[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:pro-workflow":3},"\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Frohitg00\u002Fpro-workflow\u002FHEAD\u002Fassets\u002Fbanner.svg\" alt=\"Pro Workflow\" width=\"100%\" \u002F>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frohitg00\u002Fpro-workflow\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Frohitg00\u002Fpro-workflow?style=for-the-badge&logo=github&color=D97757&labelColor=1e1e2e\" alt=\"Stars\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fpro-workflow\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Fpro-workflow?style=for-the-badge&logo=npm&color=E8926F&labelColor=1e1e2e\" alt=\"npm\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frohitg00\u002Fpro-workflow\u002Fblob\u002Fmain\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-22c55e?style=for-the-badge&labelColor=1e1e2e\" alt=\"License\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fagenstskills.com\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSkillKit-32%2B%20agents-f59e0b?style=for-the-badge&labelColor=1e1e2e\" alt=\"SkillKit\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Frohitg00-pro-workflow.mintlify.app\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocs-Mintlify-0D9373?style=for-the-badge&logo=mintlify&labelColor=1e1e2e\" alt=\"Docs\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Ch3>Your Claude Code gets smarter every session.\u003C\u002Fh3>\u003Cp align=\"center\">\n  Self-correcting memory + persistent FTS5-indexed wikis + auto-research loop, all on one SQLite store.\u003Cbr \u002F>\n  Correct Claude once — it never repeats the mistake. Build a wiki on a topic — it grows itself overnight.\u003Cbr \u002F>\n  \u003Cb>34 skills\u003C\u002Fb> • \u003Cb>8 agents\u003C\u002Fb> • \u003Cb>22 commands\u003C\u002Fb> • \u003Cb>37 hook scripts across 24 events\u003C\u002Fb>\u003Cbr \u002F>\n  Works with \u003Cb>Claude Code\u003C\u002Fb>, \u003Cb>Cursor\u003C\u002Fb>, and \u003Cb>32+ agents\u003C\u002Fb> via SkillKit.\n\u003C\u002Fp>\u003Chr \u002F>\n\u003Ch2>The Problem\u003C\u002Fh2>\n\u003Cp>You correct Claude the same way 50 times. You explain conventions every new session. Context compacts, learnings vanish, mistakes repeat. You research the same topic in three different sessions because there is nowhere durable for the answers to land.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>Every Claude Code user hits this wall.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Ch2>The Solution\u003C\u002Fh2>\n\u003Cp>Pro Workflow puts a single SQLite store underneath every session.\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Self-correction memory\u003C\u002Fstrong> — every correction becomes a rule, FTS5-searchable, auto-loaded on session start.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Knowledge plane\u003C\u002Fstrong> — persistent research wikis on disk + FTS5 shadow index, queryable from any session, optionally grown by an auto-research loop.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Quality gates\u003C\u002Fstrong> — LLM-powered hooks, deterministic git\u002Fsecret guards, compaction-aware state, cost tracking.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>After 50 sessions you barely correct anything. After a week of auto-research, your wiki on a topic is denser than the curated lists you started from.\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Frohitg00\u002Fpro-workflow\u002FHEAD\u002Fassets\u002Fself-correction-demo.svg\" alt=\"Self-Correction Loop\" width=\"700\" \u002F>\n\u003C\u002Fp>\u003Cpre>\u003Ccode>Session 1:  You → \"Don't mock the database in tests\"\n            Claude → Proposes rule → You approve → Saved to SQLite\n\nSession 2:  SessionStart loads all learnings + lists your wikis\n            UserPromptSubmit auto-injects top wiki hits when relevant\n            Claude writes integration tests, cites the right wiki page\n\nSession 50: Correction rate near zero. Wiki has 200 cited claims.\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Chr \u002F>\n\u003Ch2>Install\u003C\u002Fh2>\n\u003Cp>Pro Workflow is published in two places: the Claude Code plugin marketplace (native), and SkillKit (cross-agent translator). Other agents do not have first-class plugins yet — SkillKit translates the skill bundle into each agent's native skill format.\u003C\u002Fp>\n\u003Ch3>Claude Code (native)\u003C\u002Fh3>\n\u003Cpre>\u003Ccode class=\"language-bash\">\u002Fplugin marketplace add rohitg00\u002Fpro-workflow\n\u002Fplugin install pro-workflow@pro-workflow\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch3>Cursor, Codex, Copilot CLI, Droid, Gemini CLI, OpenCode, and 26 more (via SkillKit)\u003C\u002Fh3>\n\u003Cp>SkillKit translates the 34 skills + 22 commands into each agent's native skill format and drops them in the right config directory.\u003C\u002Fp>\n\u003Cpre>\u003Ccode class=\"language-bash\">npx skillkit install rohitg00\u002Fpro-workflow --agent <name> --force\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Notes:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>Use \u003Ccode>rohitg00\u002Fpro-workflow\u003C\u002Fcode> (the GitHub form), not the bare name — \u003Ccode>skillkit install\u003C\u002Fcode> resolves providers from \u003Ccode>owner\u002Frepo\u003C\u002Fcode>, not marketplace slugs.\u003C\u002Fli>\n\u003Cli>\u003Ccode>--force\u003C\u002Fcode> is currently required: SkillKit's security scanner has open false positives\u003C\u002Fli>\n\u003C\u002Ful>\n",1784240407919]