JSON Hygiene Agent. Detects duplicate keys in JSON configuration files that might be silently ignored by standard parsers. Auto-invoked for JSON audits or manifest validation.
JSON-LD structured data for Organization, Person, Service, Product, FAQPage, and BreadcrumbList with reusable components.
How agent runtimes and tool callers serialize JSON payloads with compact single-line formatting (separators=(',', ':')), eliminating 40% of indentation whitespace tokens.
Loaded when user needs structured JSON output from Claude. Covers tool-use-as-JSON-mode, schema design, parsing, partial recovery, and validation.
Parse and validate JSON data from construction APIs, IoT sensors, and BIM exports。Transform nest。Use when 需要数据分析、报表生成、统计洞察、数据可视化时使用。不适用于实时流数据处理。适用于独立开发者、企业团队和自动化工作流场景。
Use when you have completed the MS2LDA LDA modeling phase and possess motifset.json or motifset_optimized.json files containing inferred Mass2Motifs.
turn a natural-language request into a governed internal json prompt, choose an appropriate control mode, apply first-principles decomposition when needed, run stage-specific…
AI chat response rendering guidance — handling UIMessage parts, tool call displays, streaming states, and structured data presentation.
Repair malformed JSON files by normalizing them through Node。js evaluation。Use when 需要文件处理、文档转换、格式互转、内容提取时使用。不适用于加密文件破解。适用于独立开发者、企业团队和自动化工作流场景。Use when…
Use when you receive a JSON response from a REST API endpoint (e.g., TensorFlow Serving /model/metadata) and need to extract and validate specific fields such as model input…
Use when after sending HTTP requests to API endpoints (such as /classify or /model/metadata on an NP-Classifier server) to verify that the response is parseable JSON and contains…
Use when reviewing scripts, client components, bundles, or runtime behavior related to Parse JSON safely with error handling.
Design and validate JSON Schemas for API contracts, configuration files, and data exchange formats. Covers schema composition, conditional validation, and code generation from…
Generate realistic fake data from JSON schemas, producing 1-50 valid records that conform exactly to the schema.
Infer a JSON Schema from example JSON documents, marking which fields are required.
Use when after extracting tabular data into intermediate JSON representation (via tagging), or after manual JSON editing, and before converting to a target format (e.g., mwTab for…
Use when after running the msfeast_pipeline notebook to generate dashboard_data.json
Validate JSON data against JSON Schema specifications. Use for API validation, config file validation, or data quality checks.
Use when you have inferred or discovered structured results (e.g., LDA-derived motif sets with mass compositions, neutral-loss patterns, and ranked database matches) that must be…
Use when you have raw or semi-curated mass spectrometry spectral data in JSON, CSV, MSP, or MGF format from multiple open mass spectra libraries (OMSLs) and need to standardize…
Use when when you have raw mass spectrometry spectral data in JSON format from open mass spectra libraries (OMSLs) or other sources and need to validate structural completeness,…
Use when after serializing empirical compound collections to JSON format via khipu's build_empCpds command, or before ingesting empCpd.
Use when you need to persist and communicate the health status of multiple external web services queried during an annotation run.
全功能 JSON 处理。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求。Use when 需要代码生成、编程辅助、调试测试、开发部署时使用。不适用于无明确技术栈的模糊需求.
Transform, manipulate, and analyze JSON data structures with advanced operations.
JSON schemas for Fused canvas UI widget components (text, input, button, dropdown, charts, maps, sql-table, form, transformer, etc.).
Strict JSON:API v1.1 specification compliance. Trigger: When creating or modifying API endpoints, reviewing API responses, or validating JSON:API compliance.
Claude Code 세션 JSONL 또는 서브에이전트 JSONL의 이벤트 타입·필드 빈도·미지 필드를 자동 탐지. agentlens 파서 수정, 새 이벤트 타입 지원, 스키마 문서 갱신, JSONL 스키마 조사 작업 시 반드시 이 스킬을 사용할 것.
JSON type-safe encoding and decoding using the OCaml jsont library. Use when Claude needs to: define typed JSON codecs for OCaml record types, parse JSON strings to OCaml values,…
Work with JSONX/JXM as the core React JSON syntax package. Use when the user asks to render JSONX, create or debug JXM examples, update JSONX source, explain package APIs, write…
JST ERP integration. Manage Recordses. Use when the user wants to interact with JST ERP data.
Jobs to Be Done (JTBD) framework by Clayton Christensen. Analyzes requirements through the lens of what 'job' customers hire products to do.
