# Socialseal Content Adjustment Recommendations

> Use this skill when the user asks what to change next after a SocialSeal readout, which content to continue/adjust/add/pause/retest, why something is not surfacing, or how to turn measurement into the next brief queue. Produce small, owned, measurable changes tied to evidence and production constraints.

- Skill: `opensealai/socialseal-content-adjustment-recommendations` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add opensealai/socialseal-content-adjustment-recommendations`
- Raw SKILL.md: https://api.skillmd.com/api/skills/opensealai/socialseal-content-adjustment-recommendations/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT
- Author: OpenSealAI (https://skillmd.com/u/opensealai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/opensealai/socialseal-content-adjustment-recommendations

---


# SocialSeal Content Adjustment Recommendations

## Overview

This skill turns measurement into decisions. It should not summarize the readout again. It should say exactly what content, tracking, or briefing changes should happen next and why.

## Inputs

- performance readout
- opportunity matrix
- content plan or posted content list
- production capacity
- next-period goals

## Workflow

1. **Group findings by action type.** Continue, adjust, add, pause, investigate, or change tracking.
2. **Diagnose likely issue.** Topic, format, hook, first frame, useful detail, market/language, cadence, asset quality, or measurement gap.
3. **Write concrete changes.** Use owner-ready language: “Add two utility walkthroughs for X,” not “do more useful content.”
4. **Prioritize.** Impact, confidence, effort, and speed to learn.
5. **Define measurement.** State the tracking group, keyword/topic, and signal for each change.
6. **Create brief queue.** Convert high-priority changes into creator briefs or video concepts.

## Output

A recommendation table:

- action type
- finding/evidence (cite by video title/URL, `@handle`, `"keyword" [market, platform]`)
- recommended change
- owner/workstream
- expected signal
- tracking group/keyword
- priority
- caveat / confidence basis (measured / scoped statistic / indicative pattern; see `references/evidence-and-confidence.md`)

## Do / Don't

Do:

- tie every recommendation to evidence
- separate content changes from tracking fixes
- keep changes small enough to measure
- define review timing

Don't:

- recommend vague quality improvements
- change too many variables at once
- ignore production constraints
- invent certainty where evidence is partial

## Troubleshooting

- If every recommendation is “create more content,” return to content jobs and specify format/detail.
- If evidence conflicts, propose a small test rather than a major pivot.
- If tracking is incomplete, make tracking repair the first recommendation.

## Verification Checklist

- [ ] Each recommendation has evidence.
- [ ] Each recommendation is actionable.
- [ ] Measurement signal is defined.
- [ ] Priorities reflect impact and feasibility.
- [ ] Tracking fixes are not disguised as content strategy.