feat(linkedin): v2.4.0 — editorial-reviewer agent + Step 5.5 craft gate in /linkedin:newsletter
Endring 8 from the change spec (Del 4 production, Maskinrommet). The persona resonance sweep measures reader-response (does it land?); nothing measured prose craft or narrative architecture (is it well-made?). In Del 4 every persona reported PASS, yet the editor found 8 fresh editorial points on first reading — ~6/8 craft/architecture blind spots no agent could see. v2.4.0 adds the missing editor role. New Step 5.5 (editorial-review) runs between fact-check (Step 5) and the persona sweep (Step 6): a new editorial-reviewer agent (Opus) judges two axes — prosa-handverk (em-dash density, verbatim repetition, postulated numbers, contradictions, versal-tic) + narrativ-arkitektur (concrete instantiation, theory-anchored hypotheses, series-title symmetry, equal action per addressee, un-overloaded conclusion). Returns <=10 flags as direction (never copy), each BLOCK/REWORK/NICE, operator-gated via SendUserFile. Runs before the persona sweep so the personas measure resonance instead of stumbling on craft noise. Mirrors the Maskinrommet writing-contract section C2 (bidirectional mirror rule). - agents/editorial-reviewer.md (NEW, Opus, orange) + fasit fixture (editorial-reviewer-cases.md: Del 4 v5 gold standard, 8 points -> 2 axes + severities, 3 BLOCK / 5 REWORK, 6/8 blind spots) + structural lint (7 tests). - Step 5.5 wired into commands/newsletter.md; pipeline 14 -> 15 phases. - editorial-review phase + additive editorialReview state in config/edition-state.template.json; resumption: factcheck-sweep -> Step 5.5, editorial-review -> Step 6 (spec said fact-check; canonical key is factcheck-sweep). - persona-reviewer contract unchanged: editorial-reviewer is supplementary (one measures craft, one measures response). - All doc levels synced (plugin + root README/CLAUDE.md, CHANGELOG, plugin.json 2.3.0 -> 2.4.0; agents 15 -> 16). 94 tests green. Acceptance-criterion #8 (live run on Del 4 v5) delivered as fasit fixture: a live run needs a session reload (new agent not invokable until then) + read access to the Del 4 v5 draft in Maskinrommet. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
7ebd28cb0b
commit
9df3de795c
11 changed files with 714 additions and 28 deletions
|
|
@ -6,20 +6,21 @@
|
|||
|
||||
*AI-generated: all code produced by Claude Code through dialog-driven development. [Full disclosure →](../../README.md#ai-generated-code-disclosure)*
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
A comprehensive Claude Code plugin that turns LinkedIn from a chore into a full-spectrum content engine — short-form feed posts, carousels, video scripts, and long-form newsletter editions. v2.0.0 consolidated the surface (27 → 24 commands, 16 → 14 agents) and added `/linkedin:newsletter` as a multi-session long-form orchestrator with fact-check + persona-sweep gates BEFORE lock. **v2.1.0** adds two more gates BEFORE prose to `/linkedin:newsletter` — a skeleton gate (Step 2.5) and a spine-prose gate (Step 3a) — encoding the Maskinrommet writing-contract §A discipline (premiss / problem / anbefaling / gevinst / vei videre) into the pipeline itself, so spine errors get caught in minutes at the skeleton stage instead of hours at the resonance stage or a full day post-lock. v2.2.0 hardened the longform gates with the lessons from the next production run: blocking persona hard-fails (primær «mistet meg» / doesn't own the action / jargon wall / model-name catalog → BLOCK), a post-cutoff fact-check mandate, a new Norwegian-chronicle de-AI voice-scrubber agent, render+annotate operator gates, and edition state reconciled with the global STATE.md continuity system. **v2.3.0** makes visual assets an explicit pipeline phase — new **Step 7.5 (visual-assets)** between annotation and lock: the cover (+ optional inline figures) or a carousel deck is generated and operator-gated *before* lock, so the renderer picks up `cover.png` without a post-lock re-render (pipeline 13 → 14 phases). 24 slash commands, 15 specialized agents, 9 automated hooks, and a 24-document knowledge base grounded in LinkedIn's actual algorithm signals. Updated for the January 2026 **360Brew** algorithm change, where LinkedIn now validates your profile before distributing content.
|
||||
A comprehensive Claude Code plugin that turns LinkedIn from a chore into a full-spectrum content engine — short-form feed posts, carousels, video scripts, and long-form newsletter editions. v2.0.0 consolidated the surface (27 → 24 commands, 16 → 14 agents) and added `/linkedin:newsletter` as a multi-session long-form orchestrator with fact-check + persona-sweep gates BEFORE lock. **v2.1.0** adds two more gates BEFORE prose to `/linkedin:newsletter` — a skeleton gate (Step 2.5) and a spine-prose gate (Step 3a) — encoding the Maskinrommet writing-contract §A discipline (premiss / problem / anbefaling / gevinst / vei videre) into the pipeline itself, so spine errors get caught in minutes at the skeleton stage instead of hours at the resonance stage or a full day post-lock. v2.2.0 hardened the longform gates with the lessons from the next production run: blocking persona hard-fails (primær «mistet meg» / doesn't own the action / jargon wall / model-name catalog → BLOCK), a post-cutoff fact-check mandate, a new Norwegian-chronicle de-AI voice-scrubber agent, render+annotate operator gates, and edition state reconciled with the global STATE.md continuity system. v2.3.0 makes visual assets an explicit pipeline phase — **Step 7.5 (visual-assets)** between annotation and lock: the cover (+ optional inline figures) or a carousel deck is generated and operator-gated *before* lock, so the renderer picks up `cover.png` without a post-lock re-render. **v2.4.0** adds an **editor's craft gate** — new **Step 5.5 (editorial-review)** between fact-check and the persona sweep: a new `editorial-reviewer` agent (Opus) judges *craft* (prose-craft + narrative-architecture), not reader-response, returning ≤10 flags (BLOCK / REWORK / NICE) operator-gated via `SendUserFile` so the personas measure resonance instead of stumbling on craft noise (pipeline 14 → 15 phases). 24 slash commands, 16 specialized agents, 9 automated hooks, and a 24-document knowledge base grounded in LinkedIn's actual algorithm signals. Updated for the January 2026 **360Brew** algorithm change, where LinkedIn now validates your profile before distributing content.
|
||||
|
||||
---
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [What's New in v2.4.0](#whats-new-in-v240)
|
||||
- [What's New in v2.3.0](#whats-new-in-v230)
|
||||
- [What's New in v2.2.0](#whats-new-in-v220)
|
||||
- [What's New in v2.1.0](#whats-new-in-v210)
|
||||
|
|
@ -42,6 +43,21 @@ A comprehensive Claude Code plugin that turns LinkedIn from a chore into a full-
|
|||
|
||||
---
|
||||
|
||||
## What's New in v2.4.0
|
||||
|
||||
**An editor's craft gate becomes an explicit pipeline phase.** The Del 4 production run exposed a gap the existing gates could not see: the persona resonance sweep returned 15 flags across three personas and *every persona reported PASS / ready-to-publish* — yet the editor (KTG) found **eight fresh editorial points on first reading**, and only ~25 % overlapped anything the personas had touched. The other six were **craft and narrative-architecture blind spots** no agent measured. `persona-reviewer` measures *reader response* (does it land?); nothing measured *prose craft* or *narrative architecture* (is it well-made?). v2.4.0 adds the missing role.
|
||||
|
||||
- **New `editorial-reviewer` agent** (Opus, orange) — an **editor**, not a reader. Two axes: **prosa-håndverk** (em-dash density, verbatim repetition, postulated numbers without source/hedge, internal contradictions, versal-tic — mostly grep-able) and **narrativ-arkitektur** (concrete instantiation, theory-anchored hypotheses, series-title symmetry, equally-usable action per addressee, an un-overloaded conclusion). Returns **≤10 flags** as *direction* — never rewritten copy (the jury judges, the writer writes) — each with a quote/line-ref and a **severity: BLOCK / REWORK / NICE**. The checklist is the operationalized mirror of the **Maskinrommet writing-contract §C2**. *(New agent — requires a session reload before it is invokable.)*
|
||||
- **New Step 5.5 — Editorial review** (`commands/newsletter.md`), between fact-check (Step 5) and the persona sweep (Step 6). Runs a single foreground `editorial-reviewer` call, surfaces the report to the operator via **`SendUserFile`** (the same operator-gate pattern as Steps 2.5/3a/7.5), folds approved flags in *by tightening* → v(n+1), and optionally re-runs on the cleaned version.
