Reversal — Agent Input Reliability Layer
Normalizes URLs, PDFs, Word, Excel, CSV, images, and text into clean JSON for reliable, universal input parsing in under 2 seconds.
Bootstrap the agile-workflow substrate in a project. Detects the project's current shape (workflow-plugin / ad-hoc / no-tracking / greenfield), seeds initial items from any source layout, writes the .claude/rules/agile-workflow.md navigation rules, runs the conventions interview to populate .work/CONVENTIONS.md, copies the work-view script into .work/bin/, appends the agile-workflow section to CLAUDE.md (with idempotency markers), produces MIGRATION_REPORT.md, and commits everything as a single revertible commit. Idempotent via --update for plugin upgrades. User-invocable only — substrate bootstrap is consequential and interactive.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "convert" with this command: npx skills add nklisch/skillsmp-nklisch-nklisch-convert
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Normalizes URLs, PDFs, Word, Excel, CSV, images, and text into clean JSON for reliable, universal input parsing in under 2 seconds.
Normalizes URLs, PDFs, Word, Excel, CSV, images, and text into clean JSON for reliable, universal input parsing in under 2 seconds.
投放Agent(ad.qq.com/atlas/{account_id}/agent)自动化体验测试技能。 通过Cookie注入+Playwright浏览器自动化,对投放Agent的对话功能、快捷指令、常用指令面板、自由对话、妙招功能进行完整体验测试,并生成UX体验报告。
自动分析和优化 Agent Skill 的工具 - 监控使用情况、评估健康度、生成改进建议