Commit graph

10 commits

Author SHA1 Message Date
19dc10cfd4 docs(linkedin-studio): Voyage remediation setup — brief + research + plan (Phase 0-3)
Audit-remediation Voyage project authored end-to-end this session:
- brief.md (reviewer PROCEED; validator pass) — full Phase 0-3 scope, phased,
  with success criteria refined by research
- research/01-03 — high-effort external swarm + Gemini (Topic 1); reconciled the
  external bar and corrected several audit feature-premises (no publishable model
  name/date; saves UI-visible not API-pullable; auto-publish possible-not-built;
  9:16 not mandatory; newsletter notifications deduplicated not triple; CLI crash
  = missing npm install, depth-bug latent)
- plan.md (21 steps, 7 sessions, 5 waves; validator pass; A- 88/100) — plan-critic
  REVISE (3 blockers + majors) addressed; scope-guardian ALIGNED; gemini Pass-2
  folded in 2 blind spots (git-history decision; lint stat-grep sequencing)

Execution is future sessions (one wave each) via /trekexecute, /trekreview as the
release gate. Audit report stays local until the article ships.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-29 19:49:27 +02:00
7833d06dd3 refactor(linkedin)!: rename plugin linkedin-thought-leadership → linkedin-studio (v3.0.0)
BREAKING CHANGE: the marketplace slug, the agent namespace
(linkedin-studio:<agent>), and the runtime state-file path
(~/.claude/linkedin-studio.local.md) all change. Reinstall required;
existing state migrated in place (post metrics, streak, history preserved).
The /linkedin:* commands are unchanged — the command namespace is set
per-command in frontmatter and was always independent of the plugin slug.
Functionality is byte-identical to v2.4.0; this release is pure identity.

- dir + manifests: plugins/linkedin-studio + plugin.json + root marketplace.json
- agent namespace updated in commands/newsletter.md (only functional invoker)
- state path updated in 4 hook scripts + topic-rotation prompt + state template
- catch-all skill dir renamed skills/linkedin-studio (5 functional skills unchanged)
- docs + version bump to 3.0.0 across README badge, CHANGELOG, root README/CLAUDE.md
- historical records (CHANGELOG past entries, docs/ build artifacts,
  config-audit v5.0.0 snapshots) intentionally retain the old slug

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-29 11:32:02 +02:00
eeaecbfbc2 chore(linkedin): v2.0.0 — import trim, router gating, full doc pass (S20) 2026-05-28 06:53:55 +02:00
38cb3fd910 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
bc7c837c5a 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
38a3179225 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
98c6c69447 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
15016221c1 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
737f20b439 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
Kjell Tore Guttormsen
4dc868ea62 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