Skill Claude CodeCodex
Run a nightly sweep that keeps an existing repo's docs and changelog from rotting: diff the code since the last run, bring the docs for the changed surface back in line with the implementation, append every user-relevant change to CHANGELOG.md (or record a no-change night), and open ONE reviewable PR — never…
Skill Claude CodeCodex
The outer orchestration loop over the Agent Teams shared task list: the lead loops the board until EVERY task is completed AND each passes its TaskCompleted gate, feeding idle workers via the TeammateIdle hook so the team never stalls. One pass = read the board, assign the highest-priority unblocked task to each idle…
Skill Claude CodeCodex
Drive a metric under its budget in a disciplined profile-optimize-reprofile loop run under REPEATABLE conditions: benchmark the whole measured set under a fixed environment, find the single highest-leverage hotspot or regression, optimize one thing, re-benchmark the WHOLE set, and repeat until the metric is under…
Skill Claude CodeCodex
Keep a repo's git state intentional on a weekly cadence: scan every branch, PR, commit trail, and worktree, classify each as current / owned / safely removable-with-evidence, RECOVER any valuable work before deleting, then remove exactly one class of stale items with evidence — looping until every item is accounted…
Skill Claude CodeCodex
Watch a production or CI error signal on a cadence and, when an ACTIONABLE error appears, trace its root cause, fix it in a branch, verify the failing signal now passes, and open a PR for a human to merge — never auto-deploy and never auto-merge a prod hotfix. One pass polls the error source: actionable error present…
Skill Claude CodeCodex
The front door to the whole toolkit — one reliable entry point that reads what you want, picks the RIGHT starting skill (orchestrator, plan-builder, a loop, a role or workflow skill, or skill-explorer), and launches it for you — so you stop reaching for orchestrator on everything just to be sure a skill fires. Use…
Skill Claude CodeCodex
Adapt prompts, skills, and agent scaffolding when the underlying Claude model changes — currently the Claude 5 family (Fable 5/Mythos 5) vs Opus 4.x. Stronger models need LESS scaffolding: this skill says what to PRUNE, what backfires (narrating reasoning trips a reasoningextraction refusal), and what to add for long…
Skill Claude CodeCodex
Keep the Skill-Madness catalog in sync with the filesystem. The published plugin.json skills array and every advertised skill count (README, CLAUDE.md, PLAN.md, START-HERE.md, marketplace.json) are DERIVED from disk by one command, so they never drift. Use this whenever you add, remove, or rename a skill, register a…
Skill Claude CodeCodex
Help the user discover, recall, understand, and pick the right skill from the available toolkit. Names the skill; does NOT invoke it. Use when the user is trying to find a skill ("I forgot the name of the one that does X", "what was that skill called"), asking what skills exist ("what skills do I have", "list all my…
Skill Claude CodeCodex
Review skills for quality, consistency, triggering accuracy, and adherence to the 5000-word / 500-line body guideline. Two modes: 'all' (bulk ecosystem-wide scan for ownership conflicts, length outliers, weak triggers, dead xrefs) or a single skill name (deep dive on description quality, body structure, anti-pattern…
Skill Claude CodeCodex
Plan and apply changes to an existing skill in one workflow. Reads a skill-review report (bulk or deep-dive) or inline findings, drafts an edit list with the agent's recommended answer attached, walks the edits one at a time, applies them, and re-runs lint and frontmatter checks. Use after skill-review when you're…
Skill Claude CodeCodex
Generate new SKILL.md files conforming to the ecosystem's frontmatter spec and structure conventions. Use when creating a new agent role, meta skill, workflow skill, or contract skill — anything that needs a SKILL.md scaffold. Trigger on "create a skill", "new agent", "write a SKILL.md", "scaffold a skill", "add a…
Skill Claude CodeCodex
Coordinate multi-agent Claude Code builds end-to-end: read the plan/mission, design integration contracts, dispatch role-agents in parallel, gate on QA, ship. Under ultracode (standing opt-in) or an explicit "workflow" ask, it drives the implement + verify phases with the Workflow tool — fanning out role-agents…
Skill Claude CodeCodex
Orchestrator-dispatched only. Builds API servers, business logic, and data layers for multi-agent builds. Composed by orchestrator during multi-agent builds. Not user-invocable.
Skill Claude CodeCodex
Explicitly-invoked read-only code review along two independent axes — Standards (does it follow the repo's conventions + a built-in code-smell baseline) and Spec (does it faithfully implement the originating issue/contract) — run as separate sub-agents and reported side-by-side, never merged into one score. Run on…
Skill Claude CodeCodex
Orchestrator-dispatched only. Manages database schema migrations, seed data, and schema evolution for multi-agent builds. Composed by orchestrator during multi-agent builds. Not user-invocable.
Skill Claude CodeCodex
Orchestrator-dispatched only. Generates project documentation, API docs, READMEs, and changelogs for multi-agent builds. Composed by orchestrator during multi-agent builds. Not user-invocable.
Skill Claude CodeCodex
Orchestrator-dispatched only. Builds user interfaces, client-side state, and presentation layers for multi-agent builds. Composes with frontend-design and ui-ux-pro-max for visual quality. Not user-invocable.
Skill Claude CodeCodex
Orchestrator-dispatched only. Builds containerization, orchestration, CI/CD, and deployment configuration for multi-agent builds. Composed by orchestrator during multi-agent builds. Not user-invocable.
Skill Claude CodeCodex
Orchestrator-dispatched only. Sets up logging, monitoring, metrics, and alerting for multi-agent builds. Composed by orchestrator during multi-agent builds. Not user-invocable.
Skill Claude CodeCodex
Orchestrator-dispatched only. Designs and executes performance tests, load tests, and benchmarks for multi-agent builds. Composed by orchestrator during multi-agent builds. Not user-invocable.
Skill Claude CodeCodex
Orchestrator-dispatched only. Verifies implementations match contracts, integrations connect, and edge cases are handled — owns the qa-report.json build gate. Composed by orchestrator during multi-agent builds. Not user-invocable.
Skill Claude CodeCodex
Orchestrator-dispatched only. Audits codebases for security vulnerabilities, reviews auth implementations, and verifies OWASP compliance for multi-agent builds. Composed by orchestrator during multi-agent builds. Not user-invocable.
Skill Claude CodeCodex
Find deepening opportunities in a codebase — shallow modules, missing seams, leaky abstractions — and present them as numbered candidates ready for a grilling session before any interface is proposed. Use when the codebase feels tangled, tests are hard to write, modules feel 'shallow', or it's…