Explorar skills

Shared conventions used across all PlausibleBA skills. Load this skill whenever producing, validating, or comparing any PlausibleBA taxonomy — Capability Maps, Concept Models, Value Streams, or any other structured artefact. It defines the numbering system, column order, naming conventions, MECE rules, and XLSX formatting standards that keep all outputs consistent and cross-referenceable.

Replace with what the skill does and when to trigger it. Use action verbs and task keywords agents can match.

Search past session observations using the sessions.search MCP tool. Falls back to CLI if the MCP server is not available.

Compare original site vs implementation with automated AE/SSIM diff — near-zero vision tokens. Triggers on "it looks different", "doesn't match", "compare with original", "what's wrong", "why is the impl off", "diff against ref", "verify the clone". Uses auto-diagnose to find mismatched elements from diff images without vision tokens. Falls back to reading diff images only when auto-diagnose finds

Manage the aomi skill distribution pipeline. Trigger when the user asks about platform submission status, wants to push a skill update to a distribution channel, needs to add a new platform, wants to check staleness, or asks about any platform in _registry.yaml, including PR #679, PR #575, PR #21, issue #36, clawhub, codex-marketplace, agensi, lobehub, or anthropic submission.

Step-by-step guide for creating enriched CryptoSkills agent skills. Use when building new protocol skills, contributing to the directory, or understanding the enriched skill pattern. Covers SKILL.md structure, YAML frontmatter, examples, docs, resources, templates, marketplace registration, and validation. Triggers: "create a skill", "add a protocol", "contribute a skill", "new skill template".

MUST use for ANY user request. This is a rigid requirement that applies to all tasks and conversations.

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

Deserialization vulnerability audit skill with gadget chain knowledge for all major languages. Trigger when the user asks to: "audit deserialization", "check for insecure deserialization", "find pickle vulnerabilities", "Marshal.load audit", "gadget chain analysis", "check for unsafe YAML loading", or when reviewing code that processes serialized data (JSON with type info, YAML, XML, binary format

Guide for using the cli-anything-capcut CLI (v0.4.x) to programmatically build, validate, render, and refine CapCut/JianYing video drafts. Use this skill whenever the user wants to: scaffold a CapCut project via CLI, write or import a recipe JSON, troubleshoot CapCut CLI errors, run a preview/review/render pipeline, generate a draft from natural language, or automate any video editing workflow wit

Evidence-bound transformation of vague human requirements (Jira ticket, Confluence page, free text, file path) into AI-ready specifications for coding agents. Use WHENEVER user asks to /distill, "analyze requirements", "clarify task", "vague requirements", "ambiguous AC", "task vs bug", "EARS", "Given-When-Then", "GWT", "AI-ready spec", "prepare spec for implementation", "Open Questions", "INVEST"

Network and Retrofit setup for AndroidBooster. Use when adding API endpoints, Retrofit interfaces, or configuring network layer. Uses Retrofit, OkHttp, Gson.