ScientiaCapital

ScientiaCapital/skills

Agent Claude Code

Full observer with 7 drift detection patterns + devil's advocate stance. Writes to .claude/observers/QUALITY.md and .claude/observers/ARCH.md. Thorough analysis for STANDARD/FULL scope tasks.

ScientiaCapital/skills

Agent Claude Code

Lightweight code quality observer. Runs 4 quick checks: secrets scan, test gaps, silent failures, debt markers. Writes to .claude/observers/QUALITY.md. Fast (<60s), cheap (<$0.05).

ScientiaCapital/skills

Agent Claude Code

Analyze skill outcomes, score per-skill health, write SKILLHEALTH.md. Haiku-powered, $0.02/run.

ScientiaCapital/skills

Command Claude Code

Read-only audit of the BDR skill catalog — scores every skill, maps overlaps/gaps, and writes proposal patches (no skill files modified, nothing deprecated).

ScientiaCapital/skills

Command Claude Code

End of day — verify everything is clean and shipped.

ScientiaCapital/skills

Command Claude Code

Quick fix — branch, fix, test, commit. No ceremony.

ScientiaCapital/skills

Command Claude Code

Quick start — deps check, git state, last commits. 30 seconds.

ScientiaCapital/skills

Command Claude Code

Clean PR workflow — branch, build, simplify, review, submit.

ScientiaCapital/skills

Command Claude Code

Quick code review of recent changes.

ScientiaCapital/skills

Command Claude Code

Stage, commit, push. One command.

ScientiaCapital/skills

Command Claude Code

Simplify recent code — reduce complexity, improve readability.

ScientiaCapital/skills

Command Claude Code

Record outcome/feedback for a skill run.

ScientiaCapital/skills

Command Claude Code

Run skill health analysis on outcome data.

ScientiaCapital/skills

Command Claude Code

Project health snapshot — git, deps, tests, CLAUDE.md.

ScientiaCapital/skills

Hook Claude Code

Runs when a session starts, executing morning-pipeline.sh via bash. From ScientiaCapital/skills.

ScientiaCapital/skills

Hook Claude Code

Runs before the agent uses a tool for Write, Edit, Bash, mcp__claude_ai_Apollo_io__apollo_contacts_create, mcp__claude_ai_Apollo_io__apollo_emailer_campaigns_add_contact_ids and mcp__claude_ai_Clay__find-and-enrich-contacts-at-company tool calls, running an inline shell check. From ScientiaCapital/skills.

ScientiaCapital/skills

Hook Claude Code

Runs after a tool call finishes for Write, Write, Edit, Skill, mcp__claude_ai_Apollo_io__apollo_people_match and mcp__claude_ai_Apollo_io__apollo_people_bulk_match tool calls, executing log-outcome.sh, log-skill-usage.sh and log-workflow-result.sh via bash with --name-only and --cached (4 commands). From…

ScientiaCapital/skills

Hook Claude Code

Runs when the agent finishes a response, running an inline shell check. From ScientiaCapital/skills.

ScientiaCapital/skills

Settings file Claude Code

Agent settings declaring 4 hook events (SessionStart, PreToolUse, PostToolUse, Stop).

ScientiaCapital/skills

Instructions file

Claude Code instructions for ScientiaCapital/skills, covering tim's skills library, how to use this folder, folder structure, self-improvement infrastructure (p12) and hubspot configuration.

ScientiaCapital/skills

Skill Claude CodeCodex

Auto-generate structured AE handoff briefs when Tim books a demo for Phil Sandler or Lex Evans. Packages MEDDIC scorecard, competitive intel, discovery notes, call transcripts, and next-best-action into a single document the AE can scan in 60 seconds. Increases demo-to-close rate by ensuring AEs walk in fully…

ScientiaCapital/skills

Skill Claude CodeCodex

Map task types to the best agent, skill, model, and fallback. Route any task to the right tool. Use when: which agent, route task, agent for this, best agent, capability matrix.

ScientiaCapital/skills

Skill Claude CodeCodex

Orchestrate teams of parallel Claude Code sessions working on the same codebase. Handles task decomposition, agent coordination, context isolation, and merge strategies. Builds on worktree-manager for infrastructure.

ScientiaCapital/skills

Skill Claude CodeCodex

REST/GraphQL API design patterns - resource naming, HTTP methods, error handling, pagination, versioning. Use when: design API, REST endpoints, GraphQL schema, error responses, pagination, rate limiting, API documentation.