Commit graph

52 commits

Author SHA1 Message Date
7ebd28cb0b feat(linkedin): v2.3.0 — Step 7.5 visual-assets phase in /linkedin:newsletter
Endring 7 from the change-spec: make visual assets an explicit pipeline
phase. New Step 7.5 (visual-assets) between annotation (Step 7) and lock
(Step 8): cover (+ optional inline figures) or carousel deck, generated and
operator-gated BEFORE lock so build-linkedin.mjs picks up cover.png at lock
without a post-lock re-render. Pipeline 13 → 14 phases.

- commands/newsletter.md: Step 7.5 section, pipeline overview + build-status,
  resumption table (annotation → 7.5; new visual-assets → 8), Step 8
  precondition, reference-file list.
- config/edition-state.template.json: visual-assets phase + additive
  articles.NN.visualAssets schema (format / cover / figures / carousel).
- config/image-credit-caption.template.md (new): motif + credit + caption
  table, honest-about-AI credit, naming convention.
- Two generation routes, no lock-in: default mcp-image (cover-v<N>-kandidat.png)
  or external cover-raw.png. Operator-gate via SendUserFile → cp to cover.png.
  Carousel branch reuses render/build-carousel.mjs.
- Doc/orchestration-only — no new code. Commands (24) + agents (15) unchanged.
- Version sync 2.2.0 → 2.3.0 across plugin.json, CHANGELOG, README, CLAUDE.md,
  root README + root CLAUDE.md.

Correction: spec claimed build-linkedin.mjs handles fig1-4; verified it does
NOT — it embeds only cover.png by fixed name; figures are referenced in the
draft markdown and uploaded manually. Step 7.5 documents actual behavior.

All 8 acceptance criteria met. JSON valid (14 phases); 20/20 render tests pass.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-28 22:49:19 +02:00
4ed9717627 feat(linkedin): v2.2.0 — harden longform gates from 2nd production run
Implements the 6-change spec from the Seres-serien production
(linkedin-plugin-endringsspec.md). All acceptance criteria met.

1. Avoid-patterns (modell-/navne-katalog, completeness-over-reader-action,
   self-referential overhead openings) → longform-quality-rules.md (rule 1+3)
   + user-profile.template.md.
2. Persona gate now BLOCKING with explicit hard-fail list (primær mistet meg /
   doesn't own action / sjargong-mur / modell-navne-katalog → BLOCK;
   "JA med store forbehold" = NEI) → persona-reviewer.md + personas.template.md.
3. Fact-check declared orthogonal to narrative strength + post-cutoff
   web-search mandate + high-frequency-error checklist → fact-checker.md.
4. NEW agent voice-scrubber.md (Opus) — de-AI scrub + Norwegian-chronicle
   voice-drift; gold standard = approved Norwegian editions, NOT the English
   post corpus. Wired into newsletter.md Step 4.
5. Operator gates = render+annotate rounds (build-html.mjs to file://) as
   primary flow, AskUserQuestion as receipt/fallback → newsletter.md 2.5+3a.
6. Edition state reconciled with STATE.md (ONE-system). edition-HANDOVER
   template deleted; narrative to <serie>/STATE.md, machine data
   (factcheckLog, personaSweep, immutableRules) to edition-state.json.

Agents 14 to 15; commands unchanged (24). Backward-compatible (additive
state-shape only). Docs updated across all three levels + CHANGELOG.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-28 20:50:56 +02:00
2a27a7cd6a feat(linkedin): v2.1.0 — skeleton + spine-prose gates BEFORE prose in /linkedin:newsletter
Two new pipeline phases gate the spine before any prose is written:

- Step 2.5 — Skeleton + section pitch: writes <serie>/NN-skjelett.md with
  the five-line spine (premiss / problem / anbefaling / gevinst / vei
  videre) + one-line section pitches. Operator-gate (JA / REVIDER / NEI)
  AND parallel persona-skjelett-sweep must both return JA before the
  pipeline can advance.
- Step 3a — Spine prose: one paragraph per section against the gated
  skeleton, ~20-30% of final edition length. Operator-gate on whether the
  axis lands now that there is prose on it. Old Step 3 (Draft) split into
  3a (spine) and 3b (full expansion); 3b owns the multi-session
  draft-cursor logic.

Third persona-reviewer mode added: skjelett (alongside resonans + konverter).
Five spine axes scored HOLDER / TVILER / MANGLER, max 3 direction-only flags,
per-pitch section-pay-in check. Reads the skeleton + pitches only.

