Use this skill when promoting Jiang Lens proposals, glossary entries, model claims, ledger items, or chronology-sensitive material into canonical content after source grounding and review records exist.
Scanned 5/27/2026
Install via CLI
openskills install apresmoi/jianglens---
name: jiang-canon-promotion
description: Use this skill when promoting Jiang Lens proposals, glossary entries, model claims, ledger items, or chronology-sensitive material into canonical content after source grounding and review records exist.
---
# Jiang Canon Promotion
Use this only when material is ready to move from draft/proposal/review into canonical project state.
This skill protects the project from turning agent interpretation into canon too early.
## Inputs
- source refs with dates,
- processed transcripts or article text,
- semantic proposals,
- reviews from `content/workflow/reviews/`,
- existing canon/glossary/ledger material,
- public docs that may need links to promoted entries.
## Canon Rule
Canonical Jiang lens material must cite Jiang-authored or Jiang-spoken source spans.
Do not promote:
- unsupported synthesis,
- undated latest-position claims,
- external commentary as Jiang canon,
- an averaged summary that erases chronological change,
- quoted literary/source material as Jiang's own position unless Jiang's gloss supports it.
## Promotion Flow
1. Identify the proposal and exact target:
```text
canon:model/<slug>
glossary:<slug>
ledger:prediction/<slug>
```
2. Verify source refs exist and are dated enough for the claim.
3. Compare older and newer source positions when chronology matters.
4. Confirm review records address grounding and consistency.
5. Write or update canonical files under `content/lens/canon/`, `content/lens/glossary/`, or `content/lens/ledger/`.
6. Record the accepted change in `content/workflow/promotions/`.
7. Update public docs only where useful for readers.
## Chronology
If Jiang said A in 2020 and B in 2022, do not collapse that into "Jiang believes B" unless B is explicitly the latest dated position and the old position remains visible as historical evidence.
Promotion should preserve:
- older formulation,
- newer formulation,
- what changed,
- whether Jiang explains the change,
- latest dated position.
## Validation
Run:
```bash
node ops/scripts/compile-content.mjs
node ops/scripts/validate-content.mjs
cd website && npm run build
```
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.