github-release-notes-writer
Draft or update user-focused GitHub Release Notes from verified tags, commits, pull requests, existing releases, and supplied changelog baselines. Use when…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-16 00:04
53,864 results
Draft or update user-focused GitHub Release Notes from verified tags, commits, pull requests, existing releases, and supplied changelog baselines. Use when…
Clean up stale git worktrees with merged branch detection and disk usage report
Create a letter-from-future planning artifact for startup, product, roadmap, pivot, project kickoff, quarterly planning, or stakeholder alignment. Use when…
Diagnose and improve a landing page, funnel, campaign, ad, message, content asset, or outreach flow. Use for conversion audits, teardown requests, campaign or…
Explicitly route one task through discovered models for frontier planning, workhorse execution, and independent frontier review.
Execute Grimoire spells inside an agent session (VM mode). Use for in-agent prototyping, validation, and best-effort execution.
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning…
Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive…
Intelligent assistant for generating daily/weekly/monthly workplace reports. It automatically transforms fragmented information such as scattered work records, meeting notes, and chat logs into clearly structured, results-oriented professional reporting documents. It supports three modes: daily, weekly, and monthly reports, and includes a built-in OKR logic restructuring engine that automatically identifies core outputs and routine maintenance to ensure report content highlights the key points. Applicable scenarios: daily work reports, weekly progress syncs, and monthly/quarterly review summaries.…
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through…
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal…
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through…
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's…
Implement and review Kotlin structured concurrency with suspend functions, CoroutineScope, dispatchers, Flow, channels, cancellation, timeouts, supervision,…
Implement and diagnose stable Swift language semantics including value and reference types, optionals, generics, protocols, existentials, ownership, access…
Use when sending Slack alerts or notifications. Automatically uses the configured SLACK_WEBHOOK_URL from environment.
Repo-wide documentation sweep for updating project docs, context, ADRs, diagrams, README files, agent instructions, and documentation sites after feature work,…
Create and update an evidence-based hackathon.md build log for a Convex project. Use when a user invokes $convex-hackathon-skill, /convex-hackathon-skill, or…
The introduction is being prepared. Please check back soon.
Configure the OpenTelemetry Collector with Sentry Exporter for multi-project routing and automatic project creation. Use when setting up OTel with Sentry,…
Setup Sentry Logging in any project. Use this when asked to add Sentry logs, enable structured logging, setup console log capture, or integrate logging with…
Invoked by /trim-language. Reviews project text for cuttable prose — redundancy, over-explanation, throat-clearing, and filler — and produces a checklist of…
Give a launch, hold, or report verdict on a built eval, benchmark, judge, harness, or scoring change, or on a result before it informs a decision or reaches a…