|
||||
- **Why before the persona sweep, not after** — the personas measure *response*. If the prose is locally messy (an em-dash thicket, a postulated number, a repeated phrase) the persona flags become *noise* — the reader stumbles on the craft defect instead of judging mobilization. Clean the craft first, and Step 6 measures what it was built to measure.
|
||||
- **Supplementary, not a replacement** — `persona-reviewer` is unchanged. One agent measures craft (5.5), one measures response (6); the role boundary is sharp (`editorial-reviewer` never flags "this won't resonate"; `persona-reviewer` never flags em-dash density).
|
||||
- **`editorial-review` phase + additive `editorialReview` state** in `config/edition-state.template.json`. Pipeline grows 14 → 15 phases; resumption stays deterministic (`factcheck-sweep` now resumes at Step 5.5).
|
||||
- **Fasit fixture + structural lint** — `agents/fixtures/editorial-reviewer-cases.md` encodes the Del 4 v5 gold standard (KTG's eight points mapped to the two axes + severities; 6/8 editorial-only blind spots), with `agents/__tests__/editorial-reviewer-fixture.test.mjs` asserting its shape (7 tests, green). The calibration target for a live run (which needs a session reload + the Del 4 v5 draft).
|
||||
|
||||
Doc/orchestration-only for the wiring — the new agent, its fasit fixture, and the lint test are the only new files; **no new runtime code**. 16 agents (was 15). Commands (24) unchanged. Backward-compatible: the only state-shape change is additive.
|
||||
|
||||
---
|
||||
|
||||
## What's New in v2.3.0
|
||||
|
||||
**Visual assets become an explicit pipeline phase.** Until now, images (cover + inline figures) were produced ad-hoc *outside* the `/linkedin:newsletter` pipeline and referenced by hand — even though a cover is mandatory and has to coordinate with the text. v2.3.0 adds **Step 7.5 — Visual assets** between annotation (Step 7) and lock (Step 8), so visuals are resolved *before* the edition locks.
|
||||
|
|
@ -232,7 +248,7 @@ All 24 commands use colon notation: `/linkedin:post`, `/linkedin:quick`, etc.
|
|||
|
||||
## Agent Architecture
|
||||
|
||||
The plugin delegates specialized work to 15 purpose-built agents. Each agent has its own model assignment, color identity, and focused responsibility.
|
||||
The plugin delegates specialized work to 16 purpose-built agents. Each agent has its own model assignment, color identity, and focused responsibility.
|
||||
|
||||
| Agent | Model | Color | Primary Responsibility |
|
||||
|-------|-------|-------|----------------------|
|
||||
|
|
@ -249,6 +265,7 @@ The plugin delegates specialized work to 15 purpose-built agents. Each agent has
|
|||
| `post-feedback-monitor` | Haiku | Lime | Post-publish 48h monitoring and real-time interventions |
|
||||
| `video-scripter` | Sonnet | Violet | Video script creation with pacing and visual cues |
|
||||
| `fact-checker` | Opus | Brown | Factual-claim verification against primary/credible sources, post-cutoff web-search mandate (longform) |
|
||||
| `editorial-reviewer` | Opus | Orange | Editor's craft gate (v2.4, Step 5.5, before persona sweep): **prosa-håndverk** + **narrativ-arkitektur**, ≤10 flags BLOCK/REWORK/NICE as direction, operator-gated via `SendUserFile`; mirrors Maskinrommet §C2 (longform) |
|
||||
| `persona-reviewer` | Opus | Olive | Reader-persona **skeleton** (v2.1, before prose) + **resonance** (before lock) + **hook-conversion** (after lock) gate, blocking hard-fail list (longform) |
|
||||
| `voice-scrubber` | Opus | Red | De-AI scrub + Norwegian-chronicle voice-drift correction; gold standard = approved Norwegian editions, not the English post corpus (longform, v2.2) |
|
||||
|
||||
|
|
@ -268,7 +285,7 @@ trend-spotter --> content-planner --> differentiation-checker --> content-optimi
|
|||
|
||||
Parallel support agents: `strategy-advisor`, `analytics-interpreter`, `network-builder`, `content-repurposer`, `video-scripter`.
|
||||
|
||||
Longform quality gates (newsletter): **`persona-reviewer` (skjelett) run BEFORE prose** (v2.1, Step 2.5) → `voice-scrubber` de-AI / chronicle-voice scrub (v2.2, Step 4) → `fact-checker` (Step 5) → `persona-reviewer` (resonance) run BEFORE lock (Step 6) → `persona-reviewer` (conversion) run AFTER lock on the hook (Step 9).
|
||||
Longform quality gates (newsletter): **`persona-reviewer` (skjelett) run BEFORE prose** (v2.1, Step 2.5) → `voice-scrubber` de-AI / chronicle-voice scrub (v2.2, Step 4) → `fact-checker` (Step 5) → **`editorial-reviewer` craft gate run BEFORE the persona sweep** (v2.4, Step 5.5) → `persona-reviewer` (resonance) run BEFORE lock (Step 6) → `persona-reviewer` (conversion) run AFTER lock on the hook (Step 9).
|
||||
|
||||
> **Note (agent invocation + reload):** Commands invoke agents by their **namespaced**
|
||||
> type — `subagent_type: linkedin-thought-leadership:<name>`, never the bare name. And a
|
||||
|
|
@ -578,6 +595,7 @@ Scheduled posts are tracked in `assets/drafts/queue.json`:
|
|||
|
||||
| Version | Date | Highlights |
|
||||
|---------|------|-----------|
|
||||
| **2.4.0** | 2026-05-29 | Editor's craft gate as an explicit pipeline phase. New **`editorial-reviewer` agent** (Opus) + **Step 5.5 — Editorial review** in `/linkedin:newsletter` (between fact-check and the persona sweep): two axes — **prosa-håndverk** (em-dash density, verbatim repetition, postulated numbers, contradictions, versal-tic) + **narrativ-arkitektur** (concrete instantiation, theory-anchored hypotheses, series-title symmetry, equal action per addressee, un-overloaded conclusion); ≤10 flags BLOCK/REWORK/NICE as direction; operator-gated via `SendUserFile`; mirrors Maskinrommet §C2. Motivated by Del 4 (every persona PASS, yet 8 fresh editor points, ~6/8 craft/architecture blind spots). `editorial-review` phase + additive `editorialReview` state. Pipeline 14 → 15 phases; 15 → 16 agents. New agent + fasit fixture + lint test the only new files; commands (24) unchanged. |
|
||||
| **2.3.0** | 2026-05-28 | Visual assets as an explicit pipeline phase. New **Step 7.5 — Visual assets** in `/linkedin:newsletter` (between annotation and lock): cover (+ optional inline figures) or carousel deck, generated (default `mcp-image`; external `cover-raw.png` accepted) and operator-gated via `SendUserFile` BEFORE lock so `build-linkedin.mjs` picks up `cover.png` without a post-lock re-render. Explicit `format: "carousel"` branch reusing `build-carousel.mjs`. New `config/image-credit-caption.template.md`; additive `visualAssets` state + naming convention (`cover.png` / `cover-v<N>-kandidat.png` / `cover-raw.png` / `fig<N>.png`). Pipeline 13 → 14 phases. Doc/orchestration-only (no new code); commands (24) + agents (15) unchanged. |
|
||||
| **2.2.0** | 2026-05-28 | Longform gates hardened (2nd production run). Persona gate blocking with explicit hard-fail list (primær mistet meg / doesn't own action / sjargong-mur / modell-navne-katalog → BLOCK; «JA med forbehold» = NEI). Fact-check post-cutoff web-search mandate + high-frequency-error checklist. New `voice-scrubber` agent (Opus): de-AI scrub + Norwegian-chronicle voice-drift, gold standard = approved Norwegian editions (NOT the English post corpus). Render+annotate operator gates (Steps 2.5/3a). Edition state reconciled with STATE.md (ONE-system); `edition-HANDOVER.template.md` deleted. 14 → 15 agents; commands unchanged (24). |
|
||||
| **2.1.0** | 2026-05-28 | Skeleton gate BEFORE prose in `/linkedin:newsletter`. New Step 2.5 (skeleton + section pitch, operator-gate + persona-skjelett-sweep) and Step 3a (spine prose, operator-gate) split the old Step 3 into pre-prose stages with their own gates. New `persona-reviewer` mode (`skjelett`). Pipeline grows 11 → 13 phases; commands and agents unchanged in count (24, 14). Encodes the Maskinrommet writing-contract §A discipline (premiss / problem / anbefaling / gevinst / vei videre) into the pipeline. Empirically motivated by the Seres-serien Del 3 + Del 4 spine-rework cost. |
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue