Productivity & Automation for Claude Code

Profiles applications, identifies bottlenecks (DB, I/O, memory, CPU), and produces optimization recommendations with benchmarked metrics. Use when an app is slow, traffic is scaling, or you need a pre-release performance baseline. Trigger with \"profile this service\", \"find performance bottlenecks\".

Designs and implements Python CLI tools using Click, Typer, or argparse — covering argument parsing, output formatting, exit codes, shell completion, and PyPI packaging. Use when building or improving a command-line application in Python. Trigger with \"build a Python CLI tool\", \"improve this CLI UX\".

Systematically scans a project for issues, applies safe non-breaking quick fixes (typos, whitespace, unused imports), and generates a prioritized improvement report with HTML output. Use when starting on a codebase after time away or running a mid-session health check. Trigger with \"scout this project\", \"scan for quick wins\".

Harvests reusable code patterns from projects into a categorized snippet library, deduplicates existing entries, and updates the searchable JSON index and HTML GUI. Use when completing an integration or noticing duplicate patterns across projects. Trigger with \"harvest snippets from this project\", \"organize the snippet library\".

Logs work accomplishments by analyzing git commits and agent reports, then regenerates the HTML status dashboard and JSON data file with cross-project activity tracking. Use when ending a work session or checking recent progress across projects. Trigger with \"log today's work\", \"update the status dashboard\".

Reference guide for the complete geepers agent suite — maps every agent to its purpose and generates an HTML index. Use when unsure which agent to use or to regenerate documentation. Trigger with "which geepers agent", "show me all agents".

Design and document Make.com (Integromat) visual automation scenarios with modules, routers, error handling, and cost estimates. Use when building or architecting a Make.com integration workflow. Trigger with "design a Make scenario", "build a Make workflow".

Use this agent when the user requests an action that should trigger 'documentation' behavior. This agent is usually triggered by the obsidian-project-documentation skill.

Maintains rolling 90-day analytics baselines, learned seasonal patterns, and anomaly history so specialist agents never start cold. Use when reading prior context before a report or writing updated baselines after one. Trigger with \"load analytics context\", \"update analytics baselines\".

Recommends the right LLM model for any task by weighing quality, latency, cost, and context-window requirements across OpenAI, Anthropic, Google, and open-source options. Use when choosing a model for a new feature or reducing spend without sacrificing quality. Trigger with "which model should I use", "pick the best LLM for this".

Use when designing or reviewing how elements move — animations, transitions, scroll-driven effects, gestures, and micro-interactions — the motion specialist that picks the right animation library, holds a 60fps compositor-only budget, applies physics-based springs, respects the design system's motion language, degrades under prefers-reduced-motion, and researches current motion best practices when stuck. Verifies against the ui and performance persona standards.

Coordinates multi-agent systems by decomposing tasks, routing to the right specialist, managing handoffs with full context, and aggregating outputs into a cohesive result. Use when a complex request spans multiple domains and needs intelligent agent routing. Trigger with \"orchestrate this task\", \"route to the right agent\".

Design n8n automation workflows with node configs, JavaScript code nodes, error handling, and full importable JSON exports. Use when building complex automations or self-hosted integrations. Trigger with "design an n8n workflow", "build an n8n automation".

Designs developer onboarding experiences that get engineers to their first successful API call in under 5 minutes — quickstarts, TTFC audits, and friction analysis. Use when launching a new API, improving signup-to-activation drop-off, or auditing the current quickstart. Trigger with \"improve our developer onboarding\", \"write the quickstart\".

Recommend likely bug owners using strict 6-level routing precedence with staleness detection and override memory. Use when routing clustered bugs to teams after evidence gathering.

Triages CVEs using CVSS + EPSS + CISA KEV, designs patch SLA programs with asset-criticality tiers, and audits existing vuln management programs. Use when prioritizing a backlog of CVEs, designing a patching cadence, or finding SLA gaps. Trigger with \"triage our CVEs\", \"design a vulnerability management program\".

Builds golden paths, service catalogs, internal CLIs, scaffolding, and local dev environments that measurably improve DORA metrics for the current team. Use when onboarding takes more than a day, dev environments are snowflakes, or releases require tribal knowledge. Trigger with \"friction audit my developer experience\", \"build the golden path\".

Designs and executes load, stress, spike, and soak test scripts (k6, Locust, JMeter, Artillery) then analyzes P50/P95/P99 response times, throughput, and resource utilization to identify bottlenecks and produce actionable recommendations. Use when validating scalability before launch or diagnosing latency regressions. Trigger with \"run load test\", \"benchmark API performance\".

Phase 2 of the BigQuery schema optimization pipeline — reads the phase 1 report and schema exports to identify fields with >90% null rates, detect never-queried columns, and produce ranked removal and archival recommendations as a markdown report plus strict JSON for phase 3. Use after phase 1 completes to prioritize which fields to drop or archive. Trigger with \"run schema phase 2\", \"analyze field utilization\".

Designs phishing simulation programs, security awareness curricula, and social engineering assessments that drive behavior change through immediate feedback and difficulty progression. Use when building or auditing a security awareness program or measuring click/report rates. Trigger with \"design a phishing simulation\", \"build our security awareness program\".

Designs, patterns, and debugs LLM prompts using CoT, few-shot, zero-shot, and meta-prompting techniques, with structured templates and token-efficiency guidance. Use when authoring a new prompt or diagnosing why an existing one produces poor output. Trigger with "design a prompt", "help me write a prompt".

Reduces LLM API costs 50-90% by compressing prompts, selecting the right model tier, and applying caching and batching strategies with measurable ROI calculations. Use when an LLM workflow is too expensive or slow and you need data-driven optimization. Trigger with "optimize this prompt", "reduce my LLM costs".

Builds log pipelines and SIEM detection rules — SIGMA format, MITRE mapping, retention policies, and alert tuning to keep volume within analyst capacity. Use when designing detection coverage or reducing alert fatigue. Trigger with \"write a SIEM detection rule\", \"audit my log pipeline\".

Identifies and removes AI-generated comment noise — restating comments, obvious JSDoc, filler section markers, and preamble boilerplate — while preserving every comment that explains why, documents a workaround, or captures business logic. Use when a codebase has been heavily AI-assisted and comment quality has degraded. Trigger with \"remove slop comments\", \"clean up AI-generated comments\".

Coordinates Sugar's autonomous development workflows with strategic oversight

Diagnoses growth constraints and produces retention plans, PLG architectures, activation playbooks, and referral loop designs. Use when a growth lever needs to be identified and a specific artifact built, not a list of options generated. Trigger with \"diagnose our growth constraint\", \"design a PLG activation flow\".

Diagnoses growth constraints and designs compounding growth loops — retention before acquisition, PLG architecture, activation sequencing, and experiment design with kill conditions. Use when diagnosing why growth is stalling or designing a PLG motion. Trigger with \"diagnose my retention problem\", \"design a growth experiment\".

Strategic task planning and breakdown specialist for complex development work

Optimizes LLM context windows through token budgeting, chunking strategy, and truncation design. Use when you need to control token spend, design a chunking pipeline, or audit token usage in a production AI system. Trigger with \"design my token budget\", \"fix my context overflow\".

Format triage results for terminal display and parse review commands. Use when presenting clustered bug results to the user after routing and severity computation.

Diagnoses Unity Catalog's two-level access model for a specific user + error — walks account-admin/metastore-admin status, group memberships (incl. nested-group caveats), object grants, and the external-location/storage-credential chain — and returns the exact missing membership + grant + who must run it. Use when a user hits PERMISSION_DENIED or AccessDenied after a UC migration. Trigger with "why can't this user access", "trace uc permission", "unity catalog access denied".

User-facing progress translator that reads .vibe/status.json and renders structured, jargon-free summaries of what changed, what was verified, what's next, and any required user actions — with a dedicated error mode for failures. Use when technical progress needs to be communicated in plain language or when checking vibe-guide session status. Trigger with \"vibe status\", \"/vibe-guide:status\".

Delivers single-concept micro-explanations using everyday analogies when learning mode is active. Use when a learner wants to understand one technical concept at a time in plain language. Trigger with "explain this", "what is that".

Executes vibe-guide sessions one atomic step at a time, updating .vibe/status.json and changelog after every action. Use when running or continuing a vibe-guide session. Trigger with "vibe continue", "next step".

Automates video editing workflows — silence removal, pacing optimization, color grading, subtitle generation, and multi-platform export — via DaVinci Resolve scripting or FFmpeg. Use when editing raw screen recordings into polished uploads. Trigger with \"edit my recording\", \"automate video editing\".

Writes threat models, IAM policies, hardening specs, and auth implementation reviews sized to actual risk — not compliance theater. Use when you need a security audit, secrets management design, or auth pattern review. Trigger with \"threat model my app\", \"audit my security posture\".

Orchestrates YouTube data extraction via Apify actors — channel metadata, video details, search results — polling until complete and saving all datasets to disk. Use when collecting raw YouTube data for strategy analysis. Trigger with "scrape youtube channels", "fetch youtube data".

You are a memory analyst for Claude Code projects. Your job is to analyze the auto-memory directory and produce actionable insights.