agentsclimarketplace

Parse calendar

Skill indranilbanerjee/socialforge/skills/parse-calendar

Parse monthly content calendars from DOCX, XLSX, Notion, or text into structured calendar-data.json.From its SKILL.md

Install
npx -y skills add indranilbanerjee/socialforge --skill parse-calendar

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.5 KB, 793 tokens by cl100k_base, as published. Nobody here has run it

/socialforge:parse-calendar — Calendar Parser

Parse a monthly social media content calendar into structured JSON that drives the entire production pipeline.

Context efficiency

Asset-heavy skill. Grep before Read the asset catalog (${CLAUDE_PLUGIN_DATA}/<brand>/assets/index.json) — never list the asset directory. Reference generated images / videos by path, not by loading metadata. Brand profile loads once per session.

Supported Formats

FormatHow It Works
DOCXRead tables and structured text from Word documents
XLSXRead rows from Excel spreadsheets (one row per post)
NotionRead from Notion database via MCP (requires Notion connector)
Structured textParse markdown or plain text with consistent formatting

Required Fields Per Post

Every post in the calendar must have (or the system will ask for missing ones):

FieldRequiredDescription
post_idAuto-generatedUnique identifier (e.g., P01, P02)
dateYesPublishing date (YYYY-MM-DD)
platformYesTarget platform(s) — linkedin, instagram, x, facebook, etc.
content_typeYesstatic, carousel, video, story, reel, text_only
tierYesHERO, HUB, or HYGIENE
topicYesWhat the post is about
caption_briefYesBrief description of the copy direction
visual_briefRecommendedWhat the image should show
hashtagsOptionalPost-specific hashtags (brand hashtags added automatically)
ctaOptionalCall-to-action text or link
campaignOptionalCampaign this post belongs to
notesOptionalSpecial instructions

Process

  1. Detect format — Check file extension or URL pattern
  2. Extract posts — Parse each post entry from the source
  3. Validate fields — Check required fields present. For missing fields, ask the user.
  4. Normalize — Standardize dates, platform names, content types to schema format
  5. Assign post IDs — Sequential (P01, P02, ...) if not already present
  6. Cross-reference platforms — Check all platforms exist in brand's platform-config.json
  7. Flag issues — Duplicate dates, missing briefs, unsupported content types
  8. Save — Write calendar-data.json to ~/socialforge-workspace/output/{brand}/{YYYY-MM}/

Output

Calendar parsed: 28 posts for April 2026
  LinkedIn: 12 posts (4 carousels, 6 static, 2 video)
  Instagram: 10 posts (3 carousels, 4 reels, 3 static)
  X: 6 posts (all text+image)

Issues found: 2
  - P14: Missing visual_brief (will need manual input during asset matching)
  - P22: Date falls on Sunday — confirm intentional weekend post?

Calendar saved: ~/socialforge-workspace/output/acme-corp/2026-04/calendar-data.json

After Parsing

Ask: "Would you like to:

  • Match assets to posts? (/socialforge:match-assets)
  • Review the parsed calendar first? (I'll show the full post list)
  • Fix issues? (I'll walk through each flagged item)"

Timeout & Fallback

  • DOCX/XLSX parsing: 30-second timeout. If file is too large, suggest splitting by week.
  • Notion: 60-second timeout per database query. If Notion is slow, offer to export and parse locally.
  • If format is unrecognized: Ask user to describe the structure, then parse adaptively.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.