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.
-
zate Skill StatuslineConfigure the devloop statusline for Claude Code
-
zate Skill Pr FeedbackThis skill should be used for integrating PR review comments back into devloop plan, parsing review feedback, addressing reviewer concerns
-
zate Bundle ExcalidrawGenerate diagrams with a hand-drawn whiteboard aesthetic by writing .excalidraw files directly. Use when the user wants informal sketches, whiteboard-style visuals, or diagrams they can open and edit in Excalidraw. Saves a local .excalidraw file -- viewing/rendering is handled separately.
-
zate Skill Diagram RouterAutomatically select the best diagram format (SVG, Mermaid, Excalidraw, D2) and diagram type based on user intent. Use when the user asks to create, draw, visualize, or diagram something and has not specified a format. Routes to the appropriate format-specific skill.
-
zate Skill Wsl Clipboard SetupGuide the user through setting up WSL2 clipboard image paste fix - dependency installation, verification, and keybinding configuration
-
truchot Bundle Paid MediaExpert Paid Media pour publicité digitale payante. Utilise ce skill quand: (1) Google Ads / SEA, (2) Social Ads (Meta, LinkedIn, TikTok), (3) Display et programmatique, (4) optimisation des campagnes payantes, (5) gestion des budgets publicitaires.
-
ed3dai Skill Asking Clarifying QuestionsUse after initial design context is gathered, before brainstorming - resolves contradictions in requirements, disambiguates terminology, clarifies scope boundaries, and verifies assumptions to prevent building the wrong solution
-
ed3dai Skill Writing Implementation PlansUse when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
-
ed3dai Skill Finishing A Development BranchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
-
snits Skill DreamUse when Jerry invokes /dream or when the startup DREAM due-check reports 7+ days since the last pass. Weekly editorial inquiry over the mnemosyne journal — maintains existing pearls, spots candidate themes, and emits proposals into the vault promotion gate. Read-only against the journal.
-
snits Bundle RetroUse when Jerry asks for a retrospective, a weekly review, a summary of the past week's work, or "what kept getting in our way"; also when /wakey reports a retro is due.
-
snits Skill Verify ClaimsRe-verify every factual claim in the pending issue/doc/commit before it lands.
-
snits Skill Roborev RefineUse only when the user explicitly invokes /roborev-refine
-
snits Skill Roborev ReviewUse only when the user explicitly invokes /roborev-review
-
snits Skill Roborev SnoozeUse only when the user explicitly invokes /roborev-snooze
-
snits Skill Roborev RespondUse only when the user explicitly invokes /roborev-respond
-
snits Bundle Decision RoundupUse when Jerry wants to clear standing decisions across projects, asks "what am I blocking" or "what decisions are waiting on me", or after a stretch of work in one project while others sat idle; reads projstat's cross-project roll-up for needs-decision and needs-review and presents each as a decision-ready brief to rule on in one sitting.
-
closedloop-technologies Skill Tool ShadowDesign an explicit, uncertainty-aware approximation of an expensive or long-running tool so agents can explore and reason quickly without confusing prediction with verification.
-
closedloop-technologies Skill Tool Shadow CalibrationEvaluate, challenge, calibrate, and improve a Tool Shadow using authoritative results, physical outcomes, active learning, and decision-aware metrics rather than average prediction error alone.
-
truchot Bundle Client IntakePoint d'entrée automatisé pour réception, qualification et routage des demandes clients vers l'agence IA. Utilise ce skill quand: (1) un nouveau client contacte l'agence, (2) qualification d'un besoin projet, (3) routage vers le bon interlocuteur/skill, (4) création d'un brief initial, (5) estimation préliminaire de faisabilité.
-
openaec-foundation-erpnext-anthropic-claude-development-skil Bundle Frappe Ops PerformanceUse when tuning MariaDB, configuring Redis memory, sizing Gunicorn workers, setting up CDN, or profiling slow queries. Prevents performance bottlenecks from default configurations, memory exhaustion, and unoptimized database queries. Covers MariaDB tuning, Redis configuration, Gunicorn worker sizing, CDN setup, slow query log analysis, Python profiling, request profiling. Keywords: performance, MariaDB, Redis, Gunicorn, CDN, slow query, profiling, tuning, optimization, workers, slow page, loading time, ERPNext slow, why is it slow, page takes long, timeout..
-
openaec-foundation-erpnext-anthropic-claude-development-skil Bundle Frappe Syntax HooksUse when configuring Frappe hooks.py for app events, scheduler tasks, document events, fixtures, boot session, jenv customization, or website routing. Covers v14/v15/v16 including extend_doctype_class. Keywords: hooks.py, doc_events, scheduler_events, fixtures, app_include_js, override_whitelisted_methods, extend_doctype_class, hooks.py example, how to register hook, available hooks list, extend_doctype_class example.
-
closedloop-technologies Skill Progressive Fidelity Tool RoutingChoose between exact rules, cached results, Tool Shadows, reduced tools, authoritative tools, and physical tests using cost, latency, uncertainty, decision stakes, and evidence freshness.
-
hopeoverture Bundle Supabase Prisma Database ManagementThis skill should be used when managing database schema, migrations, and seed data using Prisma ORM with Supabase PostgreSQL. Apply when setting up Prisma with Supabase, creating migrations, seeding data, configuring shadow database for migration preview, adding schema validation to CI, or managing database changes across environments.
-
snits Skill Sync DevcontainerSync a project's .devcontainer/ files with the canonical template at ~/.claude/scratchpad/devcontainer-template/, or scaffold a new .devcontainer/ from the template. Triggers on /sync-devcontainer with optional arguments — no args (current project), <path> (specific project), or 'all' (sweep ~/devel/*).
-
snits Skill Interactive RebaseUse when you need to amend a non-HEAD commit in git history without an interactive editor — automates rebase via fixup, autosquash, and GIT_SEQUENCE_EDITOR=true
-
snits Skill Stgit Stack EditingUse when amending, reordering, or splitting commits in an in-progress patch series — especially fixing reviewer findings inside the offending commit instead of stacking fixup commits. Stacked Git (stg) alternative to interactive-rebase.
-
snits Bundle Commit DecompositionUse when breaking one or more oversized git commits into a series of logical commits — "decompose this commit", "break up this history", "atomic commits for this range". Lead-orchestrated - fresh subagent per patch, diff-parity gate, state file as cursor.
-
snits Skill Roborev Design ReviewUse only when the user explicitly invokes /roborev-design-review
-
snits Skill Roborev Review BranchUse only when the user explicitly invokes /roborev-review-branch
-
snits Skill Architecture Case StudyUse when studying the architecture of an open-source codebase for the case-study series — "case study", "architecture study", "study how X is built", adding a subject under ~/devel/case-studies. Not for reviewing our own projects' code.
-
snits Skill Roborev Lookahead ReviewUse only when the user explicitly invokes /roborev-lookahead-review
-
snits Bundle Swift Architecture SkillSwift architecture patterns and playbooks for MVVM, TCA, Clean Architecture, and more.
-
snits Skill Roborev Design Review BranchUse only when the user explicitly invokes /roborev-design-review-branch
-
snits Skill Roborev Lookahead Review BranchUse only when the user explicitly invokes /roborev-lookahead-review-branch
-
openaec-foundation-erpnext-anthropic-claude-development-skil Bundle Frappe Impl ControllersUse when building Document Controllers in a custom Frappe app: file creation, lifecycle hooks, validation, autoname, submittable workflows, controller override, child table controllers, flags system, migration from hooks.py and Server Scripts. Keywords: how to implement controller, which hook to use, validate vs on_update, override controller, submittable document, autoname, flags, extend_doctype_class, controller testing, child table controller, which hook to use, when does validate run, how to override save, document lifecycle.
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 statusline, excalidraw, diagram-router. 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.