claude-code-skills

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.

Publishes Claude Code skills as installable plugins and syncs them to a GitHub monorepo. Plugin-first: every skill with a plugin-manifest.json is auto-assembled and synced as a plugin. Also supports bare skill publishing and individual repos. Use when: (1) user says 'publish', 'share', or 'sync' a skill, (2) a skill needs to be made installable by others, (3) syncing skills/plugins to the monorepo, (4) creating a versioned monorepo release, (5) assembling a plugin from skills + commands, (6) user says 'publish plugin' or 'package plugin'.

Moves a GitHub issue or PR's Project (v2) board card to a target Status column via a deterministic script (scripts/board-move.sh). Use when: (1) moving an issue to 'In Progress' when work starts, (2) moving a card to 'Development Complete'/'In Review'/'Done in develop' when its PR merges, (3) any mid-lifecycle Project v2 status change that github-release-board-promote (release->Done only) does not cover, (4) listing a board's available Status columns. Covers: projectsV2 board discovery, Status field/option lookup, updateProjectV2ItemFieldValue, fuzzy column matching, --add for items not yet on the board, project auth-scope checks.

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.

First-run configuration and upgrade for the Obsidian Brain plugin. Sets up vault path, creates folders, copies dashboard templates, configures hookify nudges, and writes config. Idempotent — safe to re-run to pick up new features without overwriting existing config or dashboards. Use when: (1) first time installing obsidian-brain, (2) changing vault path, (3) /obsidian-setup command, (4) upgrading to a new version.

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.

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.

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.

Captures architectural and technical decisions as ADR-lite notes in the Obsidian vault. Use when: (1) /decide command to record a decision from the current session, (2) /decide <decision summary> to capture a specific decision, (3) user wants to document why a particular technical choice was made.

Captures non-obvious errors and their solutions as structured Obsidian notes for future reference. Use when: (1) /error-log command to capture an error from the current session, (2) /error-log <error description> to log a specific error, (3) user wants to document a tricky bug fix or error resolution.

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

Asks questions and gets synthesized answers grounded in vault history with source citations. Use when: (1) /vault-ask <question> to reason over vault knowledge, (2) user wants to know what their notes say about a topic, (3) user wants cross-project pattern analysis.

Interactive configuration menu for obsidian-brain settings. Use when: (1) /vault-config to view and change settings, (2) user wants to toggle log_raw_messages, (3) user wants to adjust session filtering thresholds.

Rebuild the SQLite FTS5 vault index. Non-destructive by default — preserves Friston activation data (access_log, themes, theme_members); only regenerates derivable tables. Opt into `--full` for a complete wipe.

Searches the Obsidian vault by keyword, tag, or structured query across session and insight notes. Use when: (1) /vault-search command, (2) user asks to find past notes, decisions, or error fixes, (3) user wants to recall something from their vault.

Vault health diagnostics and usage analytics — signal coverage, access patterns, importance distribution, top accessed notes. Saves report to vault for trend tracking. Use when: (1) /vault-stats command, (2) user wants to check vault health, (3) user wants to see access patterns or signal effectiveness.

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.

Backfills the Obsidian vault with historical Claude Code sessions using conversation search and parallel sub-agents. Use when: (1) /vault-import command to import recent sessions, (2) /vault-import 30d to import last 30 days, (3) /vault-import project:api-service 30d to filter by project, (4) user wants to populate vault with past session history.

Cross-references related Obsidian vault notes with bidirectional wikilinks. Use when: (1) /link to auto-suggest connections for the current session, (2) /link <description> to link specific notes, (3) user wants to connect related notes.

Install dev version of obsidian-brain into the plugin cache for local testing, or restore the original. Use when: (1) /dev-test install to test unreleased changes, (2) /dev-test restore to put back the original, (3) /dev-test to check current status.

Creates and optimizes Claude Code skills following Anthropic's official best practices with emphasis on agent parallelization and script-first determinism. Use when: (1) creating a new skill from scratch, (2) optimizing an existing skill that exceeds 500 lines or has poor discoverability, (3) extracting inline code into scripts/ or reference material into references/, (4) designing orchestrator + sub-agent architectures for complex skills, (5) restructuring a skill directory into SKILL.md + scripts/ + references/ layout, (6) auditing skill cross-references for stale links. Covers: agent-first orchestration, parallel sub-agent design, script-first determinism, frontmatter rules, progressive disclosure, directory layout, description writing, and quality checklist.

Creates and optimizes Claude Code skills following Anthropic's official best practices with emphasis on agent parallelization and script-first determinism. Use when: (1) creating a new skill from scratch, (2) optimizing an existing skill that exceeds 500 lines or has poor discoverability, (3) extracting inline code into scripts/ or reference material into references/, (4) designing orchestrator + sub-agent architectures for complex skills, (5) restructuring a skill directory into SKILL.md + scripts/ + references/ layout, (6) auditing skill cross-references for stale links. Covers: agent-first orchestration, parallel sub-agent design, script-first determinism, frontmatter rules, progressive disclosure, directory layout, description writing, and quality checklist.

Interactive Figma UI design skill with UX-expert brainstorming, progress tracking, and design-to-code bridging. Spawns a specialized UX designer agent that researches real-world references before proposing design directions. Four workflows: (A) capture running app, (B) new project design, (C) enhancement mockup, (D) extract existing Figma designs as input for specs/plans/code. Use when: (1) user asks for Figma mockups or UI designs, (2) user shares a Figma URL to use as input for a spec or plan, (3) starting a new project and needs Figma designs, (4) mocking up a feature enhancement, (5) user wants to translate a Figma design into implementation requirements.

Interactive Figma UI design skill with UX-expert brainstorming, progress tracking, and design-to-code bridging. Spawns a specialized UX designer agent that researches real-world references before proposing design directions. Four workflows: (A) capture running app, (B) new project design, (C) enhancement mockup, (D) extract existing Figma designs as input for specs/plans/code. Use when: (1) user asks for Figma mockups or UI designs, (2) user shares a Figma URL to use as input for a spec or plan, (3) starting a new project and needs Figma designs, (4) mocking up a feature enhancement, (5) user wants to translate a Figma design into implementation requirements.

AI-driven screen recording and demo production pipeline for macOS. Records screen + cursor + window bounds, then uses AI vision to analyze the recording, create a zoom script targeting specific UI elements, generate voiceover narration, and produce a polished demo video. Use when: (1) creating product demo videos, (2) recording and polishing UI walkthroughs, (3) turning raw screen recordings into narrated presentations, (4) re-processing existing recordings with different zoom/voiceover.

Creates polished, narrated product demo videos using Remotion (React) with AI-crafted storytelling (Opus 4.6), real app screenshots, animated phone mockups, brand-aligned styling, and TTS voiceover (OpenAI or macOS). Use when: (1) user asks to create a product video or demo reel, (2) user wants an Instagram Reel or YouTube video showcasing their app, (3) user has a running web app and wants animated marketing content, (4) user provides brand guidelines to apply to a video project.

Install a custom 4-tier adaptive statusline with icons for folder, git branch, and context usage

Creates and customizes Claude Code statusline scripts from composable items. Use when: (1) user wants to add or change their statusline, (2) user asks to show cost, git, context, or other info in the status bar, (3) user says 'customize my statusline' or 'add X to my statusline', (4) user wants to create a statusline from scratch, (5) debugging statusline display issues.

Show a single-line context usage progress bar with color-coded statusline

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.

Prevents context window overflow when processing large content (Figma designs, web pages, GitHub wikis, large codebases). Delegates token-heavy reads to isolated sub-agents that return distilled summaries. Auto-detects when ralph-loop is needed based on batch count. Use when: (1) reading 3+ large external sources (URLs, Figma frames, wiki pages), (2) large documentation/API reference sites decomposed into section URLs, (3) monorepo code audits across many directories, (4) dependency upgrade research across 5+ packages, (5) large PR reviews with 15+ changed files, (6) competitive feature matrix analysis, (7) security advisory triage for dependency updates.

Prevents context window overflow when processing large content (Figma designs, web pages, GitHub wikis, large codebases). Delegates token-heavy reads to isolated sub-agents that return distilled summaries. Auto-detects when ralph-loop is needed based on batch count. Use when: (1) reading 3+ large external sources (URLs, Figma frames, wiki pages), (2) large documentation/API reference sites decomposed into section URLs, (3) monorepo code audits across many directories, (4) dependency upgrade research across 5+ packages, (5) large PR reviews with 15+ changed files, (6) competitive feature matrix analysis, (7) security advisory triage for dependency updates.