Pipeline grows from 11 to 13 phases; commands (24) and agents (14) counts
unchanged. Encodes the Maskinrommet writing-contract section A discipline
(premiss / problem / anbefaling / gevinst / vei videre) into the pipeline.

Empirically motivated by the Seres-serien Del 3 + Del 4 production:
a spine error caught at the skeleton stage costs 5-15 min, the same
error caught at Step 6 (resonance) costs 4-12 h, post-lock it costs a
day of cascading rework (delingstekst, hooks, carousel, doc refs).

Backward-compatible: existing editions stop at currentPhase: "research"
and now resume at Step 2.5 instead of Step 3 — an intended deterministic
improvement, never a contract break. Steps 1, 2, 4-10 bit-for-bit
unchanged. Renderers (build-html.mjs, build-linkedin.mjs) untouched.

New phase strings in edition-state.template.json _doc.phases:
- skeleton-pitch (between research and draft)
- spine-prose (between skeleton-pitch and draft)

Files changed (10):
- plugin.json: 2.0.0 -> 2.1.0
- CHANGELOG.md: new [2.1.0] entry
- CLAUDE.md (plugin + marketplace): pipeline 11->13 phases noted
- README.md (plugin + marketplace): What's New v2.1.0 + version row
- agents/persona-reviewer.md: third mode skjelett added; resonans + konverter unchanged
- commands/newsletter.md: Step 2.5 + 3a + 3b sections, resumption + pipeline tables
- config/edition-state.template.json: 11 -> 13 phases in _doc.phases
- references/longform-quality-rules.md: Rule 8 (Skjelett foer prosa)

Verification: 9/9 criteria PASS pre-commit. Phase strings consistent
across template + command + resumption table. Renderer files git-untouched.
All 11 original step headings preserved (Step 0/1/2/4-10).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 10:09:47 +02:00
8de481399e chore(linkedin): v2.0.0 — import trim, router gating, full doc pass (S20) 2026-05-28 06:53:55 +02:00
930836597e refactor(linkedin): merge analytics + engagement agents 2→1 each (S19)
- analytics-interpreter absorbs performance-reporter (interpret/report modes,
  identical data sources): mode-selector + both output templates kept inline.
- engagement-coach absorbs comment-strategist (5x5x5 + first-hour + CEA
  commenting + target selection + scoring + quality scorecard + daily
  routine). Self-ref at engagement-coach.md:24 rewritten — target is now
  in-file. Model upgraded from haiku to sonnet (absorbed deeper work);
  tools union: Read, Glob, WebSearch.
- 7 ref-files reconciled: commands/linkedin.md (router rules merged),
  skills/linkedin-analytics (row dropped), skills/linkedin-thought-leadership
  (2 rows merged), skills/linkedin-networking (row dropped), CLAUDE.md
  (agents table 16→14, merged rows), README.md (agents table, flow diagram,
  intent table, analytics consumers line), references/glossary.md (3 'Used in'
  refs), scripts/test-runner.sh (EXPECTED_AGENTS list reconciled to current
  14 — also closed lingering S5/S6 gaps for fact-checker/persona-reviewer/
  video-scripter, removed already-deleted content-tracker/personalization-scorer),
  docs/agents-capability-matrix.md (full restructure: header count 16→14,
  agent table, capability grid columns + capabilities, pipeline diagram,
  intent table, model selection table — fixed STATE residual #1 on the
  tracker/pers-scorer stale columns in the same pass).
- Q2 decision (video-scripter → content-repurposer?): KEEP separate.
  Distinct invocation paths (/linkedin:video vs format conversion), distinct
  outputs (timed video script with pacing+captions vs format-translation
  artifact), and newsletter.md already uses content-repurposer for prose
  drafting independently of video-scripter. Net agents/ 16→14.
- agents/README.md dropped from Files (moved to docs/agents-capability-matrix.md
  in S14); literal Verify exits 2 on missing path (logged), corrected Verify
  passes 4/4 predicates. Manifest audit: 2/2 expected paths exist, 13 'CEA'
  occurrences in engagement-coach.md.
- gitleaks: clean.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 06:19:20 +02:00
0b44f219b6 refactor(linkedin): absorb authority into strategy + profile canon (S18)
- commands/strategy.md: extend frontmatter with authority triggers; insert
  Step 3.6 Authority Building (signature content map, greatest hits, derivative
  planning, content + network signals, action plan, monthly scorecard); add
  algorithm-signals-reference.md to Reference Files.
- commands/audit.md: Step 5.5 trajectory-review and Step 7 report-block
  trajectory section now route to /linkedin:strategy (the canon); Step 6
  profile-alignment routes to /linkedin:profile (the canon); drop
  trajectory-strategy-adjustments.md + algorithm-signals-reference.md from
  loaded references (canons own them).
- commands/analyze.md: 'If Profile-Content Mismatch' subsection routes to
  /linkedin:profile for the per-section checklist; quick-triage list kept.
- commands/authority.md: removed (absorbed by strategy.md).
- commands/linkedin.md: drop authority table row, merge 'Build authority'
  into AskUser item #10 (Growth strategy & authority), renumber 14-23 to
  13-22, broaden strategy routing trigger keywords, drop standalone
  authority routing rule.
- skills/linkedin-strategy/SKILL.md, skills/linkedin-thought-leadership/SKILL.md,
  CLAUDE.md, README.md: drop /linkedin:authority rows; widen /linkedin:strategy
  descriptions to reflect new scope.

