Навыки: Разработка

List known projects and their instinct statistics

This skill should be used when the user wants to list all projects, switch projects, rename a project, enable/disable PR...

Query and interact with Prometheus HTTP API for monitoring data. Use when Claude needs to query Prometheus metrics, exec...

Promote project-scoped instincts to global scope

Run the SPEAKMAN.AI environment promotion gate (local→DEV, DEV→STG, STG→PROD) and produce a pass/block report on whether...

Turn one recurring pattern from a promoter scan into a complete, reusable skill in this library's format: a SKILL.md wit...

Enforce evidence-backed promotion criteria for candidate learnings. Use when the user runs /evolution promote <id>. Wrap...

Build a promotion case that proves you're already operating at the next level. Use when asked to write a promo packet/ca...

v0.0.36 — Use when asked for prompt_engineering or when creating or editing AI instructions in prompt Markdown, includin...

Prompt caching for Claude API to reduce latency by up to 85% and costs by up to 90%. Activate for cache_control, ephemer...

Builds complete, optimized Claude prompts and Project scaffolds from task descriptions. Use when building, designing, cr...

Convert between Claude Code command markdown files (*.md) and GitHub Copilot prompt files (*.prompt.md). Use when portin...

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, ev...

Makes a repository AI-native by creating AGENTS.md, .cursorrules, and documentation that helps any AI agent understand t...

Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output...

Write effective prompts for AI coding agents. Use when crafting system prompts, implementing chain-of-thought reasoning,...

Improves user prompts by adding context, clarifying intent, and structuring for better AI responses. Use when user reque...

Generate and iteratively harden prompts and templates using frozen evaluation harnesses and adversarial validation.

Prompt injection attack prevention and defense

A comprehensive collection of battle-tested prompts inspired by [awesome-chatgpt-prompts](https://github.com/f/awesome-c...

Query the local Claude Code prompt library (52 official prompts, tagged by SDLC phase, category, and role) when composin...

Analyze raw prompts, identify intent and gaps, match Codex components (skills/commands/agents/hooks), and output a ready...

Author and execute "prompt packs" — a big job broken into a sequence of self-contained, independently-shippable prompts,...

Rewrite the user's rough task request into an executable brief, then execute the brief instead of the raw request. Load...

Convert prose prompts into compact, structured XML prompt contracts through staged passes. Use when a user asks to struc...

Generate and tune an AST-derived census of model-visible text in TypeScript or JavaScript. Use to map prompts, hooks, to...

Creates reusable prompt templates with strict output contracts, style rules, few-shot examples, and do/don't guidelines....

Design reusable prompt templates that encode domain-specific patterns for recurring AI development tasks.Use this skill...

プロンプトのテスト、評価、反復改善を専門とするスキル。A/Bテスト、評価メトリクス、自動化されたプロンプト品質保証により、本番環境で信頼性の高いプロンプトを実現します。Anchors:• Test-Driven Development: B...

Turn a natural-language app idea ("an app that...") into a working, double-clickable Windows .exe — with ZERO git, GitHu...

Use when a natural-language task must be converted into a role-neutral, statically validated one-shot plan, workflow, or...

Use when adapting, migrating, or writing a prompt or agent contract that will run on Claude Opus 5 (API id claude-opus-5...

You are a helpful assistant that can assist in writing, abstracting, annotating, and summarizing Python code.

Write, validate, and optimise PromQL queries for Prometheus and Grafana Cloud Metrics. Use when the user asks to query m...

Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving,...

Run proof-driven development using Lean 4 for formal verification - comprehensive skill handling both design (planning)...

Use when generating ZK proofs server-side, building proof-as-a-service backends, offloading proof computation from clien...

Use when building witness data for ZK proofs, showing proof generation progress to users, implementing disclosure consen...

Use before saying work is done, fixed, or complete after changing code. Run the project's checks, show their results, an...

Use before saying work is done, fixed, or complete after changing code. Run the project's checks, show their results, an...

Extract proof points from portfolio case studies and generate punchy scripts with storyboards. Use when user wants to cr...

Every TAP Threat Insight endpoint, plus a local threat store that answers the cross-endpoint questions - who is both a...

Transcribe a video with Sonilo and translate the transcript into editable .srt files — one per target language, plus the...

Solve a request strategically and architecturally rather than tactically. Use when the user invokes /proper, asks for "t...

Generate property-based tests using QuickCheck/Hypothesis-style frameworks that verify invariants over randomly generate...

Design and write property-based tests (Hypothesis for Python, proptest for Rust, same ideas for fast-check/QuickCheck):...

Writes, reviews, and debugs property-based tests — Hypothesis, fast-check, proptest, jqwik, rapid, and Echidna or Medusa...

Use this skill for property tests for parsers, validators, transforms, state machines, edge cases. Trigger when the task...