Install
$ agentstack add skill-indranilbanerjee-socialforge-match-assets ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/socialforge:match-assets — Asset Matcher
Match brand assets to parsed calendar posts using the multi-factor scoring algorithm. Assigns one of 4 creative modes per post.
Context efficiency
Asset-heavy skill. Grep before Read the asset catalog (${CLAUDE_PLUGIN_DATA}//assets/index.json) — never list the asset directory. Reference generated images / videos by path, not by loading metadata. Brand profile loads once per session.
Prerequisites
- Calendar parsed (calendar-data.json exists)
- Asset index built (asset-index.json exists)
If either is missing, prompt: "Run /socialforge:parse-calendar first, then /socialforge:index-assets."
The Matching Algorithm
For each post, calculate a multi-factor score against every indexed asset:
| Factor | Weight | What It Measures | |--------|--------|------------------| | Tag Overlap | 30% | Post keywords vs asset tags | | Suitability Match | 25% | Asset's "suitable_for" vs post context | | Content Bucket Match | 20% | Does asset suit this content bucket? | | Crop Feasibility | 15% | Can asset be cropped to all required platform ratios? | | Freshness Penalty | 10% | Penalize assets used recently this month |
Freshness penalty: 0 uses = no penalty | 1 use = score x 0.85 | 2 uses = score x 0.60 | 3+ uses = score x 0.30
Creative Mode Assignment
| Score Range | Recommended Mode | |-------------|-----------------| | > 0.8 | ANCHORCOMPOSE or ENHANCEEXTEND | | 0.5 - 0.8 | ENHANCEEXTEND or STYLEREFERENCED | | 0.3 - 0.5 | STYLEREFERENCED | | < 0.3 | PURECREATIVE |
Also selects 2-5 style reference images per post (always fed to AI generation alongside prompts).
Process
- Load calendar-data.json and asset-index.json
- For each post: extract keywords → score all assets → rank → assign mode
- Select style references per post
- Generate coverage report
Coverage Report
Asset Matching Complete: 28 posts
ANCHOR_COMPOSE: 8 posts (direct brand asset matches)
ENHANCE_EXTEND: 5 posts (asset needs enhancement)
STYLE_REFERENCED: 9 posts (AI gen guided by brand DNA)
PURE_CREATIVE: 4 posts (full AI generation)
CAROUSEL_TEMPLATE: 2 posts (HTML template rendering)
Asset gaps: 3 posts flagged (should have brand assets but none found)
- P07: Founder post but no founder photos indexed
- P14: Product demo but no product screenshots available
- P22: Office culture post but no office photos
Top used assets: asset_012 (3 posts), asset_005 (2 posts)
- Present for user confirmation — user can override any match
- Save to
output/{brand}/{YYYY-MM}/asset-matches.json
User Override
For any post, user can:
- Accept the recommendation
- Select a different asset: "Use asset_015 for P07"
- Change creative mode: "Make P14 PURE_CREATIVE instead"
- Upload a new asset on the spot
- Skip: "I'll handle P22 manually"
Timeout & Fallback
- Per-post matching: 5-second timeout. If an asset index is very large (500+ images), process in batches.
- Show progress:
[12/28] Matching Post P12 — best match: asset_023 (score: 0.74, STYLE_REFERENCED)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: indranilbanerjee
- Source: indranilbanerjee/socialforge
- License: MIT
- Homepage: https://indranil.in
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.