Verification:
- Literal Verify (plan.md:704) exits 1 (expected inversion).
- Corrected predicate (test ! -f && ! grep -rqn …) exits 0 — clean.
- Manifest: commands/strategy.md present; [Aa]uthority match count = 24.
- Hooks: python3 hooks/scripts/compile-hooks.py --check → clean.
- Command count: 25 → 24.
- End-to-end Verification §849 (templates|publish|authority|collab|speaking)
  grep across commands/ agents/ skills/ hooks/ README.md CLAUDE.md → empty.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 06:01:43 +02:00
d5ee9d19fa refactor(linkedin): merge collab + speaking into outreach (S17)
Step 18 (fasit S17): merged commands/collab.md + commands/speaking.md
into a single commands/outreach.md covering both tracks under one
outreach/pitch paradigm. Structural twins: same outreach/pitch flow
(readiness → identify → score → format/abstract → outreach by
temperature → production/portfolio → engagement-pod warning →
pipeline tracker → network/progression → results dashboard) with
track-specific detail at each step.

Capability checklist: every function of both predecessors preserved:
- Collab: 5-item readiness, partner search + 25-pt rubric,
  12 formats across 4 maturity tiers, cold/warm/established outreach,
  DM amplification protocol, 5-phase co-creation workflow,
  shared drafting ground rules, pipeline board, health signals,
  Inner Circle tiers, long-term partnership framework.
- Speaking: 100-pt readiness scorecard, event/CFP search +
  research template, Nordic/European tech conference calendar,
  4 talk abstract templates, speaker positioning content calendar,
  demo reel strategy, speaker bio variants (50/100/200 words),
  CFP cover note + organizer outreach (cold/warm),
  post-speaking follow-up sequence, pipeline tracker,
  progression ladder (4 levels).
- Both: engagement-pod warning (post-Mar-2025), quarterly results
  dashboard with both tracks.

Removed commands/collab.md, commands/speaking.md.

Reconciled all 16 route-refs across plugin (collab 8, speaking 8):
- commands/linkedin.md: table row, priority list (items 16-17 → 16),
  routing rules (lines 177-178 → one rule), removed 'outreach' keyword
  from network-builder agent suggestion (now belongs to /linkedin:outreach).
- skills/linkedin-thought-leadership/SKILL.md: pillar table + all-commands
  table (lines 30, 140, 142).
- skills/linkedin-networking/SKILL.md: commands table (lines 29-30).
- CLAUDE.md: commands table (lines 63-64).
- README.md: feature bullet (line 68), commands table (lines 168-169),
  skills pillar table (line 289), ToS table (line 514).

Verify: corrected predicate (test ! -f X && test ! -f Y && ! grep -rqn)
exit 0. Literal Verify (plan.md:681) exit 1 due to the same exit-inversion
bug observed at Step 16/17 — logged for plan-pass at Step 21.

Manifest audit PASS: commands/outreach.md present; [Ss]peaking 40 hits;
min_file_count=1 satisfied; forbidden/bash checks vacuous.

Net commands/: 26 → 25 (matches plan).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 05:41:09 +02:00
e4aa5a61c2 refactor(linkedin): merge publish into calendar — reconcile hook refs (S16)
Step 17 of voyage-build (S16 in plan). publish.md absorbed into calendar.md
as an inline action (Mark as Published flow: queue update, state update,
first-hour battle plan) reusing the same queue-manager.mjs + state-updater.mjs
primitives that publish.md called. calendar.md frontmatter triggers extended
with the publish trigger words; quick-routing block jumps straight to the
publish action when the user prompt names it.

All 21 route-refs reconciled across the 9 expected files, with the 9
hook-script refs (5 in session-start.mjs, 2 in posting-reminder.mjs, 1 in
user-prompt-context.mjs, 1 in hooks/prompts/state-update-reminder.md)
rewritten to call /linkedin:calendar so the runtime guidance no longer
points at a dead command. compile-hooks.py --check reports clean (no
type: prompt hook changes touched hooks.json).

Verify (intent: zero stray refs, file gone): exit 0. Literal Verify in
plan.md:727 logged exit 1 (same exit-inverted && pattern as S15 plan.md:635
— logged for plan-pass at Step 21).

Manifest audit: PASS (expected_paths=calendar.md present; must_contain
[Pp]ublish: 17 matches in calendar.md).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 05:27:36 +02:00
ddd84e4501 refactor(linkedin): merge templates into quick (S15) 2026-05-28 00:07:09 +02:00
92e0a0b4f5 fix(linkedin): close dogfood friction (S14)
Close all 9 friction points from the S13 newsletter dogfood (operator
elected to fix F6-F9 rather than defer):

- F1: namespace all subagent_type calls in newsletter.md to
  linkedin-thought-leadership:<name> (4 sites + canonical note)
- F2: document agent invocation form + reload requirement in CLAUDE.md
  + README.md (reload itself is an operator action)
- F3: add edition-config / edition-delingstekst / edition-HANDOVER
  templates under config/ + wire into Steps 0 and 8 + footer
- F4: reconcile draft path to <serie>/NN-utkast.md (series root)
- F5: de-hardcode series root (explicit arg / LTL_SERIES_ROOT / default)
- F6: config-derive carousel editions (remove Seres CAROUSEL set);
  correct samle comment
- F7: build-html.mjs exits non-zero when zero HTML produced
- F8: guard parseDelingstekst (graceful ENOENT) + correct Step 8 wording
- F9: relocate agents/README.md -> docs/agents-capability-matrix.md

Re-tested: 87/87 plugin tests pass; build-html/build-linkedin behavior
re-verified live. Per-item outcomes logged in dogfood-S13-friction.md.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 23:37:39 +02:00
adfa2085fc test(linkedin): dogfood newsletter pipeline end-to-end (S13)
Dogfood mot throwaway-fixture (docs/review/dogfood-serie/, gitignored),
syntetisk tema. Deterministisk ryggrad (build-html/build-linkedin) kjørt
ekte og passerte; gate-laget (fact-check/persona) BLOKKERT — escalert, ikke
tvunget grønt. 9 friksjonspunkter (2 BLOCKER, 3 MAJOR, 4 MINOR) med order-proof
(persona-sweep wiret FØR lås) og per-punkt implicated file for S14 revert-mål.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 22:57:13 +02:00
8d25dd908e feat(linkedin): longform quality rules + edition resumption wiring (S12) 2026-05-27 22:30:42 +02:00
e031fae3de refactor(linkedin): single newsletter entry + skill trigger + router row (S11) 2026-05-27 22:08:16 +02:00
f24c6e30f7 feat(linkedin): newsletter Step 7-10 lock, delivery, hook-gate, schedule (S10) 2026-05-27 21:42:22 +02:00
fba70870ce feat(linkedin): newsletter Step 5-6 fact-check + persona sweep before lock (S9) 2026-05-27 21:33:43 +02:00
39ae875b96 feat(linkedin): newsletter Step 3-4 draft + consistency (S8) 2026-05-27 21:25:42 +02:00
9b1669a3f6 feat(linkedin): newsletter command skeleton Step 0-2 (S7) 2026-05-27 21:10:39 +02:00
ca5aa4e698 refactor(linkedin): edition-state schema + retire 2 deterministic agents to scripts (S6)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 20:26:14 +02:00
1faffac303 feat(linkedin): add persona-reviewer agent (2 modes) + fixture (S5) 2026-05-27 20:08:06 +02:00
be03d44c52 feat(linkedin): add fact-checker agent + fixture (S4) 2026-05-27 19:42:41 +02:00
0dc3f903f9 feat(linkedin): add reusable persona library template (S3) 2026-05-27 19:34:39 +02:00
36ad116e43 docs(ltl): add Maskinrommet field-experience brief for upgrade
Krav fra produksjonserfaring (Seres-serien): blokkerende persona-gate,
voice unngaa-moenstre, paastands-ledger + verifiseringsdisiplin, artikkel-skjelett.
Komplementaer til brief-fullspektrum-innholdsmotor.md.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 00:52:05 +02:00
6e6ed7dd4e feat(linkedin): generalize build-linkedin to read edition-config.json (S2) 2026-05-26 23:15:26 +02:00
c225ea1dba feat(linkedin): generalize build-html annotation renderer — tables, headings, inline code (S1a)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-26 23:05:54 +02:00
b4aaf7ae82 docs(linkedin): restructure v2.0.0 plan Execution Strategy → 21 discrete sessions (1 step = 1 session)
Each Session N now maps 1:1 to Step N so /trekcontinue advances exactly one step per session and never runs a full wave at once. Steps + manifests unchanged; validator valid:true. Deprecate NEXT-SESSION-PROMPT in favor of STATE.md handoff.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-26 22:27:08 +02:00
6eff5e8e21 feat(linkedin): migrate render scripts + fonts into plugin (S1)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-26 22:11:38 +02:00
098726d397 docs(linkedin): Voyage executable plan for v2.0.0 build (21 sessions)
Production plan for lifting LTL v1.2.0 -> v2.0.0 (full-spectrum content
engine + /linkedin:newsletter + render migration + net-fewer commands/agents).

- docs/voyage-build/{brief.md,plan.md}: Voyage project dir. plan.md = 21 steps
  (S1..S20+S1a), each with a per-step Manifest. Validator: valid, 0 warnings.
- docs/{brief,plan}-fullspektrum-innholdsmotor.md + voyage-build-brief.md:
  the directional brief, hardened fasit (authoritative WHAT), and Voyage input.
- Built via /trekplan: confirmatory swarm verified the fasit against real files
  (13 corrections folded in); scope-guardian ALIGNED; plan-critic REPLAN ->
  revised (3 blockers + 5/6 major + 4/5 minor closed).
- plan.html (annotation surface) left untracked: regenerable via annotate.mjs.

Next: /trekexecute --fg --project docs/voyage-build (fresh session) -> S1.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-26 21:38:52 +02:00
f460814fe9 chore: WIP marketplace doc adjustments across plugins
Pre-trekexecute snapshot of in-progress CLAUDE.md/SKILL.md edits and
extracted docs/ files. Captured as one commit so /trekexecute claude-design
can run against a clean working tree.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-18 12:04:02 +02:00
6c94a1629f docs: add Communication patterns section to all plugin CLAUDE.md
Standardize named-markdown-link guidance across all plugins so file://
references render as independently clickable links in terminals like
Ghostty (bare file:// URLs only make the first clickable).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 21:01:45 +02:00
490d4eddc6 docs: introduce GOVERNANCE.md and unify fork-and-own blurb
Establish a single governance document at marketplace root and copy
it into each of the 9 plugins so every plugin folder remains 100%
self-contained. Replace the inconsistent provocative blurb across
all READMEs with a uniform fork-and-own paragraph that links to
the local GOVERNANCE.md.

[skip-docs]

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-03 14:57:00 +02:00
Kjell Tore Guttormsen
9ea5a2e6c6 chore(privacy): scrub real-org references from plugin internals (phase 2)
Same bulk replacement applied to plugin-internal KB, examples, fixtures,
tests, and docs. Real organization names, persona names, internal system
identifiers, and domain-specific terms replaced with fictional generic
public-sector entity (DDT) and generic terminology.

