abhattacherjee

Creates detailed story specification files from various inputs (Claude plan, requirement file, prompt, GitHub issue). Discovers project spec conventions at runtime, brainstorms approaches with vertical splitting recommendations for large stories, generates template-compliant specs, checks for over-engineering, and optionally chains to spec-review. Use when: (1) user wants to write a new story spec, (2) converting a plan or requirements into a formal spec, (3) creating specs from GitHub issues, (4) breaking a large feature into shippable vertical slices.

Implements a previously created and reviewed story spec end-to-end: reads the spec, creates a feature branch, implements all sub-tasks with progress tracking, validates acceptance criteria, updates tracking files, and creates a PR. Optionally delegates to separately-installed brainstorming, frontend-design, and ui-from-requirements skills for complex UI work. Use when: (1) user says /spec-implement or 'implement this spec', (2) a story spec has been created and reviewed and is ready for implementation, (3) user provides a spec file path to implement.

Reviews and enriches story specifications with codebase-verified technical sub-tasks, architecture alignment checks, design simplification suggestions, and API test plans. Dynamically discovers project architecture at runtime. Use when: (1) a new story spec needs review before implementation, (2) a spec has high-level tasks but lacks implementation-ready detail, (3) need to verify spec assumptions against actual codebase, (4) a spec references API changes but has no test plan, (5) reviewing specs that reference data shapes or pipeline ordering, (6) spec subtasks mention add field X to object Y or call function at line N.

Creates detailed story specification files from various inputs (Claude plan, requirement file, prompt, GitHub issue). Discovers project spec conventions at runtime, brainstorms approaches with vertical splitting recommendations for large stories, generates template-compliant specs, checks for over-engineering, and optionally chains to spec-review. Use when: (1) user wants to write a new story spec, (2) converting a plan or requirements into a formal spec, (3) creating specs from GitHub issues, (4) breaking a large feature into shippable vertical slices.

Implements a previously created and reviewed story spec end-to-end: reads the spec, creates a feature branch, implements all sub-tasks with progress tracking, validates acceptance criteria, updates tracking files, and creates a PR. Optionally delegates to separately-installed brainstorming, frontend-design, and ui-from-requirements skills for complex UI work. Use when: (1) user says /spec-implement or 'implement this spec', (2) a story spec has been created and reviewed and is ready for implementation, (3) user provides a spec file path to implement.

Reviews and enriches story specifications with codebase-verified technical sub-tasks, architecture alignment checks, design simplification suggestions, and API test plans. Dynamically discovers project architecture at runtime. Use when: (1) a new story spec needs review before implementation, (2) a spec has high-level tasks but lacks implementation-ready detail, (3) need to verify spec assumptions against actual codebase, (4) a spec references API changes but has no test plan, (5) reviewing specs that reference data shapes or pipeline ordering, (6) spec subtasks mention add field X to object Y or call function at line N.

Use when the user wants a thorough, high-assurance review of code changes — phrases like "review this until it's clean", "converge to zero issues", "adversarial review", "have Gemini and Claude review", "deep review this PR", or "make this change ironclad". Runs TWO phases on a PR or working-tree diff: (1) iterative multi-reviewer review that loops fix->re-review until a round finds zero actionable issues, then (2) a multi-round Gemini-primary adversarial cross-examination (Gemini finds -> Claude judges -> Gemini counters), fixing every confirmed finding. Repeatable across any project/PR. Use when: (1) the user wants a thorough, high-assurance review that converges to zero actionable issues, (2) the user asks for an adversarial or Gemini-and-Claude cross-examination review of a code diff, (3) deep-reviewing a PR or working-tree diff before merge, (4) the user wants to make a change ironclad.

Runs a Claude↔Gemini adversarial code review on a PR diff or working-tree diff, surfacing only findings both models independently confirm (high-precision, both-confirm rule). Use when: (1) reviewing a PR or working-tree diff with adversarial rigor and you want fewer false positives, (2) you want only findings two independent AI models agree on rather than a single-model opinion, (3) replacing a lost external PR reviewer (e.g. Copilot) with a second independent model cross-examining Claude's analysis, (4) running a high-precision pre-merge review before shipping to production. Supports automatic PR mode (posts review comments) and local mode (terminal report + gitignored markdown file). Degrades loudly to Claude-only review when Gemini is unavailable.

Triage open `- [ ]` items across your Obsidian vault with evidence-grounded AI classification. Auto-closes items shipped by merged PRs, surfaces items needing external action (e.g. `gh issue close`), hides stale items by default. Replaces the old token-overlap heuristic with a two-pass AI pipeline backed by a persistence cache. Use when: (1) sweeping a project for done work, (2) auditing what's still actionable, (3) recovering from /recall deferral fatigue.

Pure read-only context resume — summarizes unsummarized notes and surfaces last-session context. Use `/check-items` to triage open items. Use when: (1) /recall command, (2) /recall <project-name>, (3) resuming work on a project and wanting prior context.

Generates honest session retrospectives analyzing what worked, what didn't, key learnings, and actionable process improvements. Use when: (1) /retro command at end of session, (2) user wants to reflect on session quality and outcomes.

Interactively saves curated insights from the current Claude Code session to the Obsidian vault. Use when: (1) /compress command to save session insights, (2) /compress <topic> to extract a specific topic, (3) user wants to capture decisions, patterns, solutions, or error fixes from the current session.

Generates daily/weekly standup summaries across all projects from the Obsidian vault. Includes a Closed This Period section listing items checked off during the window, grouped by project. Use when: (1) /standup for today's summary, (2) /standup this week for weekly summary, (3) /standup <date range> for custom range.

Surface unnamed patterns across vault themes. Use when: (1) /emerge for last 30 days, (2) /emerge 14d for custom window, (3) /emerge this week.

Batch-cluster vault notes into named themes. Use when: (1) /consolidate to seed themes from unassigned notes, (2) /consolidate stats, (3) /consolidate split <id>, (4) /consolidate merge <a> <b>, (5) /consolidate --full to wipe and recluster everything.

Diagnostic and repair skill for the Obsidian vault. Runs a battery of checks against vault notes and offers to fix detected issues. Dry-run by default — requires 'fix' to write. Use when: (1) /vault-doctor command to scan for vault health issues, (2) /vault-doctor fix to apply repairs, (3) /vault-doctor --check <name> for a specific check, (4) user reports stale backlinks or wants to audit vault integrity.

Extracts reusable knowledge from work sessions and codifies it into Claude Code skills. Use when: (1) /claudeception command to review session learnings, (2) save this as a skill or extract a skill from this, (3) what did we learn?, (4) after non-obvious debugging, workarounds, or trial-and-error discovery. Evaluates whether current work contains extractable knowledge, checks for existing skills, and creates or updates skills following the skill-authoring best practices.

Debug getServerSideProps and getStaticProps errors in Next.js. Use when: (1) Page shows generic error but browser console is empty, (2) API routes return 500 with no details, (3) Server-side code fails silently, (4) Error only occurs on refresh not client navigation. Check terminal/server logs instead of browser for actual error messages.

Fix Prisma Too many connections and connection pool exhaustion errors in serverless environments (Vercel, AWS Lambda, Netlify). Use when: (1) Error P2024 Timed out fetching a new connection from the pool, (2) PostgreSQL too many connections for role, (3) Database works locally but fails in production serverless, (4) Intermittent database timeouts under load.

Detect and resolve TypeScript/JavaScript circular import dependencies. Use when: (1) Cannot access X before initialization at runtime, (2) Import returns undefined unexpectedly, (3) ReferenceError Cannot access X before initialization, (4) Type errors that disappear when you change import order, (5) Jest/Vitest tests fail with undefined imports that work in browser.

Git Flow branching workflow reference and status diagnostic. Use when: (1) /flow-status or checking repository state, (2) creating feature/release/hotfix branches, (3) finishing and merging Git Flow branches, (4) understanding Git Flow conventions in any repository, (5) setting up or overriding Git Flow commands for a new project.

Keeps CHANGELOG.md up to date by generating categorized entries from git commit history. Use when: (1) user asks to update the changelog, (2) before committing changes that should be documented, (3) preparing a release and need changelog entries, (4) user says 'update changelog' or 'what changed since last release', (5) a commit is about to be pushed and the changelog hasn't been updated.

Creates isolated git worktrees for parallel Claude Code sessions, each on its own branch. Use when: (1) /worktree command, (2) user wants to work on multiple branches simultaneously, (3) user has multiple Claude Code sessions conflicting on the same branch, (4) user asks to set up parallel development.

Searches Claude Code conversation history in ~/.claude/projects/ by topic, date, branch, or project. Provides verbatim conversation content and AI-generated summaries. Use when: (1) user asks to find a past conversation, (2) user wants to recall what was discussed on a topic or date, (3) user asks to search conversation history, (4) /conversation-search command.