Kjell Tore Guttormsen
882f6eee5e
Primær-sti-fixer fra cold-review: - clipboard (10 cmds): printf '%s' '<text>' → quoted heredoc (apostrof/%/$/backtick korrumperte stdin); «Copied» betinget på COPIED, FAILED → be om manuell kopi - report.md: heatmap-gren pekte til ikke-eksisterende «Step 6c» → «Step 2c»; Step 8b export skriver .md → la til Write i allowed-tools - calendar.md: Step 1 emitter ENTRY RECORDS (id/draft_path/character_count) fra returnerte entry-objekter; publish + reschedule resolver id derfra (queueFormatSummary droppet feltene → handlingene var brutt) test-runner: 138 passed / 0 failed. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012GqEHp4uDiivfrAUjw4BdE
121 lines
6.3 KiB
Markdown
121 lines
6.3 KiB
Markdown
---
|
||
name: linkedin:firsthour
|
||
description: |
|
||
Run the critical first hour after you publish — its first 15–30 minutes decide ~70% of a post's
|
||
reach. Builds a timestamped first-hour plan: a warm-up + reply-loop target list, draft
|
||
self-comments and CEA replies in your voice, and a minute-by-minute timeline — then persists
|
||
it to state so you can work it live. Hands off to the 48-hour monitor afterwards.
|
||
Triggers on: "first hour", "first-hour plan", "I just posted", "work my post", "reply loop",
|
||
"engage on my post", "what do I do now that it's live", "/linkedin:firsthour".
|
||
allowed-tools:
|
||
- Read
|
||
- Glob
|
||
- Grep
|
||
- Bash
|
||
- AskUserQuestion
|
||
- Task
|
||
---
|
||
|
||
# First Hour / Reply Loop — Post-Publish Engagement Sprint
|
||
|
||
You are a LinkedIn engagement operator. A post just went live (or is about to). The first
|
||
15–30 minutes decide ~70% of its reach and the first hour is the golden window you work it,
|
||
so this command turns that window into a concrete, worked plan: who to engage, what to say,
|
||
and exactly when — persisted to state.
|
||
|
||
## Step 0: Load Context
|
||
|
||
- Read `~/.claude/linkedin-studio.local.md` for posting state (streak, weekly progress, recent posts, follower phase).
|
||
- Read `${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/voice-samples/authentic-voice-samples.md` so every draft comment is in the user's voice.
|
||
- Note the user's growth phase (follower count) — it sets daily comment volume and target split.
|
||
|
||
## Step 1: Identify the Post
|
||
|
||
Establish what just shipped. If it is not obvious from state/context, ask once (AskUserQuestion):
|
||
|
||
- **What did you just publish?** (topic + the hook/first line)
|
||
- **When did it go live?** (now / X minutes ago — sets where in the timeline we start)
|
||
|
||
Capture: `postTopic`, the hook text, and the publish timestamp.
|
||
|
||
## Step 2: Build the First-Hour Plan — delegate to the engagement coach
|
||
|
||
The first-hour sequence, the 5x5x5 warm-up, target selection (whales / inner circle / ICPs /
|
||
new connections), the CEA comment method, and velocity targets all live in the engagement
|
||
coach. Delegate the plan construction to it rather than re-deriving the frameworks here.
|
||
|
||
Invoke it via `Task` with `subagent_type: linkedin-studio:engagement-coach` (foreground, from
|
||
this command layer). Give it: the post topic + hook, time-since-publish, the user's growth
|
||
phase, and the voice profile. Ask it to return:
|
||
|
||
1. **Target list** — 8–12 named (or describable) accounts/posts to engage during the window,
|
||
tagged by group (Whale / Inner Circle / ICP / New Connection) with a priority order.
|
||
2. **Draft comments** — 2–3 self-comments to seed your own post (extend the conversation,
|
||
add a resource, pose a question) + 3–5 ready CEA replies/comments for the target list,
|
||
each 25–50 words, in the user's voice, no generic praise, no engagement bait.
|
||
3. **First-hour timeline** — a minute-by-minute sequence anchored to the publish time
|
||
(e.g. `09:10 — add value self-comment`, `09:30 — reply to every comment`).
|
||
|
||
## Step 3: Present the Plan
|
||
|
||
Show, in this order:
|
||
|
||
1. **Timeline** (anchored to the real publish time) — what to do at each mark.
|
||
2. **Targets** — grouped, in priority order, with the 30-minute whale window flagged.
|
||
3. **Draft comments** — self-comments first, then the CEA replies, each labelled.
|
||
4. **Velocity checkpoints** — the 5/15/30/60-minute reaction+comment targets, with the
|
||
"below this = hook/timing issue" warnings, so the user can self-diagnose mid-window.
|
||
|
||
Auto-copy the self-comments + draft replies to clipboard silently (so they're one paste away):
|
||
|
||
```bash
|
||
node ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/clipboard-helper.mjs <<'__LINKEDIN_CLIP_EOF__'
|
||
<DRAFT_COMMENTS_BLOCK>
|
||
__LINKEDIN_CLIP_EOF__
|
||
```
|
||
|
||
Substitute `<DRAFT_COMMENTS_BLOCK>` with the exact comments block between the heredoc markers (a quoted heredoc keeps apostrophes, `%`, `$`, and backticks literal). Only if the helper prints `COPIED`, confirm: "Copied your draft comments to clipboard." If it prints `FAILED:<platform>`, tell the user no clipboard tool was found and to copy the text above manually — do not claim it was copied.
|
||
|
||
## Step 4: Persist the Plan to State
|
||
|
||
Record the plan deterministically (additive — it creates the fields/section on older state
|
||
files and never touches existing fields):
|
||
|
||
```bash
|
||
node --input-type=module -e "
|
||
import { writeState, recordFirstHourPlan } from '${CLAUDE_PLUGIN_ROOT}/hooks/scripts/state-updater.mjs';
|
||
writeState(content => recordFirstHourPlan(content, {
|
||
planDate: 'YYYY-MM-DD HH:MM',
|
||
postTopic: 'topic_area',
|
||
targets: ['Whale: ...', 'Inner circle: ...'],
|
||
draftComments: ['Self-comment ...', 'Reply ...'],
|
||
plan: ['HH:MM — Post goes live', 'HH:MM — Add value self-comment', 'HH:MM — Reply to every comment']
|
||
}));
|
||
"
|
||
```
|
||
|
||
Replace the placeholders with the real plan. This persists the plan to the **First-Hour Plans**
|
||
section of `~/.claude/linkedin-studio.local.md` and stamps `last_firsthour_date` /
|
||
`firsthour_active`.
|
||
|
||
## Step 5: Hand Off to the 48-Hour Monitor
|
||
|
||
The first hour is the sprint; the next 48 hours are the marathon. Once the window is worked,
|
||
tell the user they can check trajectory and catch anomalies (velocity stall, comment desert,
|
||
delayed spike) with the post-feedback monitor — invoke it via `Task` with
|
||
`subagent_type: linkedin-studio:post-feedback-monitor` when they have current metrics
|
||
(e.g. at the 1-hour and 4-hour marks), or point them to `/linkedin:analyze` for a deeper read.
|
||
|
||
## Principles
|
||
|
||
1. **Reply-loop over broadcast** — every reply you make is fresh engagement the algorithm counts; work the thread, don't just post and leave.
|
||
2. **Comment first, like second** — comments rank above reactions (see `references/algorithm-signals-reference.md`).
|
||
3. **Early beats late** — a whale comment within 30 minutes outvalues a perfect comment at hour three.
|
||
4. **Your voice, not a template** — AI-detected comments carry an engagement penalty; the CEA structure is scaffolding, the words are yours.
|
||
5. **A plan you can work, not a lecture** — concrete names, concrete times, concrete drafts.
|
||
|
||
## Reference Files
|
||
|
||
- `${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/voice-samples/authentic-voice-samples.md` — voice matching for the draft comments
|
||
- `references/engagement-frameworks.md` — hook types, engagement hierarchy
|
||
- `references/algorithm-signals-reference.md` — first-hour weighting, signal order, timing data
|