: say once as a heads-up (then continue):

Tip: bstack pays off when you complete one loop — clarify → decide → execute proportionally → measure. For commercial work: /office-hours when fuzzy, /preflight for the gate, /spec only after BUILD NOW, then /measure-outcome.

Then run touch ~/.bstack/.first-loop-tip-shown 2>/dev/null || true.

Skip this section if ACTIVATED and FIRST_LOOP_SHOWN are both yes.

If HAS_ROUTING is no AND ROUTING_DECLINED is false AND PROACTIVE_PROMPTED is yes: Check if a CLAUDE.md file exists in the project root. If it does not exist, create it.

Use AskUserQuestion:

bstack works best when your project's CLAUDE.md includes skill routing rules.

Options:

• A) Add routing rules to CLAUDE.md (recommended)
• B) No thanks, I'll invoke skills manually

If A: Append this section to the end of CLAUDE.md:

## Skill routing

When the user's request matches an available skill, invoke it via the Skill tool. When in doubt, invoke the skill.

Key routing rules:
- Fuzzy commercial ideas/brainstorming → invoke /office-hours, then /preflight
- Clear commercial ideas or roadmap candidates → invoke /preflight
- Strategy/scope after BUILD NOW → invoke /plan-ceo-review
- Architecture → invoke /plan-eng-review
- Design system/plan review → invoke /design-consultation or /plan-design-review
- Conditional review and execution pipeline → invoke /autoplan only after BUILD NOW
- Bugs/errors → invoke /investigate
- QA/testing site behavior → invoke /qa or /qa-only
- Code review/diff check → invoke /review
- Visual polish → invoke /design-review
- Ship/deploy/PR → invoke /ship or /land-and-deploy
- Save progress → invoke /context-save
- Resume context → invoke /context-restore
- Author a backlog-ready commercial spec/issue → invoke /spec only after BUILD NOW
- Measure a shipped product outcome → invoke /measure-outcome

Leave the change uncommitted so the user can review and commit it with the rest of their project changes.

If B: run ~/.claude/skills/bstack/bin/bstack-config set routing_declined true and say they can re-enable with bstack-config set routing_declined false.

This only happens once per project. Skip if HAS_ROUTING is yes or ROUTING_DECLINED is true.

If VENDORED_BSTACK is yes, warn once via AskUserQuestion unless ~/.bstack/.vendoring-warned-$SLUG exists:

This project has bstack vendored in .claude/skills/bstack/. Vendoring is deprecated. Migrate to team mode?

Options:

• A) Yes, migrate to team mode now
• B) No, I'll handle it myself

If A:

1. Run git rm -r .claude/skills/bstack/
2. Run echo '.claude/skills/bstack/' >> .gitignore
3. Run ~/.claude/skills/bstack/bin/bstack-team-init required (or optional)
4. Run git add .claude/ .gitignore CLAUDE.md && git commit -m "chore: migrate bstack from vendored to team mode"
5. Tell the user: "Done. Each developer now runs: cd ~/.claude/skills/bstack && ./setup --team"

If B: say "OK, you're on your own to keep the vendored copy up to date."

Always run (regardless of choice):

eval "$(~/.claude/skills/bstack/bin/bstack-slug 2>/dev/null)" 2>/dev/null || true
touch ~/.bstack/.vendoring-warned-${SLUG:-unknown}

If marker exists, skip.

If SPAWNED_SESSION is "true", you are running inside a session spawned by an AI orchestrator (e.g., OpenClaw). In spawned sessions:

• Do NOT use AskUserQuestion for interactive prompts. Auto-choose the recommended option.
• Do NOT run upgrade checks, routing injection, or lake intro.
• Focus on completing the task and reporting results via prose output.
• End with a completion report: what shipped, decisions made, anything uncertain.

Model-Specific Behavioral Patch (claude)

The following nudges are tuned for the claude model family. They are subordinate to skill workflow, STOP points, AskUserQuestion gates, plan-mode safety, and /ship review gates. If a nudge below conflicts with skill instructions, the skill wins. Treat these as preferences, not rules.

Todo-list discipline. When working through a multi-step plan, mark each task complete individually as you finish it. Do not batch-complete at the end. If a task turns out to be unnecessary, mark it skipped with a one-line reason.

Think before heavy actions. For complex operations (refactors, migrations, non-trivial new features), briefly state your approach before executing. This lets the user course-correct cheaply instead of mid-flight.

Dedicated tools over Bash. Prefer Read, Edit, Write, Glob, Grep over shell equivalents (cat, sed, find, grep). The dedicated tools are cheaper and clearer.

Voice

Direct, concrete, builder-to-builder. Name the file, function, command, and user-visible impact. No filler.

No em dashes. No AI vocabulary: delve, crucial, robust, comprehensive, nuanced, multifaceted. Never corporate or academic. Short paragraphs. End with what to do.

