AI & ML

buildpad-ai Bundle

Plan and implement a complete feature using spec-driven development. Analyzes requirements, designs data model, selects Buildpad components, and produces spec artifacts (requirements.md, design.md, tasks.md) with a testing strategy. Use when the user wants to add a new feature, module, or capability to an existing DaaS project.

buildpad-ai Bundle

Generate a complete collection with database migration, API routes, UI pages (list + form), TypeScript types, and tests. Creates everything needed for a new data entity in a DaaS application. Use when the user wants to add a new collection, table, entity, or data model to the project.

buildpad-ai Skill

Delegates focused work to Kiro subagents that run in isolated context. Use when work can run in parallel, when a specialized agent fits (code review, testing, security, research), or when a long task would otherwise bloat the main conversation. Trigger with "run subagents to ...".

oliver-kriska Bundle

Tidewave MCP runtime tools — debugging, smoke testing, live state; Use when evaluating code in a running Phoenix app.

encod3d-sec Skill

Capture a Burp Suite Repeater request/response as a PoC image (targets/<eng>/poc/) by driving the Burp MCP + the Kali GUI. Replays a request in a Repeater tab, sends it, and grabs the request+response panes - a Burp-native PoC (client report / CTF writeup). Use when you want the evidence to come from Burp rather than a curl/terminal card, or whenever you drive a target through Burp and need the images. Pairs with hunt-burp.

encod3d-sec Skill

CTF challenge router - fingerprint a challenge (file type / prompt / artifacts) into its category (pwn, rev, crypto, forensics, stego, web, osint, hash) and route to the matching wiki page, tools, and first moves. Wiki-first.

encod3d-sec Skill

Bring up a REAL, visible, interactive chromium on the Kali VM that the operator logs into (Smart-ID / Mobile-ID / any manual auth or MFA/CAPTCHA), while the agent drives and observes it live through the chrome-devtools MCP (navigate, DOM snapshot, network capture, screenshots, console, evaluate). Use whenever a target needs a MANUAL login the agent cannot complete headlessly, when you need to capture an authenticated session / the real API calls a page makes, or to confirm/screenshot a DOM-XSS. Triggers - "open a browser", "log in manually", "smart-id / mobile-id / national id login", "mfa / 2fa login", "solve the captcha", "drive the browser", "capture the authenticated session / network".

paulingram Skill

Use when a QA agent (bug-replicator, flow-executor, integration) detects email-touching work in its slice — template files, SMTP / transactional-email client imports, or email-sending function calls. The cross-cutting email-testing discipline that uses Mailpit (a local SMTP trap, zero external dependencies) as the default capture engine. The body documents the four phases (E1 detect email surface, E2 provision Mailpit, E3 capture sent emails + classify every link by reading template source, E4 follow every link in Playwright and complete each user flow it initiates), the rule that the agent reads the template source BEFORE the send, that EVERY link in EVERY email is tested (not just the primary CTA), mandatory teardown, and the project-level design.md provider override.

paulingram Skill

Use when creating or updating a README or any top-level project document and you want the house "bitmap" aesthetic — ASCII block-letter banner, gradient section dividers, box-drawing panels and inventory grids, ASCII flowcharts, logic maps that show routing and gates, a status timeline, colored badges, and a per-project color theme. Triggers — authoring or refreshing a README, the user asks for "flair" / "colorful" / "centered" / "bitmap" / "make it look good" styling, a new plugin or project needs its README, a version bump needs the README brought current, or a project has non-trivial control flow that the README must make legible. Reference guide — provides the canvas + centering rules, the pipe-table / ASCII-graph alignment rules, the banner / divider / panel / flowchart / logic-map / timeline patterns, the GitHub-safe + ANSI color model, the preset theme palettes, the interactive theme picker, and the consistency rules.

paulingram Skill

Use when a codebase consumes data tables/databases and you need a self-contextualizing data dictionary — given code and/or documentation that reference data, derive the data model, define every field, and record provenance + corroboration. Branches by input type (code / documentation / direct user input); recursively follows objects that mask DB connections to find table references; when context is exhausted and a database is REACHABLE, performs live inspection (schema read + ~100-row sampling) to infer grain + field meaning; produces the standard artifact DATA_DICTIONARY_MAP.md (+ data-dictionary.json sidecar) with a by-field/by-table reference map and a relational/blend map. Runs during initial codebase exploration (after codebase + integration mapping) and is kept current whenever agents do database development. The deterministic pieces live in scripts/data_dictionary/data_dictionary.py; this skill is the contract.

