agents-evolution

In the author's own words, from each skill's SKILL.md — showing the first 30 of 40 files.

• your-skill-name

  Краткое описание скилла (1-2 строки). Используется для авто-определения когда пользователь просит что-то связанное.

  .agents/skills/.template/SKILL.md on GitHub (opens in a new tab)

• avoid-ai-writing

  Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detection-only mode that flags patterns without rewriting.

  .agents/skills/avoid-ai-writing/SKILL.md on GitHub (opens in a new tab)

• caveman

  Ultra-compressed communication mode. Slash token usage ~75% by speaking like caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

  .agents/skills/caveman/SKILL.md on GitHub (opens in a new tab)

• codex-cli-permissions-and-session-resume

  Use when the user asks how to check Codex access mode, continue the previous dialog instantly, use `codex resume`, or recover the latest session id from local Codex session files without rereading old chats.

  .agents/skills/codex-cli-permissions-and-session-resume/SKILL.md on GitHub (opens in a new tab)

• critique

  Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

  .agents/skills/critique/SKILL.md on GitHub (opens in a new tab)

• autofix-bot-api

  Scan code for security vulnerabilities, leaked secrets, and dependency issues using the Autofix Bot API (api.autofix.bot), and auto-fix detected issues. Use this skill when asked to: (1) Scan or analyze a repository or code for security issues, secrets, or vulnerabilities using Autofix Bot, (2) Upload/sync a local git repository to Autofix Bot for analysis, (3) Run Autofix Bot on code changes, pu…

  .agents/skills/deepsource-autofix-bot-api/SKILL.md on GitHub (opens in a new tab)

• deepsource

  Retrieve code review results from DeepSource — issues, vulnerabilities, report cards, and analysis runs. Use when asked about code quality, security findings, dependency CVEs, coverage metrics, or analysis status.

  .agents/skills/deepsource-platform/SKILL.md on GitHub (opens in a new tab)

• engineering-principles

  Pragmatic coding principles: SOLID, KISS, DRY, YAGNI in balance. Use when writing code, refactoring, reviewing, or designing architecture. Prevents over-engineering while maintaining code quality. Триггеры: "напиши код", "рефактори", "code review", "архитектура", "engineering principles", "SOLID", "KISS", "DRY", "YAGNI", "design this", "how to structure", "разбей на модули", "спроектируй архитект…

  .agents/skills/engineering-principles/SKILL.md on GitHub (opens in a new tab)

• explain-complex-code

  Навык объяснять сложный код простым языком. Активируется только по запросу: объясни, разбери, что тут, как работает, eli5.

  .agents/skills/explain-complex-code/SKILL.md on GitHub (opens in a new tab)

• external-resources-catalog

  No description in the SKILL.md.

  .agents/skills/external-resources-catalog/SKILL.md on GitHub (opens in a new tab)

• git-secrets-precommit-scanner

  No description in the SKILL.md.

  .agents/skills/git-secrets-precommit-scanner/SKILL.md on GitHub (opens in a new tab)

• kirospec-basic

  Create and maintain .kiro specifications from local scripts without external folder dependency.

  .agents/skills/kirospec-basic/SKILL.md on GitHub (opens in a new tab)

• live-runner

  Запуск скриптов, серверов, тестов, билдов на лету. Реалтайм-мониторинг, точечная остановка процессов, отладка по ходу выполнения. Триггеры: «запусти», «прогони», «проверь», «почини», «останови», «посмотри логи», «на ходу», «реалтайм», «realtime», «на лету», «мониторь», «отслеживай», «проверяй в процессе».

  .agents/skills/live-runner/SKILL.md on GitHub (opens in a new tab)

• logging-helper

  Стратегия логирования, форматы, уровни, отладка через логи, поиск edge cases и багов. Триггеры: «добавь логи», «логирование», «trace», «отслеживай баг», «edge case», «найди причину», «почему упало», «что тут произошло», «логирование в продакшене».

  .agents/skills/logging-helper/SKILL.md on GitHub (opens in a new tab)

• outline-vpn-basic

  KISS operations skill for Outline VPN on VPS (install, key lifecycle, status, limits).

