Back to categories
Category

Agent Skills in category: Uncategorized

72294 skills match this category. Browse curated collections and explore related Agent Skills.

hive.quality-monitor

Periodically self-assess output quality to catch degradation before the judge does.

hive
hive
10,0065,605

hive.task-decomposition

Decompose complex tasks into explicit subtasks before diving in.

hive
hive
10,0065,605

ai-review-validator

Autonomously validate and execute AI Review suggestions from PR comments. Use when users provide AI Review comments (from GitHub Copilot, CodeRabbit, etc.) that suggest code changes, API migrations, or fixes. The skill verifies suggestions against official docs, tests compilation, calculates confidence scores, and auto-applies changes when verified. Triggers on phrases like "verify this AI Review", "apply this suggestion", "validate AI Review comment", or when users paste AI Review URLs/content.

mkdir700
mkdir700
3

archive-and-cleanup-vibe-docs

>

mkdir700
mkdir700
3

codex-plan-reviewer

Cross-model adversarial review loop for markdown plans. Use this skill whenever the user asks to review, validate, or stress-test a markdown plan file using Codex (OpenAI). Triggers on phrases like "review this plan with codex", "let codex check the plan", "adversarial review", "cross-model review", "codex audit", "validate plan", or when the user has a markdown plan and wants a second opinion from a different AI model. Also trigger when the user says "plan review loop", "codex review loop", or references having Codex critique a plan before execution.

mkdir700
mkdir700
3

project-onboarding

Rapidly understand unfamiliar codebases through structured analysis. Use when the user needs to understand a new project, especially poorly documented or non-standard code. Triggers include "help me understand this project", "analyze this codebase", "onboard me to [project]", "what does this project do", or when the user provides a project path for exploration. Particularly effective for legacy code, hack projects, and codebases lacking documentation.

mkdir700
mkdir700
3

justfile

Use when writing Justfiles to understand the latest syntax, features, and best practices

iloveitaly
iloveitaly
0

obra-writing-plans

Use when the user asks for a plan, roadmap, or step-by-step breakdown for a multi-step task in VS Code Copilot Agent mode.

faulkdev
faulkdev
32

obra-writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

faulkdev
faulkdev
32

investigation-mode

DEPRECATED: See systematic-debugging for current implementation.

faulkdev
faulkdev
32

minimalist-surgical-development

Use when editing an existing codebase and the goal is minimal, standard, and non-invasive changes - prioritizes simplest solution, standard libraries first, and surgical modification without unsolicited refactors

faulkdev
faulkdev
32

obra-brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

faulkdev
faulkdev
32

obra-dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

faulkdev
faulkdev
32

obra-executing-plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

faulkdev
faulkdev
32

obra-finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

faulkdev
faulkdev
32

obra-receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

faulkdev
faulkdev
32

obra-requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

faulkdev
faulkdev
32

obra-subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

faulkdev
faulkdev
32

obra-systematic-debugging

Use when errors are unclear, flaky, or regressions occur; apply a disciplined debugging loop in VS Code Copilot Agent mode.

faulkdev
faulkdev
32

obra-test-driven-development

Use when implementing new behavior or fixing bugs via tests-first (TDD) in VS Code Copilot Agent mode.

faulkdev
faulkdev
32

obra-using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

faulkdev
faulkdev
32

obra-using-superpowers

Use when working in VS Code Copilot Agent mode and you want the Superpowers workflow (plans, verification, debugging, TDD) applied consistently.

faulkdev
faulkdev
32

obra-verification-before-completion

Use before finalizing answers or PRs: confirm requirements met, run checks, and avoid “looks good” without evidence in VS Code Copilot Agent mode.

faulkdev
faulkdev
32

root-cause-tracing

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

faulkdev
faulkdev
32

systematic-debugging

Use when errors are unclear, flaky, or regressions occur; apply a disciplined debugging loop in VS Code Copilot Agent mode.

faulkdev
faulkdev
32

task-direction-approval

Use when considering switching libraries/tools, changing architecture, or replacing automation with manual workarounds - explains root cause, offers 2-3 options with trade-offs, and requests explicit user choice

faulkdev
faulkdev
32

uncertainty-verification

Use when providing exact commands, flags, config keys, file paths, API details, standards, or version-specific behavior - enforces verification via official docs (Context7/web fetch), explicit citations, and bans assumption-based specifics

faulkdev
faulkdev
32

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

faulkdev
faulkdev
32

pfp-animate

Generate animated videos from static profile pictures using AI. Use when users want to animate images, create PFP videos, make meme videos, or turn portraits into short clips. Supports video with generated audio, lip-sync to existing audio, and precise keyframe control.

velinussage
velinussage
0

specify

Create a comprehensive specification from a brief description. Manages specification workflow including directory creation, README tracking, and phase transitions.

rsmdt
rsmdt
24330

analyze

Discover and document business rules, technical patterns, and system interfaces through iterative analysis

rsmdt
rsmdt
24330

brainstorm

You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation.

rsmdt
rsmdt
24330

constitution

Create or update a project constitution with governance rules. Uses discovery-based approach to generate project-specific rules.

rsmdt
rsmdt
24330

debug

Systematically diagnose and resolve bugs through conversational investigation and root cause analysis

rsmdt
rsmdt
24330

document

Generate and maintain documentation for code, APIs, and project components

rsmdt
rsmdt
24330

implement

Executes the implementation plan from a specification. Loops through plan phases, delegates tasks to specialists, updates phase status on completion. Supports resuming from partially-completed plans.

rsmdt
rsmdt
24330

refactor

Refactor, simplify, or clean up code for improved maintainability without changing business logic

rsmdt
rsmdt
24330

review

Multi-agent code review with specialized perspectives (security, performance, patterns, simplification, tests)

rsmdt
rsmdt