Skill Codex
Automation-safe GitHub issue to green PR orchestrator. Use when Codex is asked to process GitHub issues labeled bug or needs-triage, run a one-agent-one-job repair workflow, create or babysit PRs, get PR checks/review threads green, or run a recurring Codex automation that turns eligible issues into proved pull…
Skill Claude CodeCodex
Creates mechanical contracts with postconditions, invariants, error cases, and consumer maps. Every postcondition is traceable to a test and a code line. Contracts must exist before any source code edits. Use after enterprise-plan.
Skill Claude CodeCodex
Adversarial code review with mechanical checks, contract probing, and 5 adversarial lenses. Bugs recycle to contract for full TDD treatment. 3-fail circuit breaker prevents infinite loops. Use after enterprise-review.
Skill Claude CodeCodex
Start-of-day briefing for ADHD workflow. Shows what happened since last session, surfaces stale/blocked items across ALL life domains (dev, business, personal, learning, creative), recommends focus items, and proactively nudges about forgotten things. Use when the user says "good morning", "what's up", "brief me"…
Skill Codex
Control nested single-job subagents without overrunning thread capacity. Use when the user asks for nested agents, subagents, bug-factory style one-agent-one-job delegation, review coordinators, multi-agent build/review/proof loops, or when prior agent loops hit thread limits and need disciplined orchestration.
Skill Claude CodeCodex
Fast guilt-free shelving of vault items you're not doing right now. Preserves context and sets an optional reminder date. Works for dev items, business tasks, personal errands, learning goals — anything in the vault. Use when the user says "park this", "not now", "shelve it", "put it aside", "I'll do this later", or…
Skill Claude CodeCodex
Evidence-gated post-fix review that classifies whether a bug change removes the root cause or only masks the symptom. Any invocation, including a one-sentence prompt, requires the full canonical workflow and Required Output sections: Evidence Ledger, Assumption Ledger, Boundary Ledger, Specialist Reviews, Causal…
Skill Claude CodeCodex
Use when a plan, design, migration, or deployment checklist is drafted and needs review before passing a planning gate or proceeding to implementation. Triggers on phrases like "review this plan", "is this ready", "gate check", "audit the plan", "stakeholder review", or whenever a document in docs/plans/…
Skill Claude CodeCodex
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. For refactor, debugging, lifecycle/status, or system-design plans, require source…
Skill Claude CodeCodex
Create or run a post-merge validation kit for a PR after it lands. Use when the user asks how to test a merged PR, validate a release, smoke-test production, verify deploy behavior, or choose agent-run versus human-run post-merge checks.
Skill Codex
Audit GitHub pull requests against the live Helpdesk Postgres schema. Use when asked to check a PR, merged PR, open PR, schema drift, SQL call coverage, database variables, or PR review failures against live database shape; publishes bug-labeled issues for merged or closed failing PRs and PR conversation comments for…
Skill Codex
Run before coding starts when the user wants best-practice hardening outside or before the enterprise pipeline: live source truth, live proof plan, domain hardening opportunity, SRP/refactor opportunity, table/write ownership compliance, SQL/schema risk, blast radius, edge cases, recurrence guards, and clear stop…
Skill Claude CodeCodex
Promote dev to production (dev→main PR → gates → merge → migrations-first → pinned API deploy → portal verify → canary watch). Use when the user says "promote", "ship to main/prod", or "deploy the changes to main".
Skill Claude CodeCodex
Session-start skill that loads learned behaviors from cortex annotations. Reads accumulated user corrections and builds a LEARNED BEHAVIORS context block that shapes agent behavior for the entire session. Run at session start or on-demand via /prompt-intelligence.
Skill Codex
Use when someone wants to claim work is fixed, done, ready, green, merge-ready, shipped, proven, or deployed; when GitHub checks passed but live proof may be missing; or when proof must span patch-or-fix, prove-it, PR checks, review threads, merge, and dev/prod evidence. This skill composes existing proof skills and…
Skill Codex
Post-fix runtime proof gate. Use after Codex implements or reviews a bug fix, feature fix, PR, workflow change, or claimed repair; before saying fixed/done, committing, opening a PR, merging, or shipping. Requires mandatory blast-radius, review-feedback trap replay, actual runtime evidence at the boundary where the…
Skill Claude CodeCodex
REX (Retail Express) SOAP API protocol guide. Use this skill before writing or modifying any SOAP envelope, REX API call, REX webhook handler, or code that communicates with REX endpoints. Covers dual SOAP protocol detection (1.1 vs 1.2), three-endpoint architecture (WebStore, Ecommerce, WMS), envelope construction…
Skill Claude CodeCodex
Run the full verification pipeline (lint, unit tests, E2E if UI changed) — invoke after code changes.
Skill Claude CodeCodex
Use before committing changes to verify no scope creep has occurred. Triggers when about to run git commit, when reviewing changes with git diff, when the diff touches files unrelated to the original task, or when more than 5 files have been modified. Also use when the user says "check scope", "did I go off track", or…
Skill Claude CodeCodex
Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis.…
Skill Claude CodeCodex
Use this skill when the user asks "where are we", "status check", "health check", "checkpoint", "what have we done", or any progress review of the current session. Also use when the user wants to switch tasks, drop current work for something urgent, pause to review scope, or says the context/session is getting long.…
Skill Claude CodeCodex
Shopify API and webhook integration guide. Use this skill before writing or modifying any Shopify webhook handler, API call, product sync, order sync, inventory push, or fulfillment code. Covers HMAC-SHA256 webhook verification, idempotency patterns, REST vs GraphQL API selection, cursor-based pagination, 429 rate…
Skill Codex
Use when the operator wants specialised build/review/proof agents, says agents are not specialised enough, asks for subagent prompts, multi-axis review, one-job agents, or needs work split into bounded roles before building. Produces compact specialist briefs with one job per agent, allowed scope, forbidden actions…
Skill Claude CodeCodex
SQL safety checker for database queries and migrations. This skill should be used before writing or modifying any SQL query, database migration, or code that constructs SQL strings. It enforces multi-tenant tenantid scoping, parameterized queries, correct timestamp types, IF NOT EXISTS guards, and type-safe joins.…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: