leamsigc/shortsgenerator/facebook-research-report
Claude Code and agent skill by leamsigc/shortsgenerator
- community
Checking that the SKILL.md file is still in the repository.
Report state — synthesizes all phase outputs into a comprehensive final report. Generates a self-contained HTML report (REPORT.html) plus a markdown backup (report.md). Includes performance summary, history trend comparison, top 5 deconstruction recap, video structure analysis, competitor deep-dive, replication scripts, keyword strategy, and engagement opportunities.
Install
npx vskill@latest install leamsigc/shortsgenerator/facebook-research-reportSKILL.md
Facebook Research — Report State (v3)
Generates the final report. The HTML shell is produced by a script; the analytical sections are authored from the scraped data.
Preconditions
- Config:
.fb-research/projects/<project-name>/config.json - Analysis:
.fb-research/projects/<project-name>/top5-analysis.md - Analytics:
.fb-research/projects/<project-name>/page-analytics.json+page-analytics-history.json - Competitors:
.fb-research/projects/<project-name>/competitors/ - Optional video template data:
video-template/VIDEO-TEMPLATE.md,video-analysis.json,transcripts/
Steps
1. Load all data + compute history trends
Read all JSON/markdown files. Compute trend direction per metric (followers, avg views, avg likes, top post views) across snapshots — improving / declining / stable.
2. Discover real competitors via Facebook search
Scroll, extract page results, filter to the top 5 most relevant, save to discovered-competitors.json. Benchmark each competitor's positioning relative to the target page.
3. Generate 5 replication script templates
Mix at least 3 from the page's top 5 + up to 2 from competitor patterns. Each script: original source, core pattern, why it works, adapted topic script (hook/body/CTA), caption template, production notes, performance prediction, post-publication tracking checklist.
Save each to replication-scripts/001-<slug>.md and update replication-history.json.
4. Keyword research + competitor deep-dive
- WebSearch the niche for trending topics/audience interests
- Extract keywords from top posts + competitors → keyword clusters by content type
- Visit competitor pages via Chrome DevTools, extract recent posts + video URLs
5. Generate the HTML report + markdown backup
The HTML shell is rendered from the structured data:
Then augment REPORT.html with the analytical sections authored above (executive summary, top-5 deep dive, video structure analysis, replication scripts, keyword strategy, engagement strategy, feedback for page manager, 30-day action plan). Keep REPORT.html as the primary deliverable and write report.md as the markdown backup. Append a snapshot to report-history.json.
Report Completion
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/facebook-research-report/SKILL.md
Popularity
- Repository stars
- 348
- Repository forks
- 75
- 7-day trend score
- 29
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/leamsigc/shortsgenerator/facebook-research-report)