Promptify Skill

Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelligently routes to sub-agents for codebase research, clarifying questions, or web search as needed.

Security Scan

The skill's instructions, required tools, and behavior match its stated purpose of prompt optimization and conditioned sub-agent dispatch; it does not request extra credentials or install code, but it will read project files and use web/search tools when asked.

Purpose & Capability

The name/description promise (optimize prompts, route to clarifying, codebase, or web sub-agents) matches the SKILL.md and agent files. The agents explicitly describe using AskUserQuestion, codebase exploration (Glob/Grep/Read/LS), and web search (WebSearch/WebFetch), which are coherent with the stated purpose.

Instruction Scope

Instructions legitimately direct the agent to read repository files and run web searches when +deep/+web are used; this is expected for codebase/web research. Note: SKILL.md outputs include a platform shell command (`echo 'PROMPT' | pbcopy`) which assumes a pbcopy clipboard utility (macOS) while the skill declares no required binaries—minor mismatch. Also be aware that +deep causes reading project files, which can surface sensitive contents if present.

Install Mechanism

Instruction-only skill with no install spec and no code files to write or execute. Lowest-risk install profile.

Credentials

The skill requests no environment variables, credentials, or config paths. The agents' behaviors (file reads, web searches, user questions) are proportionate to prompt-optimization tasks.

Persistence & Privilege

always:false and no mechanism for persistent system-wide changes or for modifying other skills. Normal autonomous invocation is allowed (default) but not excessive here.

Assessment

This skill appears to do what it says: optimize prompts and optionally run clarifying questions, codebase inspection, or web research. Before installing or invoking +deep/+web, consider: (1) +deep will read your repository files — don't use it on repos that contain secrets or private data you don't want analyzed; (2) +web uses web search/fetch tools — avoid sending sensitive/proprietary prompt content you wouldn't want transmitted to external documentation/search; (3) the SKILL.md suggests copying output with `pbcopy` (mac-specific) even though no binaries are required — that may not work on all platforms; (4) confirm what platform tools (Glob/Grep/Read/LS, WebSearch/WebFetch, AskUserQuestion) your agent runtime exposes and whether they have any additional logging or external network behavior. If you need stronger guarantees, restrict the skill from running +deep or +web, or review the prompt contents before confirming any web or codebase research steps.

Prompt Optimizer

Transform prompts into clear, effective ones. Model-agnostic.

Modifiers (parse from ARGUMENTS)

• +ask → Force clarifying questions
• +deep → Force codebase exploration
• +web → Force web search

No modifiers? Auto-detect what's needed.

Auto-Detection Triggers

Trigger	Signals
codebase-researcher	"this project", "our API", specific files/functions, "integrate", "extend", "refactor"
clarifier	Ambiguous ("make it better"), multiple interpretations, missing constraints, vague pronouns
web-researcher	"best practices", "latest", external APIs/libraries, framework patterns, year references

Agent Dispatch

When agents needed:

1. Announce which and why
2. Run in parallel via Task tool (agents/ directory)
3. Synthesize findings
4. Optimize with gathered context

---

Core Contract (every prompt needs all four)

Element	If Missing
Role	Add persona with expertise
Task	Make action specific
Constraints	Infer from context
Output	Specify format/structure

Process

1. If image: Analyze, incorporate context
2. Detect type: coding/writing/analysis/creative/data
3. Convert output→process: "Write X" → "Analyze → Plan → Implement → Validate"
4. Strip fluff: "please", "I want you to", filler, apologies
5. Apply contract: Verify all 4 elements
6. Add structure: XML tags for complex prompts

Type Focus

• Coding: Specs, edge cases, framework
• Writing: Tone, audience, length
• Analysis: Criteria, depth
• Creative: Constraints, novelty
• Data: I/O format, edge cases

Output

1. Optimized prompt in code block
2. echo 'PROMPT' | pbcopy
3. 2-3 sentence explanation