Explorar skills

Comprehensive PHP code review with security analysis, performance optimization, and PSR-12 compliance checking for PHP7/PHP8 projects

{{ ƔƔƔ }} Create a draft pull request to main

When isolating and fixing unpredictable or complex software bugs.

Analyze a fully-built reference application that the user wants to use as a model. Reads its architecture, conventions, tech stack, and patterns; stores a structured summary in .claude/memory/reference/ so subsequent sessions can compare the current project against it.

Enforce the FlowGoal state machine — every status transition (draft → active → {waiting_for_user, waiting_for_ci, blocked, achieved, failed, cancelled}) writes both the new lifecycle block to `.flow/goals/<id>.goal.yaml` AND a `goal-evaluation` artifact to the linked decision journal, in a single atomic operation via `bin/flow-goal-record.sh`. Use when any code path mutates `lifecycle.status`, whe

Huawei Cloud BSS billing read-only only (not AWS/Azure/other clouds; refuses pricing quotes, real-name review, and any non-billing scope): balance, spend, attribution, reconciliation, coupons, stored-value cards, enterprise/partner billing. One-page briefing via hcloud. Use only when the user explicitly mentions 华为云 / Huawei Cloud / BSS and 余额/账单/对账/资源包/代金券/储值卡/企业或伙伴账务; refuses pay, renew, refund,

Deep Python-specific security audit skill with 50+ vulnerability class coverage across 7 categories. Trigger when auditing Python code: "audit this Python app", "find Python security issues", "check Flask/Django for vulnerabilities", "Python SAST review", "check for pickle vulnerabilities", "review this FastAPI code". Covers misconfiguration, injection, crypto, XSS, deserialization, and ML/AI atta

Write in the Manzanita Research voice — warm, grounded, direct, never corporate. Use for any prose output: READMEs, marketing pages, social posts, changelogs, error messages, UI copy, blog posts, or any text that carries the brand.

Use when asked to analyze content for manipulation, propaganda, disinformation patterns, or when user provides a URL or text asking "is this manipulative?", "analyze this for bias", "check for propaganda", or similar requests. Detects emotional manipulation, suspicious timing, uniform messaging, tribal division, and missing information across 20 categories.

Humanize textos gerados por IA para evitar a detecção. Use quando o usuário quiser que textos do ChatGPT, Claude, Gemini ou outros IAs soem humanos e passem por detectores de IA como GPTZero, Turnitin e ZeroGPT.

Use when implementation is complete and you need to merge, create a PR, or clean up — verifies tests pass, presents 4 structured integration options, executes chosen workflow, and cleans up worktrees. Pairs with code-forge:worktree.

Activate a Julia project/environment for the session