replay-ux-audit
Finds and analyzes Amplitude Session Replays to surface UX friction patterns across multiple sessions. Produces a ranked friction map showing where users…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-19 00:15
53,933 results
Finds and analyzes Amplitude Session Replays to surface UX friction patterns across multiple sessions. Produces a ranked friction map showing where users…
Delivers a weekly briefing summarizing the most important trends, wins, and risks across your Amplitude instance. Use when the user asks for a "weekly review",…
Drive a feature's pending phases unattended via ralph-loop, gated by /dev-judge. Composes /dev-resume, /dev-checkpoint, and /dev-judge into a self-referential…
Create semantic version releases with auto-generated changelogs based on conventional commits
Review an open GitHub Pull Request, analyze changes against relevant .github/instructions, and post structured review comments directly on the PR.
Improve a Bumble dating profile through research-backed screenshot audits, photo selection and ordering, conversational discovery, bio and prompt writing,…
This skill should be used when the user asks to "brainstorm a production Effect Schema", "model a domain with Effect Schema", "iterate on real schemas using…
Autonomous night mode — user is away. Each /loop tick runs coordinator-yolo for ONE task through the regular /team, inside an isolated yolo branch. Never main,…
Go concurrency mastery — goroutines, channels, context, sync primitives, patterns, performance.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's…
Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size,…
Edit the target skill's actual files for every finding confirmed by adaptogen-critique's evidence gate, reading each edit back to confirm it landed. Also the…
Instructions only skill
Keep a project's shared knowledge where the second reader can reach it: a glossary with one term per concept and the words to avoid, decision records for…
Calibrate every claim before it leaves the session: tag each factual clause Verified, Measured, Inferred or Planned, verify behaviour at the production sha,…
Write deliverables the way a senior engineer types in a team channel: the decision first, plain declaratives, current state only, open points left open, misses…
Review a change the way a reviewer who will be held to it does: findings only on the change that introduced the code, verified at its head sha, one finding per…
Land work as thin, complete, reviewable slices: one pull request per plan step, nothing half-done on the shared branch, scope held to the step, verification…
Audit or write models.dev reasoning_options in provider TOML files and reasoning-option PRs. Use when verifying toggle, effort, budget_tokens, provider…
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a…
Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher…
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints…
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai,…
Sets the criticality tier of a single third-party arrangement and ties it to the firm's important business service, recovery time and recovery point…