tripod-check
Use when auditing a prediction model or clinical AI manuscript against the TRIPOD+AI checklist. Triggers on prediction models, prognostic scores, diagnostic models, machine learning clinical tools, risk calculators, AUC/c-statistic reporting, or AI-assisted clinical decision support.
update-dev-docs
Update dev docs before session compaction to capture progress. Use before compacting conversation, ending sessions, or switching tasks.
ml-engineer
Implement ML pipelines, model serving, and feature engineering. Use for ML model integration or production deployment.
network
Debug network connectivity, configure load balancers, and analyze traffic. Use for connectivity issues, network optimization, or protocol debugging.
perf
Profile applications, optimize bottlenecks, and implement caching. Use for performance issues or optimization tasks.
poker-player
Play Texas Hold'em poker as an AI agent. Use when joining a poker game, making betting decisions, or analyzing opponents.
prime
Load context for a new agent session by analyzing codebase structure and README. Use when starting a new session or needing to understand an unfamiliar codebase.
prisma-check
Use when auditing a systematic review or meta-analysis manuscript against the PRISMA 2020 checklist. Triggers on systematic reviews, meta-analyses, pooled analyses, forest plots, search strategies, or study selection flow diagrams.
prompt-engineer
Optimize prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts.
publish-the-skill
>
python
Write idiomatic Python with advanced features. Use for Python development, refactoring, or optimization.
qing
Qing dynasty court roleplay mode. Activates imperial court persona for all agent responses. Use when user wants to enable court roleplay, mentions qing, or wants a fun imperial Chinese tone.
quarto-book
Generate Quarto Book project structure with chapters, configuration, and output settings. Use when user wants to create a book, multi-chapter document, technical manual, or asks about Quarto book setup.
quicktype
Generate TypeScript types from JSON files using quicktype CLI. Use when user wants to create types/interfaces from JSON data, API responses, or config files.
refactor
Refactor code for quality, reduce technical debt, and improve maintainability. Use for cleanup tasks and code improvements.
repo-init
Initializes a public GitHub repo with CITATION.cff, citation.bib, LICENSE (MIT), AMA+APA CSL files, README.md with badges and citation block, and gh repo description. Use when creating a new repo, setting up project metadata, or when user mentions "repo init", "badges", "citation", "CITATION.cff", or "license setup".
research-plan-implement
Enforces a three-phase RPI workflow (Research, Plan, Implement) for code changes. Use when tackling non-trivial features, refactors, or bug fixes in medium-to-large codebases to prevent context waste and ensure correctness over speed.
retro
Review the current Claude Code session conversation. Extracts only human-readable content (user prompts and agent prose responses, skipping tool calls and tool results), then produces a structured retrospective report covering accomplishments, efficiency improvements, English corrections, learning recommendations, and CLAUDE.md suggestions. Use when the user asks to review, retrospect, or summarize the session — especially at the end of a work session.
rust
Write idiomatic Rust with ownership, lifetimes, and traits. Use for Rust development, memory safety, or systems programming.
sc
Unified SuperClaude workflow skill with subcommands for analysis, building, documentation, git, implementation, and more. Use for any structured development workflow.
zettel
Converts narrative medical text into Pocket Medicine bullet-style notes with proper abbreviations, then modularizes sections exceeding 20 lines into linked standalone files.
scientific-figure-assembly
Assemble multi-panel scientific figures with panel labels (A, B, C) at publication quality (300 DPI) using R. Use when combining individual plots into journal-ready figures.
vm-docker
Use when deploying Docker services on the local VM (hostname: vm, Pop!_OS) with Traefik reverse proxy and Homepage dashboard. Covers crane image workflow, Traefik file-provider registration, Homepage services.yaml entries, and compose templates on the traefik-proxy network.
search
Expert web research with advanced search techniques. Use for deep research, information gathering, or fact verification.
security
Security audits, vulnerability detection, and secure coding. Use for security reviews, auth implementation, or OWASP compliance.
skill-gen
Generates new Claude Code skills with proper structure and best practices. Use when user asks to create a new skill, slash command, or wants to automate a workflow. Guides through requirements gathering, structure generation, and validation.
visualization-check
Use when reviewing a data visualization or figure for clarity, checking if a graph communicates its message without additional context, or iterating on R/Python plot scripts until a naive reader can fully understand the figure.
slidev
Create and present web-based slides for developers using Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, or teaching materials.
sql
Write SQL queries, optimize execution plans, and design schemas. Use for query optimization, complex joins, or database design.
strobe-check
Use when auditing an observational study manuscript (cohort, case-control, or cross-sectional) against the STROBE checklist. Triggers on retrospective studies, hospital data, registry/database studies like TCGA, SEER, NHIRD, or any non-randomized clinical research.
test-auto
Create test suites with unit, integration, and e2e tests. Use when setting up tests, improving coverage, or when user asks about testing.
vale
Runs Vale prose linter on markdown/text files and auto-fixes issues. Use when the user asks to lint, proofread, or improve writing quality of markdown or text files.
agent-identity
Set up persistent agent identity files (AGENT.md, USER.md, MEMORY.md) and teach the agent to read them at every session start. Works in any Claude Code project — no external dependencies required. Trigger words: who am I, identity, remember me, agent name, my principles, who are you, what are my values.