  .agents/skills/outline-vpn-basic/SKILL.md on GitHub (opens in a new tab)

• secrets-env-manager

  Validates environment variables in CI, prevents secret leaks, enforces masking, and provides fail-fast validation with clear documentation. Use for "secrets management", "env var validation", "credential security", or "secret masking".

  .agents/skills/patricio0312rev-ci-cd-secrets/SKILL.md on GitHub (opens in a new tab)

• env-secrets-manager

  Manages environment variables and secrets securely with encryption, rotation, and provider integration. Use when users request "secrets management", "environment variables", "API keys", "credentials storage", or "secret rotation".

  .agents/skills/patricio0312rev-env-secrets-manager/SKILL.md on GitHub (opens in a new tab)

• secrets-scanner

  Detects leaked API keys, tokens, passwords, and credentials in code with pre-commit hooks, CI checks, scanning rules, and remediation procedures. Use for "secret scanning", "credential detection", "API key leaks", or "secret management".

  .agents/skills/patricio0312rev-secrets-scanner/SKILL.md on GitHub (opens in a new tab)

• secret-guard

  Mandatory secret scanning before any git operation. MUST trigger automatically before git commit, git push, git add, PR creation, or any commit-related skill. Scans staged files for API keys, tokens, credentials, and other secrets to prevent accidental exposure in version control.

  .agents/skills/pr-prep-secret-guard/SKILL.md on GitHub (opens in a new tab)

• pre-commit-setup

  No description in the SKILL.md.

  .agents/skills/pre-commit-setup/SKILL.md on GitHub (opens in a new tab)

• project-bootstrap

  No description in the SKILL.md.

  .agents/skills/project-bootstrap/SKILL.md on GitHub (opens in a new tab)

• git-workflow

  Git workflow patterns - conventional commits, branch naming, PR templates, merge strategies. Use when: commit, PR, branch naming, git workflow, conventional commits, semantic versioning.

  .agents/skills/scientiacapital-git-workflow/SKILL.md on GitHub (opens in a new tab)

• security

  Application security patterns - authentication, secrets management, input validation, OWASP Top 10. Use when: auth, JWT, secrets, API keys, SQL injection, XSS, CSRF, RLS, security audit, pen testing basics.

  .agents/skills/scientiacapital-security/SKILL.md on GitHub (opens in a new tab)

• session-recall

  Recover and summarize prior Codex conversations from local Codex history and session logs. Use when the user asks what happened in a previous chat, asks to "remember" past work, wants the last or previous session, gives a specific date or approximate time, wants to search old dialogs by keyword/topic/project, or asks to inspect Codex files/config for prior conversation context.

  .agents/skills/session-recall/SKILL.md on GitHub (opens in a new tab)

• skill-file-structure

  Паттерн организации файлов скилла: SKILL.md + подпапки для скриптов/ресурсов. Никогда не держать инлайн-код в SKILL.md — выносить в scripts/.

  .agents/skills/skill-file-structure/SKILL.md on GitHub (opens in a new tab)

• spec-mode

  Use when the user asks to structure work as specifications, requirements, design docs, team task lists, or a `.spec/<slug>/TASK.md + Requirements.md + Design.md` workflow in Russian. Use this skill to scaffold and maintain spec packs with traceability between subtasks and requirements.

  .agents/skills/spec-mode/SKILL.md on GitHub (opens in a new tab)

• subagent-creator-universal

  Создание кастомных субагентов для ЛЮБОГО AI CLI: Qwen Code, Codex, Claude Code, Factory Droid, Gemini CLI, OpenCode, GitHub Copilot CLI. Use when: создать агент, subagent, custom agent, сабагент, агент для CLI, кастомный субагент, agent for CLI, copilot agent

  .agents/skills/subagent-creator-universal/SKILL.md on GitHub (opens in a new tab)

• agentic-actions-auditor

  Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlist…

  .agents/skills/tob-agentic-actions-auditor/SKILL.md on GitHub (opens in a new tab)

• differential-review

  Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.

  .agents/skills/tob-differential-review/SKILL.md on GitHub (opens in a new tab)

• fp-check

  Systematically verifies suspected security bugs to eliminate false positives. Produces TRUE POSITIVE or FALSE POSITIVE verdicts with documented evidence for each bug.

  .agents/skills/tob-fp-check/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 127k stars · 1 skill