Development

Programming, frameworks, implementation, frontend, backend, and app development

skills in category: 80,972
pages available: 3,374

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse development skills

Showing 23,953–23,976 of 80,972 skills

Rvw WalkthroughARead, publish, improve in place, or explicitly delete one source-anchored HTML walkthrough with code references, while preserving existing Markdown and Mermaid explanations through the local rvw CLI. Use when the user asks for one implementation, surrounding-code, flow, or architecture walkthrough. Use rvw-review-compose when the user asks which Walkthroughs or Structures a whole review subject needs. Do not use this Skill for rvw comment handling or PR synchronization.developmentjavascriptjavaVotes: 0GitHub stars: 2
Rvw StructureARead, publish, replace in place, or explicitly delete one source-anchored relationship map with optional authorial spatial presentation through the local rvw CLI. Use for either one bounded PR-relevant behavior or review question, or one PR-scoped file map whose Nodes are repository files and whose Edges are verified inter-file relations. Use rvw-review-compose when the user asks which Walkthroughs or Structures a whole review subject needs. Use rvw-walkthrough when ordered prose and transiti...developmentgobashVotes: 0GitHub stars: 2
Rvw Review ComposeAAnalyze one Pull Request or explicit review subject and choose source-anchored rvw Walkthroughs, Structures, and direct code reading that minimize total comprehension cost. For a PR-wide composition, always include a PR-scoped file map of relevant definitions, processing, and dependencies while adapting every other surface. Use when the user asks to recommend or explicitly produce an overall review composition; recommendation is non-mutating. Use the producer Skills directly for one explicitl...developmentjavascriptgoVotes: 0GitHub stars: 2
ReconbridgeADrive the ReconBridge toolchain to reverse-engineer / recon / tamper Android apps on a rooted (KernelSU) device from the PC side. Use whenever the task involves: pulling an APK or native .so off a device, decompiling with jadx, locating classes/methods with DexKit/androguard, Ghidra native analysis, hooking or tracing Java methods (LSPosed) or native functions (Zygisk/ ShadowHook), watching runtime args/return-values/fields via SSE events, dumping memory / unpacking dex, or comparing two beha...developmentgojavaVotes: 0GitHub stars: 34
StatsAShow quick numeric statistics about local coding-agent usage — sessions, prompts, tool calls, error counts, languages, top commands, and active hours per project, across Claude Code, Codex CLI and Gemini CLI. Use when the user asks how much they have used Claude Code or another coding agent, asks for usage stats or numbers, says "show my stats", "istatistiklerimi göster", "ne kadar kullanmışım", or runs /devpersona:stats. Numbers only, no interpretation — for the character profile use devpers...developmentnodeVotes: 0GitHub stars: 2
AnalyzeABuild a developer character profile (persona card) from the user's local coding-agent history — Claude Code, Codex CLI and Gemini CLI transcripts, session titles, and auto-memory files, with projects worked on in several agents merged into one profile. Use when the user asks to analyze their agent or Claude Code history or past sessions, asks what kind of developer they are, says "analyze me", "build my persona", "karakterimi çıkar", "geçmişimi analiz et", or runs /devpersona:analyze. Not for...developmentnodeVotes: 0GitHub stars: 2
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
AdviseATurn the persona profile built from local coding-agent history into concrete suggestions — new agent skills worth authoring, coding-habit improvements, and architecture recommendations. Use when the user asks what skills they should create, how to improve their workflow, prompts, or code habits, says "suggest skills for me", "bana skill öner", "ne geliştirmeliyim", "önerilerin neler", or runs /devpersona:advise, optionally with a focus argument (skills | code | architecture). Requires a perso...developmentgoVotes: 0GitHub stars: 2
VerifyAClose a BUILT task with a fresh verifier. Pins the preview URL + sha, briefs the `verifier` agent or runs the `verify-change` workflow, reads its PASS / BLOCK / PARTIAL, and writes the result to the task row. Use before any row becomes ✅ VERIFIED, after every fix (a fix is new surface), and when the user asks "is it verified?".developmentrustgoVotes: 0GitHub stars: 2
Pre SendACheck anything going to a client before the user sends it (email, message, report, deck, attachment, answer to feedback). Compares the draft with everything already sent to that reader and with the signed quote, checks every fact at its source, checks questions and attachments, and returns a pass/fail list plus the corrected draft. Never sends anything.developmentgoapiVotes: 0GitHub stars: 2
HandoverAWrite the end-of-session handover when a session stops with work in flight (built but unverified, on a preview, unmerged, or waiting on the user or the client). Updates registry rows first, then writes a short handover file from evidence, releases claims to peer sessions, and sends the user only the decisions. Also use when picking up someone else's handover.developmentrustgoVotes: 0GitHub stars: 2
Splitlane FleetCOpen and drive other CLI coding agent sessions in Splitlane - open a session, hand it a task, hear when its turn ends, read its answer - all over the public `splitlane` CLI. Use when the user asks you to open a session in Splitlane, or to coordinate, supervise, or hand work between agents (Claude Code, Codex, OpenCode, Gemini, ...) that are open in Splitlane.developmentrustgoVotes: 0GitHub stars: 5