paulingram Skill

Use to reduce the token cost of agents' INTERNAL communication — inter-agent messages, scratch notes, internal reasoning summaries — by writing tersely ("talk like a caveman"), WITHOUT harming external output quality (output to users / other systems / final deliverables stays full-quality; TC-1). Provides a deterministic stdlib "caveman" compressor (drops articles / politeness / intensifiers + wordy phrases, preserves content words / identifiers / numbers / code verbatim) and documents evaluating a heavier ML token-compression package (LLMLingua-style) for developer agents while they run (TC-3). The deterministic engine lives in scripts/token_compression/caveman.py; this skill is the contract, including the hard internal-only boundary.

paulingram Skill

Use when MemPalace is installed and you are authoring or auditing a project's CLAUDE.md (or AGENTS.md). When MemPalace is present, CLAUDE.md becomes a thin POINTER document — it tells the agent WHERE to find things so context is loaded on demand, rather than CONTAINING the full context — and it stays very small. Carries two parts — standards that point to a reference DB / reference MemPalace, and customizations the user can toggle on/off. The deterministic assessor + generator live in scripts/claude_md/claude_md_efficiency.py; this skill is the contract. CONDITIONAL on MemPalace being installed — with no MemPalace, a self-contained CLAUDE.md is correct and this discipline does not apply.

paulingram Skill

The Verified Agent Output (VAO) framework — six layers of machine-mediated verification of agent claims. Closes the class of "agent silently does the wrong thing" failures the plugin has been patching one at a time. Schema v7 + 5 deterministic tool verdicts + adversarial reviewer pairings + run-history shape detection + Skill-invocation audit.

paulingram Skill

Use when the endpoint-tracer agent is producing a per-endpoint internal call-trace for an in-scope endpoint subset, or when any phase needs to consult or build the Code & Data Lineage Graph (CDLG). Defines ENDPOINT_TRACE_MAP.md + lineage-graph.json, the two-layer extraction contract (intra-service LSP-first static seed + LLM-refine on ambiguity; inter-service route/contract matching reusing INTEGRATION_MAP + INTERACTION_INTUITION_MAP), the func:// / asset:// identity nomenclature, runtime-witness verification against code-path-witness.json (the trust gate), subset-on-demand + transitive freshness + the cost ceiling. The deterministic pieces live in hooks/lineage_graph.py.

paulingram Skill

Use when a failing test escalates back to the orchestrator via a solution requirement before spawning a Phase 2 fix team. Spawns three diagnostic-researcher agents in parallel — each independently maps the FULL code flow from test input to failing assertion, then theorizes ranked diagnostic hypotheses anchored to file-line evidence. The system-architect agent reviews all three drafts for robustness, identifies coverage gaps, sends researchers back for deeper investigation if needed, and only then produces a consolidated diagnostic plan that becomes mandatory input to the fix team brief. The fix team never starts work without an approved diagnostic plan when this skill applies.

paulingram Skill

Use when a feature that creates or edits entities has been implemented and you must verify that every attribute those entities expose which a user should be able to control actually has a working end-to-end editing path — UI control through state through the API into the database and back. Triggers — a "create a thing" or "edit a thing" flow exists; an entity has attributes (title, name, description, status, tags, owner, ...) and you are not certain every one a user should set is actually settable and persists; a value shows in the UI or the data model but you cannot find where the user sets it; Phase 5 cross-layer verification; an on-demand editability audit via /architect-team:editability-audit. Spawns three editability-reviewer agents that independently reason through what must be editable, argue to a converged list, route gaps as solution requirements, and re-review after fixes until all three agree the editable surface is complete.

paulingram Skill

Use when visual-fidelity reconciliation needs to be independently verified against the live running app — at Phase 5, or via the visual-qa command. Spawns a three-role team — visual-capture agents start the live app and capture screenshots plus computed-style DATA for every DESIGN_MAP screen (countable, hard-to-fake artifacts); visual-analyzer agents perform objective structural analysis (a deterministic data diff of the captured values against the design spec, a pixel diff against the design reference image, and a code cross-check); then the system-architect synthesizes the per-screen gap lists holistically, clustering them into root causes and routing fixes. Replaces the single-agent verifier — capture, analysis, and synthesis are separate roles so no one agent can cut a step inside itself.