agent-memory
Teach cross-session memory patterns using MEMORY.md — what to save, how to organize it, how to maintain it over time, and how to structure topic files as memory grows. Works in any Claude Code project with no external dependencies. Trigger words: remember this, save for later, across sessions, persistent memory, don't forget, note this, keep this, write this down.
command-guard
Set up a PreToolUse hook in .claude/settings.json that blocks dangerous commands — rm -rf, force push, database drops, and others — before they execute. Teaches the pattern of safety hooks for any Claude Code project. Trigger words: safety, guard, block dangerous, protect, prevent destructive, safe mode, dangerous commands, risky operations.
instar-scheduler
Schedule recurring agent tasks using cron expressions. Use when the user asks to run something on a schedule, check something periodically, automate a recurring task, set up a cron job, or wants work to happen while they're away. Trigger words: schedule, recurring, cron, every hour, every day, run daily, periodic, automated.
instar-session
Spawn, monitor, and communicate with persistent Claude Code sessions running in the background. Use when a task needs to run without blocking the current session, when the user asks to do something in the background, or when a long-running task needs its own context window. Trigger words: background task, spawn session, persistent, run in background, parallel, separate session, async task.
instar-identity
Establish and recover persistent agent identity that survives context compaction, session restarts, and autonomous operation. Use when an agent needs to know who it is, recover after context compression, orient at session start, or understand the identity infrastructure. Trigger words: who am I, remember, identity, after restart, compaction, context loss, who am I working with, my principles.
instar-telegram
Send and receive messages via Telegram for two-way agent communication. Use when the agent needs to notify the user, alert them about something, relay a response, or when Telegram messaging is the requested channel. Trigger words: send message, Telegram, notify, alert user, message me, ping me, let me know, reach out.
smart-web-fetch
Fetch web content efficiently by checking llms.txt first, then Cloudflare markdown endpoints, then falling back to HTML. Reduces token usage by 80% on sites that support clean markdown delivery. No external dependencies — installs a single Python script. Trigger words: fetch URL, web content, read website, scrape page, download page, get webpage, read this link.
instar-feedback
Submit structured feedback about instar bugs, feature requests, improvements, or innovations worth sharing. Use when something isn't working, when a feature is missing, when you've built something that could benefit all agents, or when the user mentions a problem with instar. Also use proactively after building significant features — ask yourself if other agents would benefit. Feedback is relayed agent-to-agent to instar maintainers. Trigger words: bug report, feedback, issue, something's wrong, feature request, this isn't working, improvement, suggest, built something useful, other agents could use this.
credential-leak-detector
PostToolUse hook that scans Bash tool output for leaked credentials — API keys, tokens, private keys, and secrets — before they reach the conversation. Blocks critical leaks, redacts high-severity matches, and warns on suspicious patterns. 14 detection patterns covering OpenAI, Anthropic, AWS, GitHub, Stripe, Google, Slack, SendGrid, Twilio, PEM keys, bearer tokens, and generic secrets. No external dependencies. Trigger words: security, credential leak, secret exposure, key detection, token scan, API key leaked, credential guard, secret scanner, prevent credential leak.
instar-dev
Instar-specific development skill used by the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities). Wraps /build with mandatory side-effects review, signal-vs-authority principle check, and artifact generation. Structural enforcement via pre-commit/pre-push hooks — the instar repo refuses commits and pushes that didn't come through this skill. NOT a user-facing skill — end users should never invoke it.
agent-passport
View this agent's digital passport (identity + trust + allowed/forbidden actions) and verify a peer's passport against a proposed action (EXO 3.0).
systematic-debugging
Structured 4-phase debugging methodology that prevents blind probing and guesswork. Forces root cause identification before any fix attempt. Use when encountering bugs, errors, unexpected behavior, test failures, or when something "just stopped working." Trigger words: debug, bug, error, broken, not working, fix this, something's wrong, investigate, root cause, why is this failing, trace the issue.
spec-converge
Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration, decision-completeness, lessons-aware) and real cross-model external reviewers routed through the agent's own installed CLIs (codex → GPT-tier, gemini → Gemini-tier; one pass per available family) until convergence, then produce a comprehensive ELI10 convergence report. Output is a spec tagged review-convergence — one of the two tags /instar-dev requires before it will touch instar source. NOT user-invocable; run by the instar-developing agent before any spec-driven /instar-dev work.
knowledge-base
Ingest URLs, documents, and transcripts into a searchable knowledge base. Query past research and curated documentation using full-text search. Trigger words: ingest, knowledge base, look up, search knowledge, what do we know about, research, index this, add to knowledge base.
iterative-converging-audit
Run any "find all instances of X" sweep — a security audit, a safety audit, a code review, a research question, a compliance check — as an iterative loop that does NOT stop at one pass. Audit → fix → RE-audit → … until a clean pass returns zero NEW discoveries. Use whenever thoroughness matters and a single pass would miss things. Trigger words: audit, sweep, find all, review everything, comprehensive, thorough, exhaustive, security review, safety audit, no stone unturned, did we get everything, convergence.
agent-readiness
Score a task or workflow on its coordination-vs-judgment ratio to tell whether it's a good agent candidate (EXO 3.0 task-decomposition matrix).
stata-toolkit
Activate when users mention Stata commands, .do files, regressions, econometrics, stored results, graphs, dataset inspection, replication, or Stata errors. Route the task through mcp-stata tools and the specialized research skills instead of treating it as plain text coding.
Page 696 of 1718 · 85870 results
