116 skills · sorted by relevance
Design text extraction for forms, invoices, and quizzes using regex, rules that match text patterns. Check extraction confidence and send uncertain items to an LLM for review, with guidance on testing and tracking processing costs.
Improve prompts, regex patterns, SQL queries, or small code snippets through repeated scoring and revision. The skill helps define measurable tests, generate new candidates with an AI model, and inspect results to find better-performing versions.
使用Fluentd的regexp插件解析MySQL慢查询日志，将其切分为时间、用户、查询时间和SQL内容四个字段，并配置字段长度限制以避免解析错误。
The English summary is being prepared. Showing the original description.
Detects PII in unstructured data including emails, documents, images, and logs using NER-based detection with spaCy and Microsoft Presidio, regex patterns, OCR integration, and confidence scoring. Keywords: PII detection, unstructured data, NER, spaCy, Presidio, OCR, regex, email scanning, document scanning.
The English summary is being prepared. Showing the original description.
Fix JavaScript regex failures when matching CJK (Chinese/Japanese/Korean) text using \b word boundaries. Use when: (1) Regex pattern with \b silently fails to match Japanese, Chinese, or Korean text, (2) Pattern works for Latin/ASCII text but not CJK, (3) hasDriverLicenceCue or similar text-detection function returns false for CJK input despite correct characters, (4) inferIssuerFromTitleText or pattern-matching functions fail on non-Latin scripts. Root cause: JavaScript \b only recognizes [a-zA-Z0-9_] as "word characters" — CJK characters are classified as \W (non-word), so \b before/after CJK always sees a non-word/non-word boundary and fails to match.
The English summary is being prepared. Showing the original description.
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
The English summary is being prepared. Showing the original description.
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
The English summary is being prepared. Showing the original description.
使用Fluentd的regexp插件解析MySQL慢查询日志，将其切分为时间、用户、查询时间和SQL内容四个字段，并配置字段长度限制以避免解析错误。
The English summary is being prepared. Showing the original description.
Helps create, explain, debug, and optimize regular expressions for finding, extracting, or replacing text. Accounts for differences between programming languages and checks matching and nonmatching examples to identify overly broad patterns and potential performance problems.
Hunting skill for sqli vulnerabilities. Built from 12 public bug bounty reports including modern NoSQL injection (Rocket.Chat CVE-2021-22911 MongoDB $regex, Mongoose ORM CVE-2024-53900 $where bypass), modern ORM raw-fragment SQLi (Django CVE-2024-42005, Sequelize GHSA-wrh9-cjv3-2hpw), second-order SOQL injection (HackerOne Salesforce), time-based blind SQLi in GraphQL resolvers, and SQLi on OIDC-proxy backends. Use when hunting SQLi on any target. Dedicated NoSQL operator injection (MongoDB/CouchDB $where/$regex/$ne) is owned by hunt-nosqli — NoSQL appears here only as adjacent ORM/WAF context.
The English summary is being prepared. Showing the original description.
在解析结构化文本时，用于在正则表达式（Regex）和大型语言模型（LLM）之间进行选择的决策框架——优先使用正则表达式，仅针对低置信度的边界情况引入 LLM。
The English summary is being prepared. Showing the original description.
Debug regex patterns with visual breakdowns, plain English explanations, test case generation, and flavor conversion. Use when user needs help with regular expressions or pattern matching.
The English summary is being prepared. Showing the original description.
In-process semantic search over text files or in-memory strings, using Gemini embeddings via the CF AI Gateway. Use when user wants fuzzy/conceptual search where exact-keyword grep would miss — "sessions discussing regulatory constraints", "code about retry logic", "notes mentioning burnout even if the word isn't there". Complements searching-codebases (regex/AST) and extracting-keywords (YAKE). Do NOT use when an exact string/regex match is what's wanted — grep/rg wins on speed and precision there.
The English summary is being prepared. Showing the original description.
Living catalogue of 7 known hazard entries (SE-01 through SE-07) specific to agent-studio: Windows backslash paths, prototype pollution, hook exit codes, async swallowing, ReDoS in glob-to-regex, DST arithmetic, array mutation during iteration. Each entry: symptom, root cause, fix, test assertion.
The English summary is being prepared. Showing the original description.
Configurable regex-based alert system for detecting patterns in tool calls and session activity. Supports error triggers, content regex matching, token threshold triggers, and pattern detection with configurable actions.
The English summary is being prepared. Showing the original description.
copy_tuner（CopyTuner / copy_tuner_client）で集中管理している i18n データを、prefix（正規表現）単位で Rails 標準の config/locales（YAML）管理へ移すスキル。gem の local_first_key_regexp を使うので、 gem を残したまま特定 prefix だけをローカル管理にできる（部分ローカル化）。1 回の実行で 1 prefix。 全 prefix を移して gem ごと撤去したい場合は繰り返し、完了後 copy-tuner-to-locales-cleanup スキルへ進む。 対象 prefix はスキル引数で指定でき、未指定なら export を俯瞰して選定する。
The English summary is being prepared. Showing the original description.
TJS2 (吉里吉里Z 内蔵スクリプト言語) の言語仕様と組み込みクラスのリファレンス。.tjs ファイル / *.ks (KAG) 内の埋め込みスクリプト / TJS2 コード断片 を扱う、書く、レビューする、デバッグするときに使う。JavaScript / TypeScript に似ているが文法と意味論が違うので、JS の感覚で書くと壊れる場合が多い。組み込みクラス (Array / Dictionary / Date / Math / RegExp / Exception) の API もここに集約。**呼び出されたら必ず「JS との主な違い」セクションを最初に確認し、その上で必要な詳細リファレンスを Read で取りに行くこと。** 吉里吉里Z 本体のクラス API (Window / Layer / System / Storages / Bitmap 等) や engine 内部はこのスキルの対象外。
The English summary is being prepared. Showing the original description.
Comprehensive regular expressions guide covering character classes, quantifiers, anchors, groups, lookahead/lookbehind, common patterns (email, URL, IP, phone, dates, semver), ReDoS prevention, Unicode support, flags, debugging, and when NOT to use regex.
The English summary is being prepared. Showing the original description.
Hunting skill for sqli vulnerabilities. Built from 12 public bug bounty reports including modern NoSQL injection (Rocket.Chat CVE-2021-22911 MongoDB $regex, Mongoose ORM CVE-2024-53900 $where bypass), modern ORM raw-fragment SQLi (Django CVE-2024-42005, Sequelize GHSA-wrh9-cjv3-2hpw), second-order SOQL injection (HackerOne Salesforce), time-based blind SQLi in GraphQL resolvers, and SQLi on OIDC-proxy backends. Use when hunting SQLi on any target. Dedicated NoSQL operator injection (MongoDB/CouchDB $where/$regex/$ne) is owned by hunt-nosqli — NoSQL appears here only as adjacent ORM/WAF context.
The English summary is being prepared. Showing the original description.
Build Bengali search and AI features with guidance on consistent character encoding, word splitting, digit conversion, and safe text display. Includes patterns for cleaning training data, storing text, and handling Bengali alongside English.
Create rules that detect command patterns, file edits, prompts, or completion events and issue warnings or block matching actions. Configure checks for dangerous commands, sensitive files, and debug code using text patterns or multiple conditions.
Generate model responses in defined formats for data extraction and classification. Use JSON schemas, Pydantic data models, regular expressions, or fixed choices to produce structured results that other programs can parse and validate.
Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.
Analyze Apache and Nginx access logs for attack attempts, scanner activity, and repeated login requests. Add geographic context to source IP addresses and produce a prioritized findings report to support intrusion investigations and monitoring reviews.