Menu
SkillsMP has collected 31 skills from dayfinggg/claude-code-codex-skills. Open a skill to review its source and details.
Showing 31 of 31 collected skills.
Resolve material product, behavior, scope, interface, migration, or acceptance decisions that evidence cannot safely determine. Use only while such decisions remain unresolved, not merely because work is large or multi-stage.
Assess, design, or evolve module, data, runtime, deployment, or team-ownership boundaries. Use when those boundaries or responsibility contracts are the task; skip isolated code changes, folder cleanup, and refactors that leave boundaries intact.
Design, implement, or review UI/UX when a user-facing surface needs product, interaction, visual, accessibility, design-system, responsive, or public-web presentation judgment. Skip backend, mechanical frontend work with a settled design, and generic code…
Isolate an unknown cause of a bug, regression, flaky failure, or performance anomaly through reproducible evidence. Use when the cause is uncertain; skip straightforward changes with a known cause.
Resolve unclear business meaning, invariants, consistency ownership, or bounded-context boundaries. Use only while one of those domain decisions remains material; skip technical module reorganization, generic architecture, CRUD, utilities, and styling.
Deliver an approved scoped change and map its acceptance criteria to implementation and observed evidence. Use for criterion-driven implementation; skip review-only, planning-only, and unresolved product decisions.
Apply language- and platform-specific engineering rules to retained source code being created or changed. Use for implementation quality and configured gates; skip review-only work, disposable experiments, and generated or vendored code.
Review a concrete diff, pull request, patch, or completed change for material defects and unmet requirements. Use only when a changed artifact exists and review is requested; skip greenfield assessment and remain read-only unless fixes are requested.
Create an evidence-backed implementation plan or decompose an approved specification when the user explicitly asks for planning or decomposition. Do not trigger merely because an authorized implementation is multi-stage.
Run a verified red-green-refactor cycle for observable behavior. Use only when the user explicitly requests TDD or repository policy requires test-first work; skip ordinary implementation, testing, research, prose, and disposable spikes.
Audit local or third-party agent skills for trigger quality, workflow precision, token efficiency, compatibility, provenance, and execution safety. Use before installing, publishing, trusting, or substantially revising SKILL.md packages and their scripts,…
Derive reviewable agent-skill candidates from repeated successful sessions, corrections, traces, or operational histories. Use when a workflow has recurred and the user wants to preserve evidence-backed procedural knowledge; never install or activate…
Research current or time-sensitive claims using authoritative primary sources and dated evidence. Use when a request asks for latest information, exact citations, recent documentation, rules, prices, versions, people, recommendations, or verification of a…
Change external libraries, frameworks, SDKs, runtimes, compilers, or build tools with verified compatibility and bounded scope. Use when an authorized change adds, upgrades, downgrades, replaces, or removes a dependency, including CVE remediation. Do not use…
Review a branch, pull request, commit range, or working-tree diff on two axes: repository standards and the originating requirements. Use for explicit code or PR review, independent pre-merge quality gates, and checking an implementation against its…
Design or improve a known module boundary, interface, seam, dependency, or test surface. Use when implementing a new module, restructuring identified coupling, choosing an interface, or improving concrete testability. Do not use for broad architecture…
Delegate bounded work to Claude Code subagents and coordinate their results with explicit ownership, evidence, and stopping conditions. Use when the user explicitly asks for agents, subagents, delegation, parallel work, or an agent team, or when an applicable…
Design, implement, redesign, or visually review production-quality websites, apps, dashboards, flows, pages, and UI components. Use when visual direction, usability, responsive behavior, accessibility, interaction states, information hierarchy, or…
Use only when a defect's root cause is unknown and requires reproducible investigation, such as a regression, crash, flaky failure, or performance problem. Do not use for an obvious local correction, ordinary feature work, or architecture review; use this…
Create a compact, secret-safe continuation brief for another Claude Code session or engineer. Use only when the user explicitly asks to hand off, compact, transfer, pause and resume, or continue substantial work elsewhere. Do not use for normal final reports,…
Audit a codebase for evidence-backed architectural friction and rank bounded improvement candidates before implementation. Use when the user requests an architecture health review or repeated change difficulty spans modules and the boundary is not yet known.…
Create an evidence-backed, blameless postmortem after a production incident has stabilized. Use for material outages, degradation, data loss, emergency rollback, manual intervention, or monitoring failure. Do not use during active response or for routine…
Evolve a live API, database schema, event, stored format, configuration format, or provider contract while old and new states must coexist. Use for staged compatibility or production-data migrations. Do not use for private atomic refactors, greenfield…
Create an evidence-grounded, decision-complete implementation plan at the smallest useful level of detail. Use when the user explicitly asks to plan, scope, or break down a complex change, or when unresolved product or architecture decisions block safe…
Build a disposable runnable experiment that resolves one material uncertainty about behavior, state, integration, or interface design. Use when the user requests a prototype, spike, proof of concept, or alternatives, or explicitly authorizes an experiment…
Research external, niche, disputed, version-sensitive, or recently changed technical facts using authoritative primary sources and explicit evidence. Use when the user asks to research, compare, verify, or cite, or when an implementation materially depends on…
Resolve conflicts in an active Git merge, rebase, cherry-pick, or revert by preserving compatible intent from both sides. Use when Git reports unmerged paths or the user asks to resolve current conflicts. Do not use for ordinary branch comparison, starting…
Assess and improve go-live readiness for a service, API, worker, migration, infrastructure change, or release. Use for explicit readiness decisions or changes that materially affect capacity, external failures, observability, recovery, deployment, or…
Implement behavior through verified red-green-refactor cycles. Use when the user explicitly requests TDD or red-green-refactor, or when an agreed workflow requires test-first development. Do not trigger merely because a bug or suitable test surface exists; do…
Turn settled requirements, an approved plan, a prototype result, or an issue into a durable implementation-independent specification with testable acceptance criteria and explicit scope. Use when the user asks for a specification, PRD, requirements document,…
Break an approved plan, specification, or settled conversation into independently verifiable vertical-slice tasks with acceptance criteria and blocking dependencies. Use when the user asks for tickets, issues, a backlog, or work units for multiple sessions or…