Skills when-optimizing-prompts-use-prompt-optimization-analyzer
📦

when-optimizing-prompts-use-prompt-optimization-analyzer

v1.0.0 Content revision r1 Medium Risk ⚙️ External commands

Optimize Prompts With Diagnostic Analysis

Prompt libraries often grow verbose, inconsistent, and hard to maintain. This skill diagnoses prompt quality issues and turns them into practical optimization steps.

Supports: Claude Codex Code(CC)
⚠️ 50 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "when-optimizing-prompts-use-prompt-optimization-analyzer" from https://skillstore.io/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer.md and its manifest at https://skillstore.io/api/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer.md Signed manifest GET /api/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/manifest Signed lockfile GET /api/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/lockfile

Test it

Using "when-optimizing-prompts-use-prompt-optimization-analyzer". A vague code review prompt with repeated phrases and broad quality goals.

Expected outcome:

The analyzer identifies repeated wording, replaces vague adjectives with review criteria, and recommends a shorter structured review process.

Using "when-optimizing-prompts-use-prompt-optimization-analyzer". A skill trigger that says to use the skill for anything related to prompts.

Expected outcome:

The analyzer flags the trigger as too broad and suggests clear activation conditions, exclusions, and examples.

Using "when-optimizing-prompts-use-prompt-optimization-analyzer". Two versions of the same prompt before and after editing.

Expected outcome:

The analyzer compares token savings, retained intent, clarity gains, and any important instruction loss.

Security Audit

Medium Risk
v9 • 7/5/2026 Open versioned report

Most static detections are false positives caused by Markdown fences and JavaScript template literals. The real issue is repeated guidance to run npx claude-flow@alpha hook and memory commands, which can execute mutable third-party package code. No prompt injection attempt was found.

4
Files scanned
1,047
Lines analyzed
3
Review items
0
False positives ignored

Confirmed security concerns (4)

