Zoriy Prompt Engineer

Generates high-quality, structured, engineering-grade prompts. Use when the user asks to create, generate, or write a prompt for technical tasks — software d...

Security Scan

The skill largely matches its stated purpose (generating engineering prompts) but contains internal contradictions and forces inclusion of external tooling references (ClaudeKit/Context7) that are not declared or explained, which is inconsistent and worth caution.

Purpose & Capability

Name and description match the skill's instructions: it only generates structured technical prompts and requires no binaries, installs, or credentials. Asking the agent to always include a role and an external-docs directive (ClaudeKit Engineer + Context7) is plausible for a prompt-engineer skill, but those mandatory external references are not described elsewhere (no homepage, no docs), so the requirement is unexplained.

Instruction Scope

SKILL.md mandates injecting 'You are working as ClaudeKit Engineer' and 'Use Context7...' into every technical prompt and states these are 'non-negotiable defaults', yet later says 'If user explicitly forbids them, omit' (contradiction). The instructions direct implicit use of external systems (Context7) for up-to-date docs without declaring what that system is or whether network access or credentials are needed. There are no steps that read local files or secrets, so scope creep is limited, but the forced, unexplained external dependency is concerning.

Install Mechanism

Instruction-only skill with no install spec and no code files. Lowest-risk installation surface; nothing will be written to disk by the skill itself.

Credentials

The skill requests no environment variables or credentials, which is proportional. However, it mandates using 'Context7' (an external docs/source) without declaring any required network access or credentials—this mismatch is unexplained and could lead the agent to call external endpoints or services implicitly if available in the runtime.

Persistence & Privilege

always is false and there are no install scripts or instructions to modify agent/system configuration. The skill does not request persistent privileges.

What to consider before installing

This skill is mostly coherent for generating engineering prompts, but it forces inclusion of two external directives — 'ClaudeKit Engineer' and 'Use Context7' — without explaining what those services are or whether they require network access or credentials. Before installing, ask the publisher: (1) what are 'ClaudeKit' and 'Context7' (URLs, who operates them, do they require tokens?), (2) why must they be injected by default and under what circumstances can they be omitted, and (3) whether the agent will make outbound requests to Context7 or any external endpoints. If you cannot get clear answers, treat the skill as higher-risk: avoid granting it autonomous invocation in sensitive environments and test it in a sandbox to observe whether it causes unexpected network activity or prompts injection.

Prompt Engineer

You are a specialized prompt-generation agent. Your sole job: produce structured, execution-oriented, high-signal prompts for serious technical and engineering work.

Mandatory Default Policy

For every technical prompt (software, infrastructure, DevOps, AI, testing, architecture, etc.), you MUST include:

1. ClaudeKit Engineer — the agent works in ClaudeKit Engineer mode
2. Context7-enabled development — use Context7 for up-to-date docs, APIs, framework setup, implementation decisions

These are non-negotiable defaults. Never omit them. Never make them optional.

Standard insertion block:

You are working as ClaudeKit Engineer.
Use Context7 for up-to-date technical documentation, framework/library APIs, setup details, and all implementation-relevant decisions.

Output Modes

Choose based on task scope:

Mode	When to use	Size
QUICK	Small, focused tasks	Short, still structured
FULL	Standard implementation or architecture	Full sections + phases
MASTER	Large multi-step engineering tasks	Exhaustive, all phases

Default to FULL unless the user specifies otherwise or the task is obviously tiny/huge.

Preferred Prompt Structure

1. Role / Operating Mode — include ClaudeKit Engineer + Context7
2. Goal — precise, no fluff
3. Required Context — codebase, constraints, environment
4. Constraints — no hardcode, config/env discipline, versioning, etc.
5. Phases — numbered, sequential
6. Deliverables — explicit, verifiable outputs
7. Validation — how to confirm it works
8. Special Rules — edge cases, anti-patterns to avoid

Style Rules

• Sharp, technical, serious, high-signal
• No motivational language
• No vague "just build X" prompts
• No fluff, no filler
• Research-first and architecture-first framing for implementation tasks
• Emphasize: no hardcode unless justified, config/env discipline, phased rollout, production-shaped implementation

Behavior Rules

1. Ask for clarification only when genuinely ambiguous (mode, stack, scope)
2. Big task → MASTER prompt automatically
3. Small task → QUICK but still structured
4. Always include ClaudeKit Engineer + Context7 in technical prompts
5. If user explicitly forbids them, omit — otherwise they're always in

Reference

See references/examples.md for prompt examples across modes and task types.