1.3K skills · sorted by relevance
Keep plans, research findings, and progress in Markdown files for multi-step work in Kiro. Read saved project records when resuming a task to recover goals, decisions, and recent actions.
Organize complex work into phases and save plans, findings, and progress in project files. Keep separate task records and, on supported hosts, automatically bring the selected plan back into the agent’s working context.
Use German-language guidance to organize multi-step agent work in Markdown files. Store plans, findings, and progress by task, then revisit those records to resume research, review decisions, and track unfinished phases.
Review game data and formulas for combat, economy, progression, or loot. Compare values with documented targets, identify dominant strategies and broken resource loops, and produce prioritized adjustment recommendations while clearly marking areas that lack enough data.
Run one NemoClaw maintainer pass focused on work for a target release. Select a ready pull request, small repair, security concern, or test gap, complete one outcome, and record progress and decisions requiring user input.
Deploy Model Garden models to Agent Platform endpoints, the addresses used for model requests. Check supported hardware and estimated hourly costs, inspect deployment progress, test predictions, and remove deployed resources after use.
Create and update OKRs in Lark: objectives and the key results used to measure them. Track numeric progress, record written updates, review relationships between objectives, and adjust their order, weights, deadlines, and comments.
Convert a Notion specification into a linked implementation plan and manageable tasks. Extract requirements and acceptance criteria, record uncertainties, and keep task statuses, checklists, blockers, and milestone updates aligned as the work progresses.
Design and implement command-line tools with subcommands, options, interactive prompts, and progress indicators. Get command structures, configuration handling, clear error messages, and shell completion scripts, with guidance for automated use and testing across operating systems.
Track shared work across AI agents using a SQLite database. The skill claims tasks, records progress and evidence for each step, skips completed work, and checks required procedures before marking a task complete.
View project statistics covering phase progress, plan execution, completed requirements, Git history, and the project timeline. Use the combined view to check how development is progressing across plans, requirements, and recorded changes.
Update an international expansion tracker with recent progress, new tasks, or changed deadlines. Identify work that can now start because earlier tasks are complete, flag overdue items, and show the next priorities with their owners.
Create a team OKR tracking page, showing objectives and their measurable results. Arrange three objectives with progress bars, values, owners, and status labels, alongside a quarterly summary that makes progress easy to review.
Turn feature requirements into a PRD, a document defining what to build, then organize development plans and GitHub Issues. Coordinate parallel agents and track progress, blockers, and next priorities through delivery.
Carry out an existing implementation plan one task at a time in the current session. Verify each task with tests, record progress and decisions in a file, and review the whole branch after implementation.
Manage OpenRig development work from setup to completion using shared specification, progress, and evidence files. Record what was actually checked and pass work to the next owner so handoffs and conversation compaction preserve the context.
Sets up AFL++ to test C/C++ programs with varied generated inputs, a technique called fuzzing. Covers running tests across CPU cores, monitoring progress, reducing input collections, and reproducing crashes for investigation.
Guide a workshop one question at a time with visible progress and clear answer options. The skill adapts to supplied context, handles interruptions and pauses, and closes with a summary of decisions and actionable choices.
Turn Notion product requirements and feature specifications into linked implementation plans and manageable tasks. Extract requirements, flag ambiguities, and keep task status, milestones, blockers, and decisions aligned as work progresses.
Inspect existing Boltz jobs, check local download progress, and recover results after an interrupted session. Use run names or job IDs to resume downloads into the existing output directory without starting a new job.
Build a burning-paper loading ring that keeps moving during heavy page setup. The skill covers background rendering, progress display, a smooth transition into the page, and support for reduced motion preferences.
Add a background blur that grows stronger toward the top or bottom of a webpage. Layered CSS masks control the transition, with snippets and guidance for adjusting height, blur strength, stacking order, and rendering cost.
Reviews authorized LoopX goals, tasks, and deliveries to explain project progress and identify decisions the owner needs to make. It also guides handoffs to suitable agents while preserving the original objective, constraints, and evidence.
Investigate unexpected LoopX behavior, such as stalled progress or conflicting next steps. Identify whether agent decisions, state reporting, or workflow rules caused the problem, then repair, validate, and record the correction.