Skill Claude CodeCodex
Builds a 7-day SMB campaign kit: one offer with value, deadline, and an honest reason-why; channels picked from what the owner already has (email list, socials, storefront, partners); a day-by-day calendar; every asset drafted (three emails, three social posts, flyer copy); a simple spend/leads/sales tracking sheet…
Skill Claude CodeCodex
Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…
Skill Claude CodeCodex
Authors new SKILL.md employees for this repo — interviews for the job-to-be-done, picks a slug, writes a trigger-rich description under 500 chars, fills the standard body sections, then tests triggering against five paraphrased asks and iterates. Use when the user says "make me a skill for X", "turn this workflow into…
Skill Claude CodeCodex
Runs 14 numbered engineering protocols in one pack — brainstorm, spec, plan, scaffold, TDD red-green-refactor, systematic debugging, refactoring, code review, performance, security, docs, git hygiene, release checklist, postmortem. Use when the user says "build this feature properly", "debug this systematically"…
Skill Claude CodeCodex
Delivers a ruthless, structured critique of any screen, mockup or site — scores hierarchy, spacing rhythm, contrast, typography pairing and color discipline /10 with evidence, detects clichés (purple gradients, glassmorphism-by-default, emoji soup, cookie-cutter heroes), and ranks the top 5 highest-leverage fixes with…
Skill Claude CodeCodex
Organizes tax season — an organizer, not tax advice: a document checklist by category (income, expenses, assets, payroll, prior filings), an expense-category sweep that flags plausibly missed deductions in generic jurisdiction-agnostic categories, a quarterly-estimate calendar template, a clean handoff pack for the…
Skill Claude CodeCodex
The company audits its own payroll — tracks AI token spend per department and mission, estimates costs from session data or telemetry, sets budget alerts and writes the monthly cost memo. Use when the user says "how much is this costing me", "token spend", "AI budget", "cost per mission", or wants FinOps visibility on…
Skill Claude CodeCodex
Builds a complete CSS motion system — duration and easing tokens (fast 120ms micro-feedback, base 200ms, slow 320ms entrances; standard, decelerate and spring curves), enter/exit/emphasis patterns, stagger rules, and prefers-reduced-motion fallbacks — delivered as a copy-paste CSS/JS snippet library. Use when the user…
Skill Claude CodeCodex
Ten-minute NDA triage — classifies an incoming NDA as GREEN (sign under standard delegation), YELLOW (targeted fixes, listed), or RED (full review). Screens mutuality, term and survival, definition breadth, embedded non-solicits or non-competes, missing standard carve-outs, residuals clauses, and IP assignment…
Skill Claude CodeCodex
Builds an end-to-end UI system for a product — design tokens (color scale, type scale, spacing, radii, shadows), a component inventory covering every interaction state, a layout grid, and WCAG contrast checks — emitted as CSS variables plus a component spec doc. Use when the user says "set up a design system", "create…
Skill Claude CodeCodex
Explains budget-vs-actual or period-over-period variances: sets a materiality threshold first, builds the variance table in dollars and percent, decomposes drivers (price, volume, mix, timing, one-offs), draws a bridge waterfall, and writes the so-what per material line with forecast impact. Use when the user says…
Skill Claude CodeCodex
Vendor agreement status check — inventories what exists versus what is needed (MSA, DPA, SOW, SLA, insurance certs, security review), builds a gap analysis table, runs an expiration and renewal radar with dates and notice windows, notes surviving obligations, and delivers an onboarding go/no-go checklist. Use when the…
Agent Claude Code
Standard implementation agent for well-specified tasks tagged [T1] — features from a clear spec, unit tests, documentation, renames, config changes, mechanical multi-file edits, straightforward bugfixes with a known repro. MUST BE USED for [T1] tasks.
Agent Claude Code
Complex implementation agent for tasks tagged [T2] — multi-file refactors, concurrency/async, schema and data migrations, performance optimization, intricate state machines, bugs with unclear repro, subtle correctness work. MUST BE USED for [T2] tasks.
Agent Claude Code
Highest-reasoning tier, read-only. Use for (a) REVIEW of critical diffs — security, auth, payments, data migrations, public API contracts; (b) SOLVE — designing novel algorithms or root-causing bugs that survived two fix attempts. Expensive — invoke deliberately, with a complete dossier.
Agent Claude Code
Read-only codebase reconnaissance. Use PROACTIVELY before any planning or implementation to map relevant files, symbols, data flow, conventions, and risks. Never writes or modifies anything.
Settings file Claude Code
The self-distilling model router for AI coding CLIs — solve each problem class at the expensive tier once, execute it cheap forever. Just markdown, no proxy.
Skill Claude CodeCodex
Shared implementation discipline for executor agents — conventions, testing, diff hygiene, reporting. Preloaded into executor and heavy-executor via their skills frontmatter.
Skill Claude CodeCodex
Complexity-based routing of tasks across four model tiers — frontier (T3), strong workhorse (T2), fast executor (T1), cheapest recon (T0). Use when planning any multi-step work, when deciding which subagent should execute a task, when writing a dispatch brief, or when an executor fails and escalation is needed.
Skill Claude CodeCodex
Repo-specific execution patterns distilled from higher-tier (Opus/Fable) solutions via the tier-decay protocol. Preloaded into executor and heavy-executor at startup. Written ONLY by the main thread — executors read, apply, and report; they never edit this file.
Skill Claude CodeCodex
Post-completion distillation protocol that converts high-tier solutions into cheaper-tier playbook entries and recalibrates routing from real outcomes. Use after completing any [T2] or [T3] task, when logging a task outcome to the routing ledger, when a playbook probe passes or fails, or when a class keeps escalating.
Cursor rule
TierDecay protocol — tier routing, decay, and integrity invariants (always on).