The user has context you do not. Cross-model agreement is a recommendation, not a decision. The user decides.

Completion Status Protocol

When completing a skill workflow, report status using one of:

• DONE — completed with evidence.
• DONE_WITH_CONCERNS — completed, but list concerns.
• BLOCKED — cannot proceed; state blocker and what was tried.
• NEEDS_CONTEXT — missing info; state exactly what is needed.

Escalate after 3 failed attempts, uncertain security-sensitive changes, or scope you cannot verify. Format: STATUS, REASON, ATTEMPTED, RECOMMENDATION.

Operational Self-Improvement

Before completing, if you discovered a durable project quirk or command fix that would save 5+ minutes next time, log it:

~/.claude/skills/bstack/bin/bstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'

Do not log obvious facts or one-time transient errors.

Local run history (run last)

After workflow completion, record local run history. Use skill name: from frontmatter. OUTCOME is success/error/abort/unknown. These records stay under ~/.bstack/ and are never uploaded by bstack.

Run this bash:

_RUN_END=$(date +%s)
_RUN_DUR=$(( _RUN_END - _RUN_START ))
rm -f ~/.bstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
~/.claude/skills/bstack/bin/bstack-timeline-log '{"skill":"SKILL_NAME","event":"completed","branch":"'$(git branch --show-current 2>/dev/null || echo unknown)'","outcome":"OUTCOME","duration_s":"'"$_RUN_DUR"'","session":"'"$_SESSION_ID"'"}' 2>/dev/null || true
echo '{"skill":"SKILL_NAME","duration_s":"'"$_RUN_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.bstack/analytics/skill-usage.jsonl 2>/dev/null || true

Replace SKILL_NAME, OUTCOME, and USED_BROWSE before running.

Plan Status Footer## Plan Status Footer

Skills that run plan reviews (/plan-*-review, /codex review) include the EXIT PLAN MODE GATE blocking checklist at the end of the skill, which verifies the plan file ends with ## BSTACK REVIEW REPORT before ExitPlanMode is called. Skills that don't run plan reviews (operational skills like /ship, /qa, /review) typically don't operate in plan mode and have no review report to verify; this footer is a no-op for them. Writing the plan file is the one edit allowed in plan mode.

make-pdf: publication-quality PDFs from markdown

Turn .md files into PDFs that look like Faber & Faber essays: 1in margins, left-aligned body, Helvetica throughout, curly quotes and em dashes, optional cover page and clickable TOC, diagonal DRAFT watermark when you need it. Copy-paste from the PDF produces clean words, never "S a i l i n g".

On Linux, install fonts-liberation for correct rendering — Helvetica and Arial aren't present by default, and Liberation Sans is the standard metric-compatible fallback. CI and Docker builds install it automatically via Dockerfile.ci.

Emoji need a color-emoji font. macOS (Apple Color Emoji) and Windows (Segoe UI Emoji) ship one; most Linux distros and containers ship none, so emoji render as empty boxes (▯). ./setup auto-installs fonts-noto-color-emoji on Linux (apt/dnf/pacman/apk, best-effort) and the print CSS falls back through Apple / Segoe / Noto emoji families. Set BSTACK_SKIP_FONTS=1 to skip the install (CI without sudo, managed or offline machines).

Core patterns

80% case — memo/letter

One command, no flags. Gets a clean PDF with running header + page numbers

• CONFIDENTIAL footer by default.

$P generate letter.md                 # writes /tmp/letter.pdf
$P generate letter.md letter.pdf      # explicit output path

Publication mode — cover + TOC + chapter breaks

$P generate --cover --toc --author "Example Author" --title "On Horizons" \
  essay.md essay.pdf

Each top-level H1 in the markdown starts a new page. Disable with --no-chapter-breaks for memos that happen to have multiple H1s.

Draft-stage watermark

$P generate --watermark DRAFT memo.md draft.pdf

Diagonal 10% opacity DRAFT across every page. When the draft is final, drop the flag and regenerate.

Fast iteration via preview

$P preview essay.md

Renders HTML with the same print CSS and opens it in your browser. Refresh as you edit the markdown. Skip the PDF round trip until you're ready.

Brand-free (no CONFIDENTIAL footer)

$P generate --no-confidential memo.md memo.pdf

Diagrams — mermaid and excalidraw fences render as pictures

A column-0 ```mermaid or ```excalidraw fence in the markdown renders as a crisp vector diagram, fully offline (vendored bundle, no CDN). Indented fences (inside lists) stay plain code blocks by design. A broken fence produces a visible red diagnostic block with the parse error — never silent raw code.

Fence info-string options:

```mermaid title="Auth flow"        ← caption + aria-label
```mermaid render=false             ← keep it as a code block (today's behavior)
```mermaid page=landscape           ← force this diagram onto a landscape page
```mermaid page=portrait            ← veto auto-landscape for this diagram

A ```excalidraw fence contains a full .excalidraw scene file (what excalidraw.com saves). Authoring NEW diagrams from English is /diagram's job — it emits an editable triplet (source, .excalidraw, SVG/PNG) and pairs with this skill: embed the .mmd source in your markdown, not the PNG.

Images — scaled right, never truncated

Local images inline automatically (relative paths resolve against the markdown file). Every image caps at the content box — zero truncation, ever. Oversized photos downscale to print resolution (300dpi) so payloads stay small with no visible quality loss.

Remote (http/https) images are blocked with a visible placeholder by default — offline posture; pass --allow-network to fetch them. An image that resolves outside the markdown's directory (even via symlink) still inlines, but warns loudly; --strict makes it fatal. Files over 64MB or non-regular files (fifos, devices) degrade to a placeholder instead of hanging the run.

Per-image directives, written immediately after the image:

![chart](data.png){width=full}      ← stretch to content-box width
![chart](data.png){width=50%}       ← percentage or 3in/8cm/200px
![wide](arch.png){page=landscape}   ← give it its own landscape page
![wide](shot.png){page=portrait}    ← veto auto-landscape

Wide, small-text diagram images auto-promote to their own landscape page (conservative: aspect ≥ 1.8, width over ~2.5x the content box, AND a diagram-ish alt word — diagram/architecture/flowchart/chart/graph). The promoted page is vertically centered. When the heuristic guesses wrong, {page=portrait} vetoes it; false negatives just need {page=landscape}.

Other formats — single-file HTML and Word

$P generate readme.md out.html --to html    # ONE self-contained file: inline
                                            # SVG diagrams, data-URI images,
                                            # zero network refs, screen-readable
$P generate readme.md out.docx --to docx    # Word: content fidelity (headings,
                                            # tables, code, diagrams as PNG) —
                                            # layout is Word's, not ours

--to is the output format. --format is something else entirely (a --page-size alias) — don't confuse them.

CI mode — fail loud on missing assets

$P generate docs.md --strict     # missing, remote, out-of-tree, oversized,
                                 # and non-regular-file images exit non-zero
                                 # instead of warn + placeholder

Common flags

Page layout:
  --margins <dim>            1in (default) | 72pt | 2.54cm | 25mm
  --page-size letter|a4|legal

Structure:
  --cover                    Cover page (title, author, date, hairline rule)
  --toc                      Clickable TOC with page numbers
  --no-chapter-breaks        Don't start a new page at every H1

Branding:
  --watermark <text>         Diagonal watermark ("DRAFT", "CONFIDENTIAL")
  --header-template <html>   Custom running header
  --footer-template <html>   Custom footer (mutex with --page-numbers)
  --no-confidential          Suppress the CONFIDENTIAL right-footer

Output:
  --to pdf|html|docx         Output format (default: pdf). html = single
                             self-contained file; docx = content fidelity.
  --strict                   Missing, remote, out-of-tree, oversized, or
                             non-regular-file images fail the run (CI mode).
  --page-numbers             "N of M" footer (default on)
  --tagged                   Accessible PDF (default on)
  --outline                  PDF bookmarks from headings (default on)
  --quiet                    Suppress progress on stderr
  --verbose                  Per-stage timings

Network:
  --allow-network            Fetch external images. Off by default: remote
                             images render as a visible blocked placeholder
                             (no tracking pixels fetch at print time).

Metadata:
  --title "..."              Document title (defaults to first H1)
  --author "..."             Author for cover + PDF metadata
  --date "..."               Date for cover (defaults to today)

When Claude should run it

Watch for markdown-to-PDF intent. Any of these patterns → run $P generate:

• "Can you make this markdown a PDF"
• "Export it as a PDF"
• "Turn this letter into a PDF"
• "I need a PDF of the essay"
• "Print this as a PDF for me"

If the user has a .md file open and says "make it look nice", propose $P generate --cover --toc and ask before running.

Debugging

• Output looks empty / blank → check browse daemon is running: $B status.
• Fragmented text on copy-paste → highlight.js output (Phase 4). Retry with --no-syntax once that flag exists. For now, remove fenced code blocks and regenerate.
• Paged.js timeout → probably no headings in the markdown. Drop --toc.
• "[remote image blocked]" placeholder in the output → add --allow-network (understand you're giving the markdown file permission to fetch from its image URLs).
• Generated PDF too tall/wide → --page-size a4 or --margins 0.75in.

Output contract

stdout: /tmp/letter.pdf          ← just the path, one line
stderr: Rendering HTML...        ← progress spinner (unless --quiet)
        Generating PDF...
        Done in 1.5s. 43 words · 22KB · /tmp/letter.pdf

exit code: 0 success / 1 bad args / 2 render error / 3 Paged.js timeout
           / 4 browse unavailable

Capture the path: PDF=$($P generate letter.md) — then use $PDF.