Kjell Tore Guttormsen 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

10 KiB

Raw Blame History

Agent Capability Matrix

14 specialized agents for LinkedIn thought leadership. Each agent has a focused responsibility, defined model, and unique color for visual identification.

Quick Reference

Agent	Model	Color	Primary Responsibility
content-optimizer	Sonnet	Blue	Optimize posts against algorithm signals
strategy-advisor	Sonnet	Green	Growth strategy and phase-specific guidance
analytics-interpreter	Sonnet	Yellow	Pattern discovery + weekly/monthly performance reports (interpret/report modes)
engagement-coach	Sonnet	Magenta	5x5x5 + first-hour tactics + CEA commenting + target selection
content-planner	Sonnet	Cyan	Weekly/monthly content calendars
network-builder	Sonnet	Teal	Strategic networking and outreach
content-repurposer	Sonnet	Purple	Format conversion and evergreen refresh
trend-spotter	Sonnet	White	Trending topics and opportunity scoring
voice-trainer	Sonnet	Pink	Voice profile building and drift detection
differentiation-checker	Sonnet	Gray	Originality scoring and commodity detection
video-scripter	Sonnet	Violet	Video script creation with pacing and visual cues
post-feedback-monitor	Haiku	Lime	Post-publish 48h monitoring and real-time interventions
fact-checker	Opus	Brown	Factual-claim verification against primary/credible sources (longform)
persona-reviewer	Opus	Olive	Reader-persona resonance + hook-conversion gate (longform)

Capability Matrix

Capabilities mapped across agents. P = Primary, S = Secondary/Supporting.

Capability	optimizer	strategy	analytics	engage	planner	network	repurpose	trends	voice	diff-check	video	post-monitor	fact-check	persona-rev
Post optimization	P
Hook analysis	P										S			S
Algorithm alignment	P			S							S	S
Growth strategy		P			S
Phase assessment		P
Trajectory analysis		P	S
Audience analysis		S	P
Pattern discovery			P
Performance reports			P
Content DNA			P						S
Engagement coaching				P		S
5x5x5 method				P		S
Comment strategy				P
CEA method				P
Target identification				P		S
Content planning					P			S
Mix enforcement					P
Gap analysis					P
Network building				S		P
Connection scoring						P
DM templates						P
Format conversion							P				S
Evergreen scoring							P
Content lifecycle					S		P
Trend scanning					S			P
First-mover assessment								P
Angle mapping					S		S	P
Voice profiling									P
Drift detection									P
Quarterly audit									P
Originality scoring										P
Commodity detection										P
Differentiation										P
Video scripting							S				P
Script pacing											P
Visual cue notation											P
Post-publish monitoring												P
Velocity analysis												P
Factual verification													P
Primary-source check													P
Persona resonance														P
Hook-conversion gate														P

Content Pipeline

How agents collaborate in the end-to-end content lifecycle:

┌─────────────┐    ┌──────────────────┐    ┌─────────────────┐
│ trend-spotter│───▸│  content-planner  │───▸│ diff-checker    │
│ (find topics)│    │ (plan + schedule) │    │ (originality    │
└─────────────┘    └──────────────────┘    │  gate ≥51/100)  │
                          │                 └────────┬────────┘
                          │                          │
                   ┌──────▼──────┐           ┌───────┴────────┐
                   │voice-trainer│           │  FORMAT SPLIT  │
                   │(voice check)│           └──┬──────────┬──┘
                   └──────┬──────┘              │          │
                          │             ┌───────▼───┐ ┌────▼─────────┐
                          │             │video-     │ │content-      │
                          └────────────▸│scripter   │ │optimizer     │
                                        │(scripts)  │ │(text posts)  │
                                        └───────┬───┘ └──────┬───────┘
                                                │            │
                                                └─────┬──────┘
                         ┌────────────────────────────┤
                         │                            │
                  ┌──────▼────────────┐       ┌────────▼───────┐
                  │analytics-         │       │  [PUBLISH]     │
                  │interpreter        │       └────────┬───────┘
                  │(interpret/report) │                │
                  └───────────────────┘       ┌────────▼───────┐
                                              │engagement-coach│
                                              │(5x5x5 + first  │
                                              │ hour + CEA     │
                                              │ commenting)    │
                                              └────────────────┘

For longform editions, two additional Opus agents run BEFORE lock:

draft ─▸ fact-checker ─▸ persona-reviewer ─▸ LOCK ─▸ delivery
        (primary-source     (resonance +
         verification)       hook-conversion
                             gate)

Parallel Support Agents

These agents operate independently and feed into the pipeline at multiple points:

strategy-advisor ──────▸ Macro-level planning and phase guidance
analytics-interpreter ─▸ Pattern discovery + periodic reports feeding back into planning
network-builder ───────▸ Relationship building amplifying content reach
content-repurposer ────▸ Post-publish: extends content lifecycle

Which Agent Do I Need?

Scenario	Agent	Command
"I want to write a post"	content-optimizer	`/linkedin:post`
"What should I post about?"	content-planner, trend-spotter	`/linkedin:pipeline`
"Make this post better"	content-optimizer	`/linkedin:post`
"Is this original enough?"	differentiation-checker	`/linkedin:pipeline`
"Plan my week's content"	content-planner	`/linkedin:batch`
"Am I on track this week?"	—	`/linkedin:calendar`
"How did I do this week?"	analytics-interpreter (report mode)	`/linkedin:report`
"Analyze my LinkedIn data"	analytics-interpreter (interpret mode)	`/linkedin:analyze`
"What's my LinkedIn strategy?"	strategy-advisor	`/linkedin:strategy`
"Help me engage more"	engagement-coach	`/linkedin:strategy`
"Who should I comment on?"	engagement-coach	`/linkedin:strategy`
"Build my network"	network-builder	`/linkedin:strategy`
"Does this sound like me?"	voice-trainer	`/linkedin:post`
"Repurpose my best post"	content-repurposer	`/linkedin:pipeline`
"What's trending in my field?"	trend-spotter	`/linkedin:pipeline`
"Audit my content strategy"	analytics-interpreter, strategy-advisor	`/linkedin:audit`
"How do I monetize?"	strategy-advisor	`/linkedin:monetize`
"Create a video script"	video-scripter	`/linkedin:video`
"Turn this post into a video"	video-scripter, content-repurposer	`/linkedin:video`
"Script a talking head video"	video-scripter	`/linkedin:video`
"Verify facts in this draft"	fact-checker	`/linkedin:newsletter` (longform)
"Will this land with my readers?"	persona-reviewer	`/linkedin:newsletter` (longform)

Model Selection Rationale

Model	Agents	Why
Opus	2 agents (fact-checker, persona-reviewer)	Longform judgment: factual verification, reader-persona resonance
Sonnet	11 agents	Complex reasoning: optimization, strategy, analysis, scoring, scripting, comment targeting
Haiku	1 agent (post-feedback-monitor)	Lighter task: post monitoring with anomaly detection

10 KiB Raw Blame History