Agent skills for Claude Desktop

Run a managed pentest of a web app or API through the app.strix.ai REST API — no local Docker, LLM key, or install needed.

Surface the structural truth of the codebase: coupling, cycles, dead code, parallel implementations, deprecated paths, abandoned…

Use this skill to choose the dominant information structure for a website, interface, portfolio, archive, product page, profile…

Use to write the NEJM structured abstract — four headed sections (Background, Methods, Results, Conclusions), ≤250 words, with the trial…

Extract answer keys from Chinese Gaozhong-style English exam papers (PDF or image) and format them into a standardized structured output.

Executes structured frontend code changes based on confirmed technical designs while maintaining traceable implementation logs and…

Evaluate raw Strudel/Tidal code directly — for power users

Verify that functionality migrated from Struts 2 to Spring works correctly in the running application from the API, client, and user…

Agent-only playbook for stuck or missing ordinary Firstmate direct reports.

Orchestrates an end-to-end educational assessment workflow covering rubric design, error analysis, homework grading, student growth…

Transforms raw classroom observations into natural, authentic, ready-to-send Chinese parent feedback messages via WeChat.

Use when designing studies and measurement for a Journal of Applied Psychology (JAP) manuscript so they meet the journal's high bar on…

Use when designing the multi-study package for a Journal of Personality and Social Psychology (JPSP) manuscript — sequencing studies…

Natural-language TV control via the stv CLI.

Apply a named visual style or brand look to a Figma file — writing its palette as local color variables, its type rules as text styles…

Fetch and apply reusable creative styles (visual + voice) from StyleRef.io.

Switches the conversation to Homeric epic style.

Switches the conversation to hard-boiled noir narration style.

Switches the conversation to Yoda's speaking style from Star Wars.

Analyzes, clusters, and prioritizes product backlogs to generate iterative release recommendations and identify dependencies.

Use when the user explicitly asks for subagents, parallel agents, worker agents, independent code review, multi-agent codebase…