Medium
PROCESS.md:174
System reconnaissance
npx claude-flow@alpha hooks post-task --task-id "prompt-optimization"
This line runs an npx claude-flow@alpha post-task hook from a bash example. It is not system reconnaissance, but it still asks an agent or user to execute an external package.
Medium
PROCESS.md:249
System reconnaissance
--task-id "optimize-[prompt-id]" \
This argument is part of the npx claude-flow@alpha post-task command started in the same block. The context is external package execution, so the command risk is real even though reconnaissance is not shown.
Medium
SKILL.md:453
System reconnaissance
npx claude-flow@alpha hooks post-task --task-id "skill-optimization"
The cited line runs npx claude-flow@alpha hooks post-task. It is not reconnaissance, but it is still a real external command execution risk.
Medium
SKILL.md:63-66SKILL.md:279SKILL.md:438-444SKILL.md:453PROCESS.md:32-33PROCESS.md:174-175PROCESS.md:222-233PROCESS.md:248-251
Unpinned External Package Execution Guidance
The skill repeatedly directs users to run npx claude-flow@alpha. The alpha tag is mutable, so these examples can execute changing third-party package code.
Multiple documentation blocks explicitly use npx claude-flow@alpha. I found no pin to an immutable version or warning that command execution requires user approval.
Capability review items (3)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
SKILL.md:61-71
Ruby/shell backtick execution
```bash
The bash block instructs users to run npx claude-flow@alpha hook and memory commands. npx can download and execute mutable third-party package code.
Medium
SKILL.md:270-285
Ruby/shell backtick execution
```bash
The bash example stores recommendations through npx claude-flow@alpha. This is external package execution from a mutable alpha tag.
Medium
SKILL.md:436-454
Ruby/shell backtick execution
```bash
The pre-publish checklist includes npx claude-flow@alpha hook and memory commands. These examples can execute an external alpha package if followed.

Risk Factors

⚙️ External commands (29)
SKILL.md:61-71 SKILL.md:71-74 SKILL.md:74-117 SKILL.md:117-149 SKILL.md:149-176 SKILL.md:176-183 SKILL.md:183-223 SKILL.md:223-227 SKILL.md:227-243 SKILL.md:243-265 SKILL.md:265-270 SKILL.md:270-285 SKILL.md:285-291 SKILL.md:291-339 SKILL.md:339-341 SKILL.md:341-344 SKILL.md:344-346 SKILL.md:346-349 SKILL.md:349-354 SKILL.md:354-363 SKILL.md:363-368 SKILL.md:368-400 SKILL.md:400-409 SKILL.md:409-424 SKILL.md:424-436 SKILL.md:436-454 SKILL.md:454-466 SKILL.md:466-467 SKILL.md:467-468

Detected Patterns

System reconnaissance×3
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/security.svg)](https://skillstore.io/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

DNYoussef. (2026). when-optimizing-prompts-use-prompt-optimization-analyzer security audit report (audit version 9) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/audits/9

BibTeX citation

@techreport{dnyoussef-dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer-2026, author = {DNYoussef}, title = {when-optimizing-prompts-use-prompt-optimization-analyzer security audit report (audit version 9)}, institution = {Skillstore}, year = {2026}, number = {9}, url = {https://skillstore.io/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/audits/9}, note = {Author version 1.0.0} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "when-optimizing-prompts-use-prompt-optimization-analyzer security audit report (audit version 9)" version: "1.0.0" type: report authors: - name: "DNYoussef" date-released: "2026-07-05" url: "https://skillstore.io/skills/dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer/audits/9" identifiers: - type: other value: "skillstore:dnyoussef-when-optimizing-prompts-use-prompt-optimization-analyzer:audit:9" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
100
Maintainability
87
Content
70
Community
83
Spec Compliance

What You Can Build

Prepare a Skill for Publication

Review a new skill prompt for clarity, token waste, and weak trigger conditions before release.

Improve a Prompt Library

Compare prompts across a team and identify repeated wording, vague rules, and maintenance problems.

Refine Support Instructions

Turn broad agent guidance into clear steps, measurable outcomes, and easier review criteria.

Try These Prompts

Find Basic Token Waste 
Analyze this prompt for repeated phrases, filler words, and vague instructions. Return the top five fixes and estimated token savings: [paste prompt].
Improve Skill Instructions 
Review this skill prompt for token efficiency, trigger clarity, and conflicting requirements. Prioritize issues by severity: [paste skill content].
Compare Before and After 
Compare these prompt versions. Explain what improved, what became weaker, and whether the optimized version keeps the original intent: [paste both versions].
Audit a Prompt Library Plan 
Analyze these related prompts as a library. Identify shared anti-patterns, overlapping triggers, and a phased optimization plan: [paste prompt set].

Best Practices

  • Provide the full prompt, target user, model, and token goal.
  • Fix high-severity clarity issues before optimizing only for length.
  • Run the analysis again after major prompt changes.

Avoid

  • Optimizing only for token count when precision is required.
  • Treating heuristic scores as final quality guarantees.
  • Running external workflow commands without approval and version pinning.

Frequently Asked Questions

What does this skill analyze?
It analyzes prompt wording, structure, triggers, redundancy, and common instruction anti-patterns.
Does it edit prompts automatically?
No. It produces recommendations and comparisons. An agent or user must apply the changes.
Can it provide exact token counts?
It estimates token savings. Exact counts depend on the tokenizer used by the target model.
Is it useful for Claude Code or Codex?
Yes. It can review instructions meant for Claude, Codex, and Claude Code workflows.
What inputs should I provide?
Provide the full prompt, intended use, target model, and any token or quality constraints.
Are the workflow commands required?
No. Treat external command examples as optional and review them before running anything.

Developer Details

Author

DNYoussef

License

MIT

Author version

v1.0.0

Skillstore revision

r1

Repository

https://github.com/DNYoussef/ai-chrome-extension/tree/main/.claude/skills/meta-tools/when-optimizing-prompts-use-prompt-optimization-analyzer

Ref

c579efd02184f1128d6741d16e6c8d951d7d4208

Maintenance freshness

7/18/2026

Usage

11 downloads · 220 views

File structure

📄 process-diagram.gv

📄 PROCESS.md

📄 README.md

📄 SKILL.md