Skill Claude CodeCodex
Turn accepted requirements into ordered dependency-aware slices and a repository-grounded implementation plan. Use before editing when work spans systems, has migration or rollout risk, needs architecture choices, or should be split.
Skill Claude CodeCodex
Coordinate a live outage, breach, or degradation affecting users. Establish incident command; triage, contain harm, bound blast radius, preserve evidence, communicate, roll back, and verify restoration.
Skill Claude CodeCodex
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.
Skill Claude CodeCodex
Canonical lefthook git-hooks setup — pre-commit (format, check, secret scan) and pre-push (test), each delegating to mise run tasks. Use when configuring or debugging git hooks.
Skill Claude CodeCodex
Create, theme, validate, and embed Mermaid diagrams as the default text-based diagram format for GitHub, Slidev, documentation, and technical communication.
Skill Claude CodeCodex
Configure pinned mise tools and canonical install, format, check, test, build, and watch tasks shared by hooks and CI.
Skill Claude CodeCodex
Execute an accepted implementation plan in bounded, verified slices. Use to coordinate multiple agents and shared-file ownership, resume planned work, or finish scoped tasks without crossing commit, push, deploy, or publication boundaries.
Skill Claude CodeCodex
Red-team a product, architecture, implementation, migration, or launch plan before execution. Use for pre-mortems, strategy or scope challenge, and independent testing of assumptions, dependencies, and failure modes — not code.
Skill Claude CodeCodex
Critique customer interface flows using interaction, visual, responsive, keyboard and screen-reader accessibility, content, and runtime evidence. Use for UX audits, design reviews, UI polish, onboarding, empty states, or redesign.
Skill Claude CodeCodex
Discovery, specification, launch, and learning for a product in one loop. Build-or-stop calls, MVP wedges, demand tests, customer interviews, PRDs, requirements, user journeys, acceptance, positioning, onboarding, rollout, pricing, pivots.
Skill Claude CodeCodex
Audit production operability and operational fitness: go/no-go, rollback, migrations, observability, recovery, support and halt thresholds; separate local, exact-head CI, runtime, deployed, and public release proof.
Skill Claude CodeCodex
Turn audit findings into deduplicated, prioritized issue drafts with dependencies and explicit authorization before GitHub mutation.
Skill Claude CodeCodex
Select and generate the correct LICENSE — MIT for public fmind/fmind-ai repos, otherwise proprietary — and update project manifests. Use when adding or fixing a project's license.
Skill Claude CodeCodex
Design production LLM or agent prompt stacks: instructions, tool contracts, examples, outputs, and runtime context. Use for precedence, conflicts, dynamic or untrusted context; prove behavior with agent-evaluation.
Skill Claude CodeCodex
Write standalone single-file Python scripts using PEP 723 inline metadata and uv. Use when creating a quick CLI script that needs dependencies without a full project.
Skill Claude CodeCodex
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
Skill Claude CodeCodex
Design and execute risk-based test campaigns and exercise risky feature journeys; identify what remains unproved across unit, integration, E2E, browser, accessibility, performance, resilience, and manual tests. Not a diff review.
Skill Claude CodeCodex
Sync AGENTS.md (for agents) and README.md (for humans) with the codebase's current tools, layout, and usage. Use when either drifts from the project's actual state.
Skill Claude CodeCodex
Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.
Skill Claude CodeCodex
Reconstruct why tracked code exists from read-only Git history. Trace files, symbols, or lines through introducing commits or pull requests, rationale, reverts, renames, authorship, co-change clues, and issues.
Skill Claude CodeCodex
Audit a whole repository across architecture, source, tests, tooling, security, CI/CD, docs, and releases. Use for cross-cutting audits, readiness, or technical-debt reviews with ranked findings — not one diff or release candidate.
Skill Claude CodeCodex
Scan repositories with Trivy and gitleaks for vulnerabilities, IaC, secrets, licenses, images, and git history; triage concrete findings.
Skill Claude CodeCodex
Audit third-party Agent Skills/extensions for supply-chain security without running them before install/trust. Inspect scripts, hooks, MCP/plugins, hidden instructions, symlinks, credential/network flows, and provenance/licenses.
Skill Claude CodeCodex
Manage secrets with sops and age: commit encrypted files, decrypt only in memory, and wire Flux or OpenTofu runtimes.
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: