716 skills · sorted by relevance
Clarify an unclear request through one question at a time, with the agent sharing its best guess for each answer. Produce a user-confirmed statement covering the desired outcome, audience, timing, success criteria, constraints, and exclusions.
Review another agent’s recent work records to identify recurring problems and propose small changes to instructions, skills, or tool descriptions. Produce evidence-backed drafts and reviewable diffs, checking that proposed rules would preserve successful outcomes from past tasks.
Create acceptance criteria and a manual validation plan for feature changes. Cover successful flows, unusual inputs, failures, and performance limits, with observable outcomes and clear evidence requirements so reviewers can decide whether each criterion passes.
Read email linked to assigned Paperclip tasks, send new messages or replies through an assigned AgentMail inbox, and check delivery outcomes. Follow task permissions and preserve retry identifiers to avoid duplicate sends.
Turn product requirements, roadmaps, architecture reviews, and retrospectives into HTML slides for decision-making. Choose one of eight visual themes to create a consistent, horizontally navigable deck, using source evidence and real numbers to support review.
Turn notes and analysis into HTML slide decks for client recommendations, technical talks, or reports. Choose from themes and layouts, add speaker scripts and animations, and export slides as PNG images using the supplied rendering script.
Create an HTML year-end self-review deck for a product manager, organizing responsibilities, results, lessons, and requests around supporting evidence. The template uses rounded cards and pastel colors to present the case to managers or review committees.
Review a design against Dieter Rams' ten principles using evidence from code, screenshots, copy, and measurements. Receive a scorecard, a verdict on whether to create, refine, or redesign, and a prompt for planning the next steps.
Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.
Group AI providers and models behind one model ID in OmniRoute. Choose among 19 routing strategies, define fallback sequences for failures, simulate which provider will be selected, and inspect latency, success rates, and costs.
Run scoped quality checks without changing product code. Record the exact revision, commands, logs, and outcomes, then report failures, incomplete checks, and existing unresolved issues to support reviews or release preparation.
Turn complex goals into actionable steps by examining requirements, expected effects, and costs. Build a path from the current situation to the desired outcome, then revise the plan when actions fail or conditions change.
Run saved workflows and check their progress, with controls to pause, resume, or cancel execution. Also run JavaScript workflows that coordinate multiple agents and resume them using a recorded run ID.
Turn a complex goal into an executable plan by checking each action’s requirements, expected results, and estimated effort. Tracks dependent tasks, verifies outcomes, and revises the remaining plan when conditions change or actions fail.
Apply simple code changes across files without calling an LLM, using agent-booster's local transformation engine. The skill checks a confidence score before saving results and records outcomes for cost tracking and future routing decisions.
Manage code changes across multiple AI agents and record their operations and outcomes. Use those records to find successful patterns, review past failures, and get suggestions for similar development or deployment tasks.
Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.
Audit conflicting search indexing settings across robots.txt, noindex directives, and canonical tags that identify preferred URLs. Identify why pages may be included or excluded unexpectedly, and review changes that align the settings with the intended outcome.
Guides coding work from planning and implementation through checks on actual screens, commands, or APIs. It adjusts verification to the change’s risk and records evidence, decisions, and cleanup so completion can be assessed against the requested outcome.
Coordinate child agents on tasks that must happen in a particular order. Define dependencies, pass results through handoff files, verify the outcome, and recover individual failed tasks while reusing work that has already finished.
Discover what a paired phone or wearable currently supports, then run the requested device, app, camera, media, or smart-home action. Check each device's published capabilities and permissions, and report the actual outcome or any execution errors.
Guide test writing, updates, and reviews in Remotion by checking observable user outcomes. Choose integration, unit, visual, or end-to-end tests that detect broken workflows, and verify that bug fixes address the original regression.
Find marketing ideas for a SaaS or software product based on its stage, audience, budget, and team. Draw from 139 ideas to shortlist relevant options, with starting steps, expected outcomes, and resources needed.
Plan creator partnerships from partner selection and compensation to content briefs, sponsorship disclosures, and performance measurement. The skill covers one-off sponsorships and ongoing ambassador programs, focusing on audience fit and qualified outcomes such as leads or purchases.