Writing

• Every change to someone's text traces to a confirmed finding or a source span: facts, numbers, quotes, links and the writer's meaning survive, and nothing is added that the source or brief did not supply.
• Prose in the principal's voice aims at the measured corpus model and the anchor piece and clears VoiceGate.ts and VoiceJudge.ts without being degraded to pass; stripping AI-isms alone never counts as done.
• Every Pangram number comes from a real PangramScore.ts run and is reported as a signal with its caveats, never as a pass/fail gate.
• A check that could not run (no config, no key, no Interceptor) is reported as not run, never as passed.

Uncertain routing, or a request that needs every legacy instruction, loads the full bundle (the complete guide and every intent file). Standalone detection with no rewrite intent routes to the public DetectAI skill instead; ScoreAI stays here because the publication audit runs it inline.

Loading a bundle

Before executing, load the matching bundle with the deterministic loader: bun "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/LIFEOS/TOOLS/ContextLoad.ts" Writing load BUNDLE

It returns the selected instructions, their mandatory dependencies and source hashes; follow every returned requirement. Required external references and audits still apply. Skill-local paths resolve from the skill root, LIFEOS/ paths from the install root. An unchanged section already in context needs no second read; after compaction or a source change, reload the relevant bundle.

For bundle reads, set the shell tool output budget to 30000 tokens, and a code-mode wrapper's output budget to 30000 too. A truncation warning anywhere, not only at the END CONTEXTLOAD marker, means the load did not succeed.

list shows sections and bundles; search "query" searches the preserved guide. A failed search does not establish absence: inspect the index, broaden the query, or load full. If the loader fails, read References/CompleteGuide.md and every relevant intent file directly. Never proceed on a partial load.

The skill config is LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Writing/Config.md. It names the voice directory (voice_dir, holding Corpus.md, Exemplars.md, PostExemplars.md, VoiceProfile.md, VoiceProfile.json), an optional published-content index (corpus_cli), the preview browser, and the few example phrases the gate and judge quote. With no config, VoiceGate.ts and VoiceJudge.ts stop with exit 2 and point at the guide. First-time set-up, field tables and a proof run: Setup.md. The full key and file tables are in References/CompleteGuide.md § Data & Config, loaded by the principal bundle. bun Tools/WritingConfig.ts status reports what is configured.

The env key is PANGRAM_API_KEY (ScoreAI only).

The skill's gotchas live in References/CompleteGuide.md § Gotchas, a required section in Context.json that every bundle loads.

User: "deai this draft"
→ Rewrite (rewrite bundle)
→ Profile named, findings listed, a minimal-diff rewrite and a clean second-pass audit

User: "write the intro to this post as me"
→ WriteAsPrincipal (principal bundle)
→ A draft anchored in the principal's published position, with VoiceGate and VoiceJudge exit codes and a reported Pangram score

More worked examples live in References/CompleteGuide.md § Examples, loaded by the full bundle.