AI & ML

shinpr Skill

Define structural design foundation — information architecture, user flows, content model, brand direction, and AI interaction model — from validated opportunities and hypotheses

shinpr Bundle

Defines structural design artifact formats — information architecture, user flows, content model, brand direction, and AI interaction model. Use when creating or reviewing structural design documents that precede prototype generation.

theinfosecguy Skill

Synthetic inert detector regression fixture.

fabioc-aloha Skill

Use when the user wants to feel out an idea before committing to a real build — "spike this out", "try it", "is this even possible?", "compare A vs B". Throwaway experiments that decompose into 2-5 feasibility questions, build minimal observable prototypes, and return VALIDATED / PARTIAL / INVALIDATED verdicts. Disposable by design. Adapted from Hermes Agent / GSD.

ferroxlabs Skill

Internal session metrics tracking. Auto-triggered at session boundaries. Tracks tokens, agent usage, efficiency gains. View with /ijfw-status.

ferroxlabs Bundle

Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent generation.

archibate Bundle

Guide and template for converting MCP servers into self-contained Claude Code skills with a Python wrapper script. TRIGGER when creating a new MCP skill, wrapping an MCP server as a skill, or need the mcpcall script template.

archibate Bundle

AI-powered documentation for GitHub repositories via DeepWiki MCP. TRIGGER when need to understand a GitHub repository, read its documentation topics, ask questions about a repo's codebase, architecture, or usage, or explore how an open-source project works.

archibate Skill

Multi-specialist agent crew for complex, cross-cutting tasks. Activates when work spans multiple disciplines (product scoping, design, research, engineering, operations), when requirements are ambiguous and need structured breakdown, or when the user asks for planning/architecture before implementation. Orchestrates specialist roles with structured handoffs and subagent-driven development. Also triggers on "plan this", "break this down", "crew", "agents", or any task that would clearly benefit from divide-and-conquer.

archibate Skill

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

archibate Bundle

This skill should be used when the user sends an image and asks to "analyze this image", "describe this picture", "what's in this image", or any request requiring visual understanding of images. Provides image analysis using Zhipu GLM-4.6V multimodal model.

archibate Skill

Use this skill for browser automation.

aifinlab Skill

为银行经营分析提供确定性数值计算能力，涵盖百分比、同比环比、贡献度、分布、排名等银行业务常用计算，避免LLM心算幻觉

multiatlas Skill

Auditoría de seguridad de servidores MCP — antes de instalar uno nuevo y antes de cada actualización. Triple defensa (pre-instalación / pre-actualización / vigilancia continua) para que solo entren al stack MCPs auditados y las actualizaciones no entren a ciegas. Activar en cualquier proyecto con MCPs configurados, especialmente al añadir uno nuevo o ejecutar npm update.

relationalai Bundle

Bumps the plugin version across manifest files, commits, and creates a local git tag for rai-agent-skills. Pushing and publishing the GitHub release happen separately, under human review. Use when cutting a release.

relationalai Skill

Reviews RAI agent skills for structure, content quality, prompt engineering, boundaries, examples, and agent usability. Use when creating, reviewing, or auditing skills in rai-agent-skills or rai-agent-skills-private.

relationalai Bundle

PyRel v1 language — modeling syntax (concepts, properties, relationships, data loading), business rules as derived properties (validation, classification, tiers, flags), and query construction against `relationalai.semantics.Model` (selects, filters, joins, aggregates, export). Load BEFORE writing any PyRel code, even your first line — prior knowledge of the syntax is likely stale. Use whenever the user asks to model, load, derive, classify, flag, query, count, rank, aggregate, join, or export data from a RAI model, even if they don't say PyRel. Not for ontology design decisions (see rai-ontology), optimization formulation (see rai-prescriptive-problem), graph algorithms (see rai-graph-analysis), or GNN work (see rai-predictive-modeling).

relationalai Bundle

Setup and configuration for RelationalAI — first-time install walkthrough and all raiconfig.yaml tuning. Use when installing RAI, connecting to Snowflake, running RAI locally on DuckDB for development, or editing raiconfig.yaml. Not for writing PyRel model code (see rai-pyrel) or solver usage and diagnostics (see rai-prescriptive-results).

relationalai Bundle

Builds and evolves RAI ontologies — greenfield starter builds from Snowflake tables or local data, and all domain-modeling decisions (concepts, relationships, identity, subtypes, data mapping, layering, enrichment). Use when creating a new RAI model, starting a proof of concept, onboarding a dataset, or reviewing and enriching an existing ontology. Authoring the PyRel itself (syntax, data loading, rules, queries) is `rai-pyrel`.

surgepix Bundle

Restyle 1–5 reference photos into minimalist poetic editorial illustrations via SurgePix (server-locked style). Prefer this over surgepix-image-edit when the user says 极简诗意风格, 极简线条, 诗意风格, 改成极简诗意, 帮我把这张图改成极简诗意风格, 极简诗意编辑插画, 极简抽象插画, 视觉记忆面板, 极简档案海报, 摄影诗意编辑, or "poetic editorial". Language: write --prompt in the user's conversation language. Output rule: show ONLY the download URL from script stdout verbatim in a code block; NEVER fabricate or retype URLs. Local reference paths are uploaded first — API accepts URLs only. Do NOT use for general image edit (surgepix-image-edit), cinematic restaging (surgepix-generate-restaged-cinematic), or topic-based article illustrations (surgepix-generate-illustrations). If the user only says 把照片做成插画 without naming 诗意/超现实, ask first. 「极简诗意风格」is an explicit style — call this skill, do not ask and do not use image-edit.

traderalice Skill

Audit OpenAlice's AI tools end-to-end — call each one (using its declared example input as the starting point), judge whether it runs, whether its description / params / output are good, and write a review with concrete "how to change it" notes. Use when the developer wants to dogfood the tool surface, find tools that are broken / thin / confusing, or get an optimization to-do list: "audit the tools", "which tools are broken", "review all the MCP tools", "test the tool surface", "go use every tool and tell me what to fix". A half-automatic regression + tool-optimization input.

traderalice Skill

Define durable work and scheduled/headless execution with `.alice/issues/<id>.md`: structured ownership and optional `when` frontmatter plus one canonical markdown What. Use for creating or editing an Issue, choosing its assignee, schedule, prompt, delivery behavior, or health state. Use the `alice` skill instead when the goal is to ask another Session for an answer.

yipxiyi Skill

Use when migrating an existing repository or workspace into OpenArc conventions, aligning docs, specs, plans, assets, agent guides, versions, and release workflow without destructive rewrites.

yipxiyi Skill

Use when auditing repository governance read-only, or when explicitly initializing or repairing governance and patching an agent guide without destructive rewrites.

amatray Bundle

Format an informal, conversational request into a structured prompt, then execute it. Use when user invokes /prompt with a task description.

amatray Skill

Format an informal request into a structured prompt. Output only — do not execute. Use when user invokes /prompt-only with a task description or content block.

amatray Skill

Use when the user wants automated iterative plan review with convergence detection (multiple review passes without manual approval between iterations) OR wants to audit a plan's adversarial-agent contract (check that Adversary, Verifier, audit-readiness, or determinism agents are wired always-on, not conditionally gated). Triggers on "auto-review the plan", "iterate on plan review", "review my plan thoroughly", "keep reviewing until it's tight", "/review-plan-auto", "$review-plan-auto", "check whether my adversarial agents will actually fire", "audit how the plan wires the Adversary", "stress-test the safety machinery in my plan", "is this plan safe for an overnight run", "verify the plan's adversarial-agent contract", "make sure the Adversary in this plan is not just a deterministic check", or any case where the user would otherwise run `/review-plan` repeatedly.

amatray Bundle

Use when the user wants an external second opinion on a plan from the strongest available ChatGPT model via codex, or says "send the plan to GPT", "get ChatGPT to review my plan", "codex review of the plan", "external review of the plan", "second opinion on the plan from GPT", "/review-plan-codex", or wants a cross-model critique round run as a standalone step on any plan (not just empirical Bob plans). Codex runs the convergence loops; Claude supplies the independent critique; each model's findings are audited by the other.

baconpaul Skill

Reference for the Six Sines synthesizer DSP and synth engine (src/dsp/, src/synth/). Covers the node model and its patch/DSP mirroring, parameter IDs and streaming versions, signal flow, extended source modes, modulation routing, voice lifecycle, the patch/patchMain threading model, and the test suite.

baconpaul Skill

Reference for the ShortCircuit XT UI layer (src/scxt-plugin/). Covers SCXTEditor structure, the dumb-terminal model, the attachment/offset pattern for wiring controls, sst-jucegui widgets, JSON layouts, begin-edit and undo gestures, and the workflow for adding a control.

baconpaul Skill

Reference for the SpectrumWorx engine and plugin layer (src/core/, src/le/spectrumworx/engine/, src/le/parameters/). Covers the threading and ownership model, the dynamic parameter system, streaming and presets, latency, ports and side chain, MIDI, undo, and the layering rules. Routes to doc/tech/, which is the authority.

chinfi-codex Bundle

当用户需要抓取宏观市场原始数据、汇率、美债收益率、BTC、黄金/原油/天然气、纳指期货、中国 CPI/PPI/社融/PMI，或为地缘风险(伊朗局势/中东/霍尔木兹/油价)、A 股、美股研究准备宏观 evidence 时使用此 skill。脚本优先调用金十 MCP 取行情（Brent/黄金/天然气/USD-CNH），失败再用 Alpha Vantage、Tushare 与 Stooq 补充和兜底，输出 JSON 数据包；模型负责判断数据含义、写报告和说明风险。不用于宏观预测、交易建议、自动报告生成或替代正式数据终端。

chinfi-codex Skill

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

drjmf Bundle

Safely repairs and updates RagFlow agent DSLs (graphs) without causing UI corruption. Use when an agent is not responding, has broken node references, or disappears from the UI after an update.

drjmf Bundle

Generates a performance and diagnostic report for a RagFlow agent. Use when the user asks for logs, tool usage, or internal steps of a specific RagFlow dialogue or agent ID.

drjmf Bundle

Updates RagFlow dataset configurations (language, metadata generation settings) via API. Fixes the "uneditable UI" issue by using the dedicated metadata endpoint.