Coding & Dev Tools
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
-
nodejsmith Skill I CritiqueUse when the user says: "critique this UI", "design critique", "review this interface", "does this look AI-generated". Evaluate design effectiveness with actionable feedback.
-
nodejsmith Skill I OverdriveUse when the user says: "go all out", "make it extraordinary", "overdrive", "wow factor", "push the limits". Push interfaces past conventional limits with advanced techniques.
-
propane-ai Skill EscalationStructure and package support escalations for engineering, product, or leadership with full context, reproduction steps, and business impact. Use when an issue needs to go beyond support, when writing an escalation brief, or when assessing whether an issue warrants escalation.
-
propane-ai Skill Ticket TriageTriage incoming support tickets by categorizing issues, assigning priority (P1-P4), and recommending routing. Use when a new ticket or customer issue comes in, when assessing severity, or when deciding which team should handle an issue.
-
willyu1007 Bundle Initialize Project From RequirementsUse only in repos that still include the `init/` bootstrap kit to produce Stage A/B/C artifacts, update skill pack selection, and sync provider skill wrappers.
-
willyu1007 Bundle Redis Guardrails And PlaybooksProvide Redis design/operation guardrails and scenario playbooks to prevent common mistakes (keys, TTL, memory, cluster, locks, rate limits).
-
willyu1007 Bundle Apply Backend Service GuidelinesApply cross-cutting backend service patterns across routing, services, repositories, validation, configuration, errors, and tests.
-
willyu1007 Bundle Build Service And Repository LayersBuild backend service and repository layers to isolate business logic from persistence and improve testability.
-
willyu1007 Bundle Resolve Typescript Build ErrorsResolve TypeScript compilation errors by grouping diagnostics, fixing root causes first, applying safe fix patterns, and verifying via a clean compile.
-
willyu1007 Bundle Implement Backend Routing And ControllersImplement or refactor backend HTTP routing and controllers using a layered pattern (routes delegate, controllers validate and call services).
-
willyu1007 Bundle Instrument Backend ObservabilityInstrument backend services with logging, error tracking, metrics, and tracing to diagnose failures and performance issues.
-
propane-ai Skill Product CopyProduct copy, microcopy, and UX writing for product UI and in-product messaging. Use when writing UI copy, error messages, onboarding, empty states, or aligning voice and tone to product.
-
propane-ai Skill Response DraftingDraft professional, empathetic customer-facing responses adapted to the situation, urgency, and channel. Use when responding to customer tickets, escalations, outage notifications, bug reports, feature requests, or any customer-facing communication.
-
propane-ai Skill Intervention PlanningIntervention tiers, target accounts, actions, owners, and timeline for at-risk customers. Use when planning interventions for at-risk accounts, when building an intervention playbook, or when tying health and churn signals to concrete next steps.
-
propane-ai Skill Metrics TrackingDefine, track, and analyze product metrics with frameworks for goal setting and dashboard design. Use when setting up OKRs, building metrics dashboards, running weekly metrics reviews, identifying trends, or choosing the right metrics for a product area.
-
propane-ai Skill Competitive DesignAnalyze competitor UX/UI with flow comparison, pattern analysis, and design implications. Use when researching competitor design, comparing flows or patterns, or preparing a competitive design brief.
-
dangeles Skill EditorUse when documents need prose improvement, CLAUDE.md style enforcement (prose over bullets, bridging transitions, complete sentences), or final polish before archival
-
dangeles Bundle CopilotUse when reviewing code INLINE during development (real-time second opinion on correctness, bugs, edge cases) in an adversarial but collaborative manner. NOT for pre-PR comprehensive review (use /pr-review-toolkit:review-pr) or post-PR automation (use /code-review).
-
dangeles Skill EconomistUse when order-of-magnitude cost estimates are needed to assess financial feasibility, compare cost-effectiveness of alternatives, or identify major cost drivers (not for detailed quotes—that's Procurement)
-
dangeles Skill ProcurementUse when equipment specifications need matching to potential vendors, sourcing landscape must be mapped (catalog items vs. custom orders), or lead time considerations affect project planning
-
dangeles Skill Cfd ReviewerUse when invoked by cfd-bioreactor orchestrator to provide adversarial engineering review of CFD simulation plans and generated code. Challenges mesh quality, boundary conditions, solver parameters, stabilization choices, and physical plausibility.
-
dangeles Bundle Skill EditorUse when creating, modifying, or refactoring any Claude Code skill in this repository — the default entry point for new skills, targeted edits, refactoring, and quality review alike. Triggers on "create a skill", "edit the X skill", "refactor a skill". Always prefer this over skill-creator or plugin-dev:skill-development for skills that belong in claude-config/.
-
dangeles Skill StatisticianUse when selecting STATISTICAL methods (hypothesis tests, regression), performing power analysis, guiding uncertainty quantification (Bayesian/frequentist), or validating MCMC/Monte Carlo implementations. NOT for deterministic algorithm design or complexity analysis (use mathematician), nor physics/engineering feasibility (use calculator).
-
natea Skill N8n Expression Testingn8n expression syntax validation, context-aware testing, common pitfalls detection, and performance optimization. Use when validating n8n expressions and data transformations.
-
telum-ai Skill EpicEpic lifecycle orchestrator. Invoke only via /epic.
-
telum-ai Skill StoryStory lifecycle orchestrator. Invoke only via /story.
-
telum-ai Bundle AdjustRe-engineers validated work after deliberate change. Use after validation to rebuild and re-prove a redesign or pivot.
-
telum-ai Skill HardenHardens post-validation defects and missed gates. Use for bugs; use adjust for deliberate redesign.
-
telum-ai Bundle AnalyzeRuns decorrelated planning analysis. Use after project-plan, epic-breakdown, or story-tasks before downstream work.
-
telum-ai Skill ValidateUser-only router for /validate --level. Auto-selection uses the project, epic, or story validator directly.
-
telum-ai Skill Epic PlanWrites epic-tech-spec.md with design and traceability. Use after epic clarification and optional architecture work.
-
telum-ai Skill Project UXDefines project UX strategy. Use before project-plan for Platform or Build projects with four-plus epics.
-
telum-ai Skill Speck ScanExtracts code-side facts at project, epic, or story scope. Use for brownfield work or a fresh reality check.
-
telum-ai Skill Story PlanWrites plan.md with design, contracts, and tests. Use after story clarification or code scan, before story-tasks.
-
dangeles Skill MathematicianUse when designing DETERMINISTIC algorithms, analyzing time/space complexity, selecting numerical methods (ODEs, optimization, linear algebra), or verifying mathematical correctness. NOT for statistical/probabilistic method selection (use statistician) or physics-based engineering feasibility (use calculator).
-
dangeles Bundle Pov ExpansionUse when seeking analogous solutions from other domains, when stuck on a problem and need fresh perspectives, or when evaluating whether approaches from field X might apply to field Y. Requires structured problem statement.
Frequently asked questions
What are Coding & Dev Tools agent skills?
Coding agent skills teach AI agents repeatable engineering workflows: reviewing pull requests, writing tests, refactoring safely, and enforcing house style. Install one SKILL.md and your agent applies the same checklist every time, whether you use Claude Code, Cursor, Codex, or another agent.
Which Coding & Dev Tools skills are most installed?
Popular Coding & Dev Tools skills on SkillMD right now include i-critique, i-overdrive, escalation. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Coding & Dev Tools skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.