Pflege die Extraktion von ATS-Kriterien aus CVs; verwenden bei Anpassungen an Kontakt-, Erfahrung- oder Bildungsextraktion.
Create semantik plugins (connectors, embeddings, chunkers, rerankers, extractors, agents). Use when developing plugins, creating new integrations, or asking about plugin patterns, protocols, or testing.
Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
Use when user says "/release-prep", "prepare release", "release readiness", or needs to verify a milestone is ready for release.
agent-browser CLI の仕様と使い方に関する知識を提供。ヘッドレスブラウザ自動化、スナップショット、セレクター、セッション管理、ネットワーク制御について回答。Use when user asks about agent-browser, browser automation, snapshots, selectors, sessions, or web scraping. Also use when user says agent-browser について, ブラウザ自動化, スナップショット, セレクター, セッション管理.
Handle vulnerability reports with coordinated disclosure, timely patches, and clear communication.
Analyze disk space and find cleanable files. Use when user wants to clean disk, free up space, find large files, analyze disk usage, or asks about what's taking up space. Triggers on requests like "clean my disk", "free up space on C:", "find large files", "what's using my disk space", "disk cleanup".
Pflege das regelbasierte CV<->JD Matching inkl. Explainability; verwenden bei Anpassung der Scoring-Logik, Gewichtung oder Match-Outputs.
Human code review gate for critical components. Activates automatically for security-sensitive paths, high-complexity code, or large changes. Activation trigger: [ACTIVATE:CODE_REVIEW_GATE_V1]
Ensure protocol facts derived from MIDI spec PDFs are reflected in canonical JSON schema/OpenAPI sources.
Generates FPF-compliant Agent Skills from the FPF Specification (Strict E.8 format).
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
Ask the user to pick a response style and persist the preference.
Write documentation following Metabase's conversational, clear, and user-focused style. Use when creating or editing documentation files (markdown, MDX, etc.).
Thorough, adversarial security review of API endpoints, UI flows that call those endpoints, and any database-interacting code. Use when the user asks for a security review, permission/authorization audit, red-team style assessment, or vulnerability analysis. Assume access to source code and a running system; perform threat modeling and check current vulnerabilities relevant to the stack.
Concurrency with Effect.all, forEach concurrency, Fiber lifecycle, race and timeouts. Use for parallelizing tasks safely.
Pflege das Parsing von Job Descriptions (JD); verwenden bei neuen Feldern, Headern oder Parsing-Regeln.
Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.
Requests approval for a constrained action or change.
Edit PDFs with natural-language instructions using the nano-pdf CLI.