n4m3z/PromptAnalysis
skills/PromptAnalysis/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add n4m3z/forge-core PromptAnalysisInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 14, 2026, 6:11 AM217.5s12 files scanned
SKILL.md
- name:
- PromptAnalysis
- version:
- 0.1.0
- description:
- 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.
PromptAnalysis
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.
Subskill Routing
| 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| Check model/provider targeting correctness| | "stale", "staleness", "deprecated"| @Staleness.md | Check for outdated references | | "cleanup", "minimize", "fix" | Cleanup | Scan + auto-fix with confirmation | | single file path | Single | Full analysis of one file with all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|
External Tool 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 |
Scan Mode
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.
Single File Mode
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.
Cleanup Mode
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.
Output Format
Follow @Output.md for the ASCII dashboard layout, card types, optional gauges, and batch decision flow.
Sources
- https://github.com/N4M3Z/forge-core
- https://arxiv.org/html/2603.08993v1
- https://www.promptfoo.dev/docs/intro/
- https://www.llmlingua.com/
- https://artificialanalysis.ai/documentation
Related Skills
n4m3z/Wtf
development
VerifiedTrustedCommunity
Reactive correction and root-cause fix. USE WHEN something went wrong, user is frustrated, demands a correction, says wtf, what the hell, why did you, that's wrong, this is broken, no not that, stop. Executes the immediate fix, then hunts the upstream artifact that caused it and creates a corrective change.
4SKILL.mdUpdated May 28, 2026
n4m3z/ResearchTopic
development
VerifiedTrustedCommunity
Decompose a research question into sub-queries, spawn parallel WebResearcher agents per angle, synthesize findings with citations and explicit confidence. USE WHEN the user asks to research, investigate, look online, look up, dig into, find sources, gather evidence, or survey what's known about a topic. Single-pass; for multi-round adversarial research use ResearchCouncil in forge-council.
4SKILL.mdUpdated May 27, 2026
n4m3z/WriteDocs
tools
VerifiedTrustedCommunity
Author project documentation that future humans (and AI sessions) actually read. Covers TLDRs for tools, READMEs, runbooks, journals. USE WHEN write documentation, create tldr, tool one-pager, document a cli, write readme, runbook, journal entry, capture knowledge about a tool, distill a session into reusable notes.
4SKILL.mdUpdated May 25, 2026
n4m3z/StagedReview
development
VerifiedTrustedCommunity
Review your own staged changes via a code-review TUI before triggering a commit. USE WHEN about to commit, walking through your own staged diff, self-reviewing before approval, tuicr, revdiff, git diff cached.
4SKILL.mdUpdated May 25, 2026