From forge-core
Validate and minimize prompts — provenance, targeting, staleness, redundancy, ablation testing, perplexity scoring. USE WHEN audit rules, check provenance, minimize prompts, prompt cleanup, validate targeting, find redundant rules, prompt audit, prompt analysis, stale rules.
npx claudepluginhub n4m3z/forge-coreThis skill uses the workspace's default tool permissions.
Analyze rules, skills, and agents for minimum viable prompt compliance (MVPR-0001). Each concern is a subskill with its own detection patterns and output format.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Processes PDFs: extracts text/tables/images, merges/splits/rotates pages, adds watermarks, creates/fills forms, encrypts/decrypts, OCRs scans. Activates on PDF mentions or output requests.
Share bugs, ideas, or general feedback.
Analyze rules, skills, and agents for minimum viable prompt compliance (MVPR-0001). Each concern is a subskill with its own detection patterns and output format.
| Keyword | Subskill | What it does |
|---|---|---|
| "scan", "audit", "check", "all" | Scan | Run all subskills on a module |
| "provenance", "sources", "refs" | @Provenance.md | Check external source citations |
| "target", "targeting", "provider" | @Targeting.md | Check model/provider targeting correctness |
| "stale", "staleness", "deprecated" | @Staleness.md | Check for outdated references |
| "cleanup", "minimize", "fix" | Cleanup | Scan + auto-fix with confirmation |
| single file path | Single | Full analysis of one file with all subskills |
| Keyword | Subskill | Requires |
|---|---|---|
| "deep", "test", "ablation" | @PromptFoo.md | npm install -g promptfoo + API keys |
| "compress", "perplexity" | @LLMLingua.md | pip install llmlingua |
| "benchmark", "capability" | @ArtificialAnalysis.md | API key from artificialanalysis.ai |
Run all static subskills (Provenance + Targeting + Staleness) on every rule in a module:
/PromptAnalysis scan Modules/forge-core/rules
Scan collects results from each subskill and presents a unified report grouped by status. No API calls, no model queries — purely static.
All subskills on one file:
/PromptAnalysis Modules/forge-core/rules/NoHeredoc.md
Shows full content with inline annotations, current targeting, qualifier variants, and a recommendation.
Scan + apply safe structural fixes with confirmation:
/PromptAnalysis cleanup Modules/forge-core/rules
For each fixable issue, present via AskUserQuestion. Only structural fixes (add targets, move to qualifier dir). Never delete rules or change content.
Follow @Output.md for the ASCII dashboard layout, card types, optional gauges, and batch decision flow.