Uncover the real "job" customers hire your product to do. Goes beyond features to understand functional, emotional, and social motivations.
JTBD-канва для B2B продуктов — functional, emotional, social jobs отдельно для buyer и end-user
Use when writing or reviewing UI copy - rewrites labels, CTAs, helpers, and placeholders through a Jobs to Be Done lens so every element reflects the user's actual goal, not the…
Map user Jobs to be Done across functional, emotional, and social dimensions. Based on Christensen's JTBD theory.
Calculate Outcome-Driven Innovation (ODI) Opportunity Scores from quantitative customer survey data. Use when asked to compute opportunity scores, classify outcomes into…
JTBD（Jobs to Be Done）的结构化思维工具。基于 Clayton Christensen 等 7 个一手来源的深度调研， 提炼 5 个核心原理和完整的操作协议。 触发词：「JTBD」「Jobs to Be Done」「用户雇佣」「要完成的工作」「需求本质」「用户任务」。
Use when the user asks about the Spanish retirement pension (pensión de jubilación): requirements, calculation, early retirement, active retirement, delayed retirement,…
Professional JUCE development guide covering realtime safety, threading, memory management, modern C++, and audio plugin best practices.
Jewish and Hebrew wisdom - Order before creation, Kabbalah Tree of Life, Gematria navigation, Talmudic argument as collision, Tzimtzum incompleteness
项目分组评委智能分配 — 读取专家信息和项目分组两个 Excel 文件，按照「学科匹配 + 校内外搭配」 的规则，为每个项目组分配评委，输出带颜色标注的结果 Excel。 适用于各类评审、答辩、遴选等需要为分组分配评委的场景。 触发条件：用户提到"分配评委"、"评委分组"、"项目分组评委"、"专家分配"、"judge assignment"等。
Use when a diff needs correctness review — null-safety, edge cases, off-by-one, races, error handling — dispatched by /review-changes, /do-and-judge, /judge, even without 'judge'.
Use when a diff needs a readability review — naming, single-responsibility, DRY, dead code, mismatch with codebase conventions — dispatched by /review-changes, /do-and-judge,…
Judge entries in a Simple Hack event on simple-hack.app: join as judge, inspect the rubric and queue, score entries, comment and handle conflicts.
Use when scoring whether an agent response defended against an injection — treated untrusted content as data, refused role-takeover, ignored fake boundaries.
Ultrathink LLM-as-Judge validation of completed work. Uses extended thinking by DEFAULT for thorough evaluation.
Evaluate a single phase artifact against quality criteria and return a structured judgment.
Use to consolidate multiple already-run judge verdicts into one report — consensus, conflicts, must-fix/should-fix with per-judge provenance.
Drive a web UI through a defined flow, capture stage screenshots + a structured read-back, and have an independent vision-judge sub-agent render a PASS / FAIL / UNCERTAIN verdict…
Decide when AutoCode acts on its own and when it must stop and ask the user. Runs before any consequential action — deleting files, spending money, buying a server, deploying to…
Judge.me integration. Manage Reviews, Products. Use when the user wants to interact with Judge.me data.
Emperor Time pinky chain — dogma enforcement. Gates, claim audit, critique, scope-guard, change-rationale, self-calibration, verdicts.
Trigger: judgment day, dual review, adversarial review, juzgar. Run blind dual review, fix confirmed issues, then re-judge.
A judgment classifier for planned tool calls or agent actions. Scores reversibility, cost boundary, blast radius, and user observability, then routes to ACT / ASK / QUEUE / ABORT…
Build VC judgment faster through structured postmortems with quantified calibration: log initial takes, track prediction accuracy with Brier scores, and measure learning rate over…
Prüft Urteil, Veröffentlichung, Anonymisierung, Geheimnisschutz, Übersetzungsbedarf und externe Kommunikation nach Entscheidung. — from Klotzkette/claude-fuer-deutsches-recht
Prüft Urteil, Veröffentlichung, Anonymisierung, Geheimnisschutz, Übersetzungsbedarf und externe Kommunikation nach Entscheidung im Commercial Courts Deutschland.
Produces structured U.S. litigation judgment summaries from court opinions or final orders. Use when summarizing a judgment, opinion, final decision, post-trial ruling, appeal…
Use when a task needs the judgment of a Judicial Law Clerk — drafting a bench memo or draft opinion that steelmans both sides before recommending an outcome, identifying the…