Jev Model RouterASuggest one host-provided coding model for a bounded task when several available models differ in cost and capability.developmentVotes: 0GitHub stars: 5
Skills DirectorySkills Directory 6 slots · $699/mo · on every skill page · sponsors can never buy grades.See placements
Jev Bug TriageASuggest the first component to inspect for a bug from a finite set of plausible components.developmentVotes: 0GitHub stars: 5
ArchgramADraws a project's software architecture as an animated SVG with archgram, for its README and docs, from the code and documentation, or from a document the user names (a docs page, a design doc, an article). Writes a spec in docs/diagrams/, checks and draws it with the archgram command, in the project's own colours when asked, then opens the drawing and lists each part with the file behind it. Also draws a sequence diagram, the order in which the parts call each other for one request, and what...developmentrustgoVotes: 0GitHub stars: 7
Flow Ptr AppAGuide for developing a new Flow Production Tracking (FPTR) / ShotGrid Toolkit (sgtk) app following a Spec-driven approach. Triggers on: create a new FPTR app, new Flow Production Tracking app, new Toolkit app, tk-multi-starterapp, sgtk app development, tank install_app, tank switch_app, dev sandbox pipeline configuration, ShotGrid Toolkit app.developmentpythongoVotes: 0GitHub stars: 65
Aps Docs PortalANavigate the Autodesk Platform Services (APS) documentation portal — find the right API docs, decode glossary terms, index table-of-contents JSON trees, extract content from static HTML pages, and build valid aps.autodesk.com portal links. Covers ACC, BIM 360, Model Derivative, Data Management, Viewer, Design Automation, Authentication, Webhooks, and all related APS APIs.developmentjavascriptpythonVotes: 0GitHub stars: 65
SokratesAStart here for anything about Sokrates (sokrates.dev), the source-code analysis tool: analyze a repository, understand a codebase, set up or improve the Sokrates config, scan for risks, build a landscape of many repositories, improve code where it matters. Finds out where the user is and routes to the right sokrates-skill, running Sokrates when that is the next step.developmentpythonrustVotes: 0GitHub stars: 3
Testing ScanAReads the tests as a system: the test model as implemented (layers, frameworks, locations, test-to-main ratio per component), the coverage map inferred from what tests reference, test quality (assertions, mocking, determinism, flakiness, skips, duplication), the infrastructure and how to run them, and the gaps on load-bearing paths. Use for how well a project is tested, what the tests cover, flaky or untrustworthy tests, where coverage is missing, or a test strategy review.developmentpythonrustVotes: 0GitHub stars: 3
Skills DirectorySkills Directory Pro Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills.See Pro
Tech Stack ScanADeep technology-stack inventory: languages, frameworks, libraries, build tooling, CI/CD, infrastructure, databases, external services and protocols, each with file/line evidence, written as validated findings. Use for what technologies a codebase uses, a tech inventory or radar input, a dependency overview, or when another analysis needs a reliable picture of the stack first.developmentpythonrustVotes: 0GitHub stars: 3
Storage ScanAMaps how a codebase works with persistent data: what lives in files, databases, caches and object stores and in which formats, how it is accessed (ORM vs raw SQL, transactions, locking, streaming), how schemas and formats are versioned and migrated, integrity and corruption handling, and the data lifecycle (retention, cleanup, backup, export). Use for where a project stores its data, migrations, file formats, data integrity, retention, or a storage review.developmentpythongoVotes: 0GitHub stars: 3
Sokrates Scan CoreAShared foundation of every Sokrates AI scanner: the findings format with file/line evidence, the evidence rules, how to read a _sokrates analysis, and the validate / render / merge / diff / re-check / summarize scripts. Load when running any *-scan skill, writing a new scanner, or validating, rendering, diffing or summarizing findings files.developmentpythonrustVotes: 0GitHub stars: 3
Risk Synthesis ScanATurns Sokrates' quantitative risk signals into explained, actionable findings: what each hotspot file does, why its metrics (complexity, churn, single ownership, change coupling) make it risky, and what to do. Use for where the risks are, which files to refactor first, debt hotspots, bus factor or knowledge risk, "what should we worry about", or to have Sokrates results explained and prioritized. Requires a _sokrates analysis.developmentpythonrustVotes: 0GitHub stars: 3
Reliability ScanAMaps how a codebase behaves when things go wrong: the error model, failure handling on the paths that matter, isolation and blast radius, recovery (retries, backoff, timeouts, circuit breakers, idempotency), degradation and offline modes, resource cleanup, crash safety and orderly shutdown. Use for error handling, resilience, robustness, fault tolerance, "what happens when X fails", retries and timeouts, or a reliability review or hardening plan.developmentpythonrustVotes: 0GitHub stars: 3
Performance ScanAStatic performance review: the workload model (what scales with input, hot loops, data volumes), hot-path algorithms and data structures, I/O and memory behaviour, concurrency and contention, caching and recomputation, explicit limits, ranked into likely bottlenecks and the highest-leverage optimizations. Use for why a project is slow, bottlenecks, what scales badly, memory, parallelism, caching, or a performance or efficiency review.developmentpythonrustVotes: 0GitHub stars: 3