paulingram Skill

Use when designing or reviewing an application that embeds an LLM agent and you need the agent's output to be guaranteed consistent and standardized. Encapsulates best-in-class output-standardization techniques (MCP-1…3) — an explicit output contract (a closed JSON Schema), a structured-output mechanism the model is FORCED to call, validation of every produced value against the contract, and retry-on-mismatch. Applies whenever an embedded agent is asked to produce something, so its outputs are reliable to parse and consume. The deterministic contract builder + validator + completeness assessor live in scripts/mcp_design/output_contract.py; this skill is the contract and the mcp-design-agent is the worker.

paulingram Skill

Use when the orchestrator is dispatching teammates in Phase 2 or capturing review-gate evidence in Phase 3. Defines non-overlapping file-scope rules, plan-approval-mode triggers, direct teammate-to-teammate messaging conventions, the review-gate evidence file schema (v7 — the teammate's 17-field self-review including the 5 Verified Agent Output fields, plus an independent task-reviewer verdict), the independent task-reviewer dispatch, the teammate manifest format the SubagentStop hook reads, and escalation policy on repeated hook rejection.

selina2025-alt Skill

AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道"今天 AI 圈有什么"、"AI 日报"、"AI HOT"、"AI 资讯"、"AI 热点"、"最近 AI"、"OpenAI/Anthropic/Google 最近发布了什么"、"AI hot today"、"AI news today"、"看一下 AI 行业动态"、"今天有什么大模型发布"、"昨天 AI 圈"、"看下精选条目"、"AI HOT 精选"、"最近一周的 AI 论文"、"AI 模型发布"、"AI 产品发布"、"AI 行业动态"、"AI 技巧与观点" 等任何中文 AI 资讯查询时使用。即使用户只说"AI 圈"、"AI 新闻"、"AI 日报"，或者只是问"今天发生了什么"且上下文是 AI / 大模型 / LLM / 创业领域，也应该触发本 Skill。Skill 会直接 curl 公开 REST API 拉数据并整理成中文 markdown 简报，不需要用户配置任何 API Key 或 MCP server。**不要 undertrigger**——用户问 AI 资讯而你不调本 Skill 就是把过时的训练数据当作今日新闻，对用户有害。

selina2025-alt Skill

Reading companion agent. Accompanies user through any text (books, articles, essays, papers, news) with translation, structural annotation, deep questioning, and cross-domain insights. Detects language, translates English to Chinese (faithfulness-expressiveness-elegance), guides reader to understand the author and encounter real questions. Use when user says '伴读', '陪我读', '读这篇', 'read with me', 'companion read', or shares a text/URL wanting guided reading.

selina2025-alt Bundle

多Agent蜂群并行协作，纯git自组织，适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。

selina2025-alt Skill

Huashu Prompt Save

selina2025-alt Bundle

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

selina2025-alt Bundle

Build a complete narrated B-roll/mixed-footage video from an uploaded article, document, inline script, or narration audio. Use when the user needs exact-text TTS, ASR from audio-only input, semantic timeline splitting, key sentence detection, YouTube/reference-video cuts, free-resource/Pexels/Pixabay B-roll, one-line subtitles, FFmpeg rendering, structured manifests, and a workflow that can be migrated into another agent system or GitHub project.

selina2025-alt Bundle

Two-stage channel material workflow for Chinese articles: generate platform-specific high-cognition titles and 5-8 optimized tags first, pause for human review, then after confirmed title generate cover prompt/image and final publishing package. Use when asked to turn an article into titles, tags, cover copy, Xiaohongshu/Douyin/Shipinhao/WeChat channel assets, or to follow a mandatory title-review-before-cover workflow.

romancola-glitch Skill

MCP: инструменты 1c-platform-tools

cyz26 Bundle

Deprecated and not recommended for new use. Legacy guidance for installing, updating, diagnosing, configuring, and operating Agent Reach only when the user explicitly asks for that local toolchain.

cyz26 Skill

Use when auditing AgentKB frontmatter, context packs, and raw-source freshness.

cyz26 Bundle

Configure and use Playwright in Codex with a CLI-first workflow and MCP fallback.

cyz26 Skill

Use when answering from AgentKB Markdown without full-vault scans.

cyz26 Skill

Use when local files, PDFs, office documents, URLs, Feishu/Lark docs, or Drive folders should enter AgentKB source intake.

cyz26 Skill

Use when raw AgentKB sources need durable Markdown notes.

cyz26 Skill

Use when completed work needs durable AgentKB Markdown updates.

cyz26 Skill

Use when free-form input should enter the personal-first AgentKB vault.

cyz26 Skill

Use when context-pack.md is stale, oversized, or missing recent AgentKB work.