Scope:
- okr/ — examples, governance, framework, integrations, sources
- ms-ai-architect/ — KB references (engineering, governance, security,
  infrastructure, advisor), tests/fixtures, agents, docs
- linkedin-thought-leadership/ — voice samples, network-builder,
  examples (genericized identifying headlines to "[your organization]")
- llm-security/ — research notes, scan report

Manual genericization beyond bulk replace:
- okr SKILL.md "Primary user / Domain" — generic Norwegian public sector
- linkedin-voice SKILL.md headline placeholder
- network-builder.md headline placeholder
- high-engagement-posts.md voice sample employer line + hashtag

Phase 3 (factual-attribution review) remains: a few KB files attribute
publicly known transport-sector docs/datasets (e.g. håndbok V440, NVDB)
to the fictional DDT after bulk replace. Needs manual semantic review
to either remove or restore correct citation without re-introducing
affiliation references.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-03 04:28:15 +02:00
Kjell Tore Guttormsen
445a632d39 docs: add AI-generated code disclosure to marketplace and all plugins
Transparency: all code in this marketplace is produced by Claude Code
through dialog-driven development. Root README gets a full disclosure
section; each plugin README gets a one-line disclosure linking back to
the marketplace section.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-19 19:27:05 +02:00
Kjell Tore Guttormsen
72f2e8f6c9 docs(linkedin): update documentation for v1.2.0 friction reduction release
Version bump v1.1.0 → v1.2.0 across all docs (CLAUDE.md, README.md,
root README.md, plugin.json, CHANGELOG.md). Documents new scripts
(state-updater, clipboard-helper, ical-generator), reduced interactive
steps, auto-clipboard, progressive onboarding, and MCP carousel pipeline.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-11 01:01:13 +02:00
Kjell Tore Guttormsen
8606abf5ee feat(linkedin): progressive onboarding — hide score until 3+ posts, suppress voice guardian noise
- session-start.mjs: count published posts, gate personalization score
  display and reminder behind >= 3 published posts
- voice-guardian.md: suppress LOW CONFIDENCE messages, silently skip
  drift scoring when < 5 samples
- state-file.template.md: add "general" default for expertise_areas
- onboarding.md: show friendly defaults message for new users, move
  score dashboard to returning-user flow

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-11 00:50:18 +02:00
Kjell Tore Guttormsen
d7a562fc45 feat(linkedin): auto-prune content history entries older than 90 days
Adds pruneContentHistory call to session-start.mjs after week rollover.
Uses dynamic import() for state-updater.mjs. Non-critical: silently
skipped on failure.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-11 00:43:08 +02:00
Kjell Tore Guttormsen
1474948ef8 feat(linkedin): integrate state-updater.mjs across all commands and hooks
Replace manual YAML editing instructions with deterministic
state-updater.mjs calls in 8 content commands (post, quick, react,
pipeline, first-post, video, publish, carousel) and 2 hook prompts
(state-update-reminder, post-creation-automation). Batch.md gets note
that state updates happen at publish time.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-11 00:42:17 +02:00
Kjell Tore Guttormsen
aa5cca9cf6 feat(linkedin): add state-updater.mjs — deterministic state mutations with tests
Pure functions for post tracking (streak, week rollover, first_post_date),
content history pruning, and follower count updates. 19 tests green.
Follows week-rollover.mjs pattern (pure functions) + queue-manager.mjs
pattern (I/O wrapper with atomic writes).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-11 00:40:16 +02:00
Kjell Tore Guttormsen
b3979d0e5d feat(linkedin): generate iCal file during batch creation
Step 5b in batch.md generates a .ics calendar file from the queue,
giving users 15-minute reminders in their calendar app before each
scheduled post. Supports macOS Calendar, Google Calendar, Outlook.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-11 00:28:00 +02:00
Kjell Tore Guttormsen
8e759fb373 feat(linkedin): add ical-generator.mjs — RFC 5545 calendar file generation
Pure-function iCal generator with CRLF endings, line folding at 75 octets,
VALARM reminders, VTIMEZONE, and special character escaping. 16 tests green.
Standalone CLI mode: node ical-generator.mjs --from-queue --output path.ics

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 18:38:20 +02:00
Kjell Tore Guttormsen
aca312ea57 feat(linkedin): add MCP image pipeline to carousel command
Add Step 5.5 (Generate Slide Images) using mcp-image Nano Banana Pro.
Each slide is generated with template-specific styling at 3:4 aspect
ratio. Graceful degradation: if mcp-image unavailable, falls back to
text-only output with manual design guide (existing behavior).

- mcp__mcp-image__generate_image added to allowed-tools
- Template-aware visual styles (5 templates → 5 visual directions)
- Images saved to assets/drafts/carousel-[date]-[slug]/
- Step 6 branches: generated images → publish instructions, no images → design guide
- Removed interactive AskUserQuestion from refinement (friction reduction)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 15:49:35 +02:00
Kjell Tore Guttormsen
b0df1ba304 test(linkedin): verify mcp-image text-overlay capability for carousel slides
Text overlay VERIFIED: Nano Banana Pro renders readable text on dark
gradient backgrounds at 3:4 aspect ratio (closest to LinkedIn 4:5).
Header and subtitle both legible. Mermaid Chart available but untested.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 15:29:28 +02:00
Kjell Tore Guttormsen
10b70dba10 feat(linkedin): reduce interactive steps in quick, react, pipeline commands
quick.md:
- Replace 8-option post type menu with context inference
- Auto-select CTA based on post type
- Remove proactive alternative version offering
- AskUserQuestion: 0 in main flow (was 1 implicit menu)

react.md:
- Auto-select strongest angle instead of 3-option AskUserQuestion
- Replace 6-option refinement AskUserQuestion with plain text options
- Same treatment for comparison path (Step 4b)
- AskUserQuestion: 1 in main flow (multi-URL only, was 3)

pipeline.md:
- Skip ideation ask if topic provided with command invocation
- Auto-propose planned topic without AskUserQuestion
- Inline angle selection (auto-select strongest)
- AskUserQuestion: 2 in main flow (ideation fallback + scheduling, was 3)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 15:18:50 +02:00
Kjell Tore Guttormsen
180e2fb4c2 feat(linkedin): reduce post.md to max 2 interactive steps
- Skip topic ask if user provided one with command invocation
- Auto-select strongest angle instead of 3-option AskUserQuestion menu
- Infer format from content type instead of interactive selection
- Present ONE draft without proactive alternative versions
- Replace refinement AskUserQuestion with plain text options

Net result: 0 AskUserQuestion calls in main flow (was 2).
User provides topic → gets ONE draft → clipboard-ready.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 15:16:49 +02:00
Kjell Tore Guttormsen
dcaa0d13c6 feat(linkedin): add auto-clipboard on all content commands
Adds Bash to allowed-tools and clipboard-helper.mjs auto-copy to:
post.md, quick.md, react.md, pipeline.md, first-post.md,
video.md, multiplatform.md, carousel.md.

Each command auto-copies the final post/caption text to clipboard
after presenting the draft. Replaces manual copy-paste instructions
in first-post.md (=== COPY FROM HERE ===) with auto-copy.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 15:12:19 +02:00
Kjell Tore Guttormsen
214675d0a0 feat(linkedin): add clipboard-helper.mjs — cross-platform clipboard utility
TDD: 13 tests written first, then implementation.
Exports copyToClipboard(text) and clipboardAvailable() — never throws.
Supports darwin (pbcopy), win32 (clip), linux (xclip/xsel fallback).
Dual standalone/import mode following personalization-score.mjs pattern.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-10 15:08:42 +02:00
Kjell Tore Guttormsen
34bb4e5971 docs: standardize installation instructions across all plugins
All 6 plugin READMEs now use identical installation section:
marketplace-first approach with /plugin browsing, then direct
settings.json as alternative. Replaces inconsistent mix of
git clone, plugin add, and JSON-only instructions.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-08 15:10:24 +02:00
Kjell Tore Guttormsen
fd5f393a31 chore: add root .gitignore, untrack session state files
REMEMBER.md, TODO.md, and ROADMAP.md are local session state files
that should not be tracked in git. Untrack the two previously
committed ROADMAP.md files (linkedin, ultraplan) and add root
.gitignore to prevent future tracking.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-08 13:00:36 +02:00
Kjell Tore Guttormsen
5be9c8e47c feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.

New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.

Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.

Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-08 08:58:35 +02:00
Kjell Tore Guttormsen
1a8cc1942c feat(linkedin-thought-leadership): v1.1.0 — Q2 2026 feature release
9 improvements across 3 tracks:

Onboarding: /linkedin:onboarding wizard, README Quick Start rewrite
Content Quality: voice drift scoring, industry angle variants,
  /linkedin:carousel, /linkedin:react multi-URL comparison
Analytics: automated week-rollover, day-of-week heatmap,
  month-over-month reports

25→27 commands. All Q2 ROADMAP items completed.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-08 06:16:35 +02:00
Kjell Tore Guttormsen
f8bf0b67da docs(linkedin-thought-leadership): add Q2-Q4 2026 roadmap
Covers onboarding, content quality, analytics, Claude Code platform
integration, architecture improvements, and growth features.
Includes dependency tracking and deprioritized items with rationale.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-07 22:12:58 +02:00