Automation
Task automation and scripting
implementation-verify
by drillan
Verifies implementation against specifications by checking requirement fulfillment, task completion, and contract implementation. Generates a fulfillment report with coverage metrics. Always run after /speckit.implement completes.
plan-execution
by HJewkes
"Execute implementation plans and coordinate parallel agents. Handles in-session subagent dispatch, batch execution, parallel task coordination, and team orchestration."
triage
by weegigs
Interactive issue discovery session. Use when walking through an application to capture issues, then batch-evaluate severity and complexity.
modal-deployment
by ferdousbhai
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch jobs, scheduling tasks, serving APIs with GPU acceleration, or scaling compute-intensive workloads. Triggers on requests for serverless GPU infrastructure, LLM inference, model training/fine-tuning, parallel data processing, cron jobs in the cloud, or deploying Python web endpoints.
script-writer
by mamba-mental
This skill should be used whenever users need YouTube video scripts written. On first use, collects comprehensive preferences including script type, tone, target audience, style, video length, hook style, use of humor, personality, and storytelling approach. Generates complete, production-ready YouTube scripts tailored to user's specifications for any topic. Maintains database of preferences and past scripts for consistent style.
subagent_manager
by oneles
Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates
next
by weegigs
Review tasks and recommend the next action. Use when starting a session or after completing work to identify highest-impact next steps.
code-cleanup
by krmcbride
Delegate repetitive tasks to specialized agent to preserve context. Use when user asks to fix linting errors, fix diagnostics, rename variables across files, update imports, fix formatting issues, or perform other mechanical bulk changes across multiple files.
evaluate-exponential-trend-deviation-regimes
by fatfingererr
計算資產價格相對長期指數成長趨勢線的偏離度，衡量當前是否處於歷史極端區間，並可選擇性地進行宏觀因子分析以判斷行情體質。
agentic-structure
by BackGwa
Collaborative programming framework for production-ready development. Use when starting features, writing code, handling security/errors, adding comments, discussing requirements, or encountering knowledge gaps. Applies to all development tasks for clear, safe, maintainable code.
vbaExcel
by lunasoft2001
Extraer y reimportar codigo VBA de archivos Excel .xlsm en Windows usando Python (pywin32/oletools) o VBScript. Usar para exportar modulos .bas, refactorizar en VS Code y volver a importar al XLSM.
automation-governance
by SanctifiedOps
Governance and guardrails for automation/bots: permissions, logging, kill-switches, and ethics. Use before deploying bots that move funds or post publicly.
openspec-writing-plans
by AnthemFlynn
"OpenSpec-integrated plan writing. Use INSTEAD of superpowers:writing-plans when project has openspec/ directory. Reads design from OpenSpec change, writes plan to OpenSpec change."
realm-persistence
by dagba
Use when implementing Realm database in iOS apps, encountering thread-safety errors, async/await crashes, performance issues with sync/writes, or integrating with Codable APIs
swift-concurrency
by dagba
'Expert guidance on Swift Concurrency best practices, patterns, and implementation. Use when developers mention: (1) Swift Concurrency, async/await, actors, or tasks, (2) "use Swift Concurrency" or "modern concurrency patterns", (3) migrating to Swift 6, (4) data races or thread safety issues, (5) refactoring closures to async/await, (6) @MainActor, Sendable, or actor isolation, (7) concurrent code architecture or performance optimization, (8) concurrency-related linter warnings (SwiftLint or similar; e.g. async_without_await, Sendable/actor isolation/MainActor lint).'
compounder
by vxcozy
Weekly review partner that compounds productivity gains over time. Tracks velocity, logs friction, sets next-week targets, recognizes patterns across weeks, and feeds insights back to the audit for the next loop. Use when you want a weekly review, need to identify friction, want to see patterns, or want to update your system map. Part of the architect-system loop. Outputs to system/compounder/week-{date}.md.
n8n-production-readiness
by RedcoatAsher
Dynamic tier system for right-sizing n8n workflow hardening. Use this skill on ANY n8n workflow request to determine appropriate validation, logging, and error handling levels. Adapts to user needs — from quick prototypes to mission-critical production systems.
super-skills
by clawdbot-skills
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills, and creates new skills when needed.
jj-workspace
by weegigs
Manage jj workspaces in a well-known location (~/.jj-workspaces) for parallel agent work. Use when spawning isolated work environments for beads tasks.
querying-logseq-data
by C0ntr0lledCha0s
Expert in building Datalog queries for Logseq DB graphs. Auto-invokes when users need help writing Logseq queries, understanding Datalog syntax, optimizing query performance, or working with the Datascript query engine. Covers advanced query patterns, pull syntax, aggregations, and DB-specific query techniques.
kosha
by thapakrish
Sanskrit vocabulary and lexicon skill covering word meanings, synonyms (paryaya), etymology (nirukta), gender, and technical terminology. Based on Amarakosha and traditional lexicography. Use when looking up Sanskrit word meanings, finding synonyms, explaining word derivations, identifying gender of nouns, or exploring vocabulary by category (gods, nature, body parts, etc.).
spawn-worker
by weegigs
Spawn headless Claude agents in isolated jj workspaces to work on beads tasks. Use when delegating tasks to parallel workers.
bringhurst-typography
by agrimsingh
Apply Bringhurst-style typography principles from The Elements of Typographic Style to editorial pages, web UI, product surfaces, reports, slides, and books. Use when Codex must design, review, or improve hierarchy, measure, leading, spacing, punctuation, typeface selection/pairing, page geometry, and print-or-screen production quality.
5d-tasks
by tapania
"Break gap analysis into sequenced, actionable tasks. Use when: (1) After GAP ANALYSIS phase in 5D-SDD workflow, (2) User is ready to start implementation, (3) Gaps are identified but not yet organized into work items, (4) User asks for 'task list,' 'breakdown,' or 'what to do first.' This phase creates the implementation roadmap."