adelaidasofia
UserThe operating system for Claude Code. Memory, accountability, journaling, knowledge graphs, pattern recognition — one install, every session compounds.
Categories
Indexed Skills (46)
resolver-query
Read Meta/RESOLVER.md, parse rules and statuses, and answer a natural-language question by surfacing the matching rule(s). Trigger /resolver-query <natural-language-question>. Use when an operator wants to look up which rule applies to a query without reading the full RESOLVER.md by hand. Do NOT use for writing rules (that is synth-pr-to-sop or synth-thread-to-sop) or for rebuilding RESOLVER.md (that is resolver-build.py).
secret-warn
Real-time edit-time guardrails that catch API keys, code injection patterns, and unsafe pipe-to-shell installs the moment they're typed in the Claude Code tool-call loop — before commit, before CI, before any second-pass review. Ships a PreToolUse + PostToolUse hook, a Bash-tool guard, and a curated 11-rule regex catalog covering the most common secret shapes (AWS, Stripe, GCP, OpenAI, Anthropic, GitHub, Slack, JWT, PEM, generic high-entropy assignment) plus three injection-pattern classes. Use when the user mentions secret detection, gitleaks-equivalent during edit time, pre-commit secret scanning, API key safety, edit-time guards, security hooks in Claude Code, or wants real-time protection against unsafe MCP server installs. Do NOT use for full security audits (different scope), penetration testing, or DLP across non-Claude-Code surfaces.
security-snapshot
Generate a client-ready security hygiene snapshot for a prospect domain. Free lead magnet for consulting practices. Outputs a markdown report covering SSL/TLS grade, HTTP security headers, email authentication (SPF/DMARC), and server fingerprint leaks. Use when the user says /security-snapshot, /snapshot [domain], "run a security check on X", or "generate a security report for [company]". Do NOT use for penetration testing, internal infrastructure audits, or application-layer vulnerability assessment. This is a passive, unauthenticated scan for conversation-starter value, not a full audit.
setup-vault-types
Interactive wizard to configure which document types your vault uses. Asks the user what kinds of notes they take (journals, books, meetings, clients, podcasts, etc.), enables the matching extractors, and scaffolds extractors for custom types. Run once after installing ai-brain-starter, and again whenever you add a new kind of doc. Do NOT use this to run extraction. Use /second-brain-mapping for that.
synth-pr-to-sop
Read a merged-PR markdown export and synthesize a typed workflow SOP into Meta/Workflows/. Trigger /synth-pr-to-sop <pr-markdown-file-or-folder>. Use when a closed PR captures a repeatable process worth filing as a procedural memory entry. Do NOT use for in-session synthesis (that runs through session-close cascade) or for non-PR sources (use /synth-thread-to-sop for Slack threads).
diagnose
Run a self-check against an installed AI Brain Starter vault. Verifies CLAUDE.md, Meta folder, skills, hooks, journal index, MCPs, .ps1 BOM/em-dash hazards, and ai-brain-starter freshness. Prints a green/yellow/red report. Run any time something feels off, or after a git pull, or when onboarding someone else's vault.
dev-repo-checkpoints
Auto-stash uncommitted work in code repos on every Claude Code Stop/SubagentStop event, so 60+ exchange sessions can't lose work to a branch switch. Stop hook scoped to ~/dev/* repos (vault is covered by its own snapshot script). Recoverable via `git stash list | grep claude-checkpoint`.
dev-repo-worktrees
Per-session git worktree pattern for ~/dev/<repo> code repos. Prevents the CONCURRENT-SESSION-HEAD-DRIFT bug class where two Claude Code sessions writing to the same physical checkout collide on the single .git/HEAD pointer + index + working tree. Ships a wrapper script + hookify warn rule + the rule prose. Complements dev-repo-checkpoints (recovery) by preventing the failure at the structural layer (isolation).
evolve
Cluster hardened instincts (high-confidence feedback_*/discovery_* memories) into a proposed higher-level structure — a Command, Skill, or Agent. Run when many related instincts have accumulated in one domain. Part of the Instinct Engine. Do NOT use for one-off pattern capture (use /patterns) or daily journaling.
for-my-team
Walk a user through what changes when they take ai-brain-starter from a personal vault to a team vault. Reads the for-teams/ folder aloud in conversation, asks three diagnostic questions, and closes with the path to having it built for them. Trigger when the user asks any variant of "how do I add my team to this," "optimize this for my company," "what does the team version look like," or anything else that signals they want the multi-person version of the brain.
frontend-taste
Anti-slop tactical layer for React / Next.js / Tailwind / Framer Motion frontend work. Pairs with the impeccable skill (strategic layer / register laws). Use when building or auditing UI, working on hero sections, landing pages, dashboards, components, or any frontend surface that an AI agent is generating. Carries the Dial System, the Frequency Gate, the Jane-Doe anti-slop content rules, hero discipline, Bento 2.0 motion-engine archetypes, Double-Bezel nested architecture, image-first workflow, shadow + surface recipes, a ~50-item redesign audit checklist, minimalist warm-monochrome variant, stack-specific gotchas, and anti-truncation output discipline.
graphify
any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report. Do NOT use for simple file reads, vault edits, or searching existing graph data (use /graphify query for lookups on an existing graph).
influencer-pack
Pre-configured creator-economy vertical pack for the ai-brain-starter substrate. Ships typed-memory categories for audience, DMs, content, collabs, and creator revenue; connector configs for Instagram, TikTok, YouTube, Substack, X, LinkedIn, Stan Store, Stripe, Patreon; retention defaults aligned with Meta + TikTok + YouTube data-handling expectations; the idea engine, an evidence-grounded content-idea generator that learns the creator's taste from every discard; decision-audit patterns for sponsored-disclosure and evidence-grounding. Use when onboarding a creator, personal-brand operator, or content-engine team that needs the substrate to come pre-shaped to the work rather than starting from a blank vault.
longitudinal
Multi-year health-mcp pattern surface. Scans years of HealthKit + journal data, returns ONLY the strongest correlations (Briden noise filter). Use when the user asks for "patterns in my health data," "what does my body tell me," "correlations between mood and HRV," "Floor x body fingerprint," or runs /longitudinal. Do NOT use for single-day analysis (use /health-doctor), this-week patterns (use /weekly), or pattern extraction across journals only (use /patterns).
note-todos
Extract action items from any non-meeting note (class notes, book notes, podcast notes, transcripts, panel writeups) and route them to the scope-correct to-do file with wikilinking and per-task owner tags. Generalization of meeting-todos. Trigger with /note-todos [filename-or-pattern]. For meetings, prefer /meeting-todos which carries the full meeting workflow cascade.
remotion-best-practices
Best practices for Remotion - Video creation in React
repurpose-talk
Turn a speaking engagement into 10-30 pieces of content (LinkedIn posts, Substack notes, video clips plan)
second-brain-mapping
Unified vault-mapping pipeline. Extracts structured metadata from every typed file in your vault (books, meetings, people, articles, goals, etc.), optionally runs knowledge-graph extraction, applies wikilinks, and surfaces cross-type insights you can't see from any single file. Zero LLM cost per run for metadata + insights. Use whenever you want to "map your second brain", refresh your vault's queryable index, or discover cross-doc patterns.
deconstruct
First-principles analyst. Surfaces hidden assumptions, finds foundational truths, rebuilds from scratch, identifies the high-leverage move.
insights
Weekly and monthly journal insights -- pattern recognition, floor trends, life coach pushback, therapist observations, and advisory panel thoughts. Use /weekly for the current calendar week, /monthly for the current calendar month. Do NOT use for daily journal entries (use daily-journal), cross-session pattern extraction (use patterns), or operational reviews.
meeting-todos
Extract action items from a meeting note and add them to the to-do list. Separates your tasks from others' tasks. Use when the user says /meeting-todos, "the meeting is done", "I just had a meeting", or otherwise wants action items pulled from a recent meeting note. Do NOT use for general task management, journaling, or pulling full meeting transcripts (use the meeting workflow for that).
patterns
Instinct Engine — scans recent sessions, journals, and decisions for recurring patterns and turns them into concrete captures (CLAUDE.md rules, concept notes, writing seeds, skill improvements). Run after a weekly review or whenever you sense a pattern hardening. Also runs semi-autonomously via session-end auto-detection triggers. Do NOT use for weekly/monthly journal reviews, daily journaling, or one-off decisions.
instinct-export
Export this project's instinct library (confidence-weighted feedback_*/discovery_* memories) to a portable YAML pack that another harness or teammate can import. Part of the Instinct Engine. Use to share or back up a curated instinct set. Do NOT use to read existing memories (that is /patterns).
instinct-import
Import a portable YAML instinct pack into this vault with confidence-gated merge — a higher-confidence import updates the local instinct, an equal-or-lower one is skipped, and a brand-new one lands in inherited/. Part of the Instinct Engine. Do NOT use to author memories by hand (just write the file).
setup-brain
Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.
backfill-journal-body-context
Walks every daily journal entry in a date range (default this year) and appends a "Body track" section BELOW the original verbatim content. Pulls health-mcp data for each date (HRV, RHR, sleep, cycle phase, lab status, recovery/sleep/strain scores) and weaves a Floor-paired interpretation. Idempotent (skips entries that already have the section). Use when user says /backfill-journal-body-context, asks to enrich journals with body data, says "backfill my journals with health" or wants existing journal entries paired with their Apple Health / Oura / Fitbit data retroactively.
coach
Longevity + fitness coach. Issues a daily workout prescription that reads from health-mcp (recovery, sleep, cycle phase, somatic state, lab status) and pairs with today's Floor (emotional state) from journal frontmatter. Tracks progressive overload per-lift. Programs deload every 4th week. Drops weekly plan into Google Calendar. Use when user says /coach, /coach today, /coach week, /coach profile, /coach log, asks "what should I do today", asks for a workout, asks for a longevity plan, or asks how to train. Pairs with health-context (already auto-fires) and insights (already body-track wired). The substrate's longevity-coach surface.
coaching
Multi-pass coaching session for processing a hard conversation, decision, or accumulated tension that won't fit in a daily journal. Runs panel passes with corrections, surfaces patterns to track over time, files a synthesized accountability record, and updates the rolling Panel Feedback Log. Use when the user wants honest panel feedback on a specific event (a difficult call, a decision they're second-guessing, accumulated friction with a person), wants to track whether they're growing on a specific theme over weeks/months, or wants the panel to run multiple passes with their corrections instead of one shot. Do NOT use for daily journal entries (use /journal), weekly/monthly reviews (use /weekly or /monthly), one-off panel reactions inside a journal (those run inline in /journal), or pattern detection across many sessions (use /patterns).
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.
health-context
Auto-fires when the daily-journal, coaching, advisory-panel, patterns, or insights skills run. Pulls health context (HRV, sleep, recovery) from the health-mcp DuckDB and folds it into the active skill's prompt. Use when user invokes /journal, /coaching, /panel, /patterns, /weekly, /monthly, or any skill that benefits from biometric context. Read-only with respect to the vault. Skip silently if health-mcp is not registered or has no data.
health-doctor
Observability surface for the health-mcp auto-trigger chain. Shows freshness of every data source (Apple Health, Oura, Fitbit, labs), last coach prescription + completion, missed-day count, lab status flags, and which auto-trigger hooks are installed. Use when user says /health doctor, /health status, asks "is the auto-chain working", "when was the last sync", "did the coach prescribe today", or wants to debug why a prescription didn't appear in calendar.
health-setup
Interactive setup wizard for the health-mcp connector. Picks the right wearable (Apple Watch / Apple Health, Oura Ring, Fitbit, Garmin, Whoop) and OS (macOS / Windows / Linux), walks the user through getting API tokens or exporting data, sets env vars, and verifies the connection end-to-end. Use when the user says /health-setup, asks to set up their wearable, asks "which wearable", asks how to import Oura or Fitbit, or after a fresh install of health-mcp.
interview-me
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.
modern-python-substrate
Modern Python toolchain substrate. uv for installs and venvs, ruff for lint and format, ty for typecheck, pytest for tests, hypothesis for property-based tests, src/ layout, pyproject.toml as single source of truth, pre-commit hooks. Plus LLM-stack patterns when the codebase calls anthropic, openai, tiktoken, or similar SDKs (prompt caching, retries, streaming, token counting). Use when the user says /python-setup, "set up Python project", "modern Python toolchain", "switch from poetry to uv", "ruff config", "ty migration from mypy", "configure pytest", or starts a new Python codebase. Covers Python 3.11+ idioms.
nano-banana
Generate, edit, and compose images using Google's Gemini 3 Pro Image model (Nano Banana Pro). Use this skill when the user asks to create images, generate visuals, edit photos, compose multiple images, create logos, thumbnails, infographics, product shots, or any image generation task. Supports text-to-image, image editing, multi-image composition (up to 14 images), iterative refinement, aspect ratio control, and Google Search-grounded image generation for real-time data visualization. Do NOT use for non-image tasks, text generation, or design feedback (use Canva MCP for template designs, design:design-critique for feedback).
rise
Use when the user says /rise, "good morning", "let's start the day", or wants their morning consciousness routine. Identifies the Floor from natural-language check-in (does NOT ask the user to name a floor), runs body movement scaled to cycle phase or feeling, recommends top 1-3 priorities from configured to-do files, derives a daily intention. Pairs with /journal at night for accountability. Do NOT use for evening reflection (use /journal), pattern detection (use /patterns), or workout prescription (use /coach for the full session — /rise only handles the post-wake body wake-up flow).
seo-substrate
SEO + GEO substrate for solo founders and indie creators. Covers technical SEO, on-page optimization, schema markup, AI-search-optimization (GEO), Google Search Console + GA4 wiring, bilingual routing (hreflang), and per-post Substack optimization. Use when the user says /seo-audit, /seo-fix, /geo-audit, /substack-seo, or asks to audit, fix, or optimize SEO on a single page, blog post, or whole site. Scoped for two-site stacks (consulting site + creator/Substack), not enterprise e-commerce or programmatic SEO.
source-driven-development
Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.
sunday-review
Weekly meta-review that orchestrates /weekly + /patterns + vault-hygiene + claude-md-drift + decision-retrospective in one flow. Use when the user wants a comprehensive Sunday wrap-up of the week, or says /sunday, /sunday-review, or "let's do the weekly review."
daily-journal
Daily journal interview and entry creator. Use this when the user wants to journal, do a daily check-in, or says /journal. Interviews the user conversationally, identifies their High-Rise floor, and saves the entry as an Obsidian note. Do NOT use for meeting notes (use meeting-todos), weekly/monthly reviews (use insights), or pattern analysis (use patterns).
performance
Use this skill when the user says /performance, /digest, asks for a weekly Claude performance report, or wants to review how their Claude Code sessions have been going. Reads JSONL session files from ~/.claude/projects/, computes six effectiveness metrics (activity distribution, one-shot edit rate, subagent turn count, model mix, project allocation, hookify firings), fires diagnostic rules when thresholds breach, and writes behavioral rules into ~/.claude/CLAUDE.md so future sessions adapt. Closes the measurement loop for self-improving AI workflows.
insights
Use this skill when the user says /weekly, /monthly, asks for a weekly review, monthly review, or wants to analyze patterns across their journal entries. Reads journal files from the configured vault path, identifies floor trends using the 34-level High-Rise scale, surfaces life coach and therapist observations, runs an advisory panel, and saves a structured report. Companion to claude-daily-journal.
meeting-todos
Extract action items from a meeting note and add them to the to-do list. Separates your tasks from others' tasks. Trigger /meeting-todos. Do NOT use for general task management or pulling full meeting transcripts.
deconstruct
First-principles analyst. Surfaces hidden assumptions, finds foundational truths, rebuilds from scratch, identifies the high-leverage move.
patterns
Instinct Engine — scans recent sessions, journals, and decisions for recurring patterns and turns them into concrete captures (CLAUDE.md rules, concept notes, writing seeds, skill improvements). Run after a weekly review or whenever you sense a pattern hardening. Also runs semi-autonomously via session-end auto-detection triggers. Do NOT use for weekly/monthly journal reviews, daily journaling, or one-off decisions.
daily-journal
Use this skill when the user wants to journal, do a daily check-in, process their day, or says /journal. Interviews the user conversationally, identifies their emotional floor using the High-Rise framework, optionally runs behavior accountability and advisory panel commentary, and saves a structured Obsidian markdown entry. Do NOT use for meeting notes, weekly/monthly reviews, or pattern analysis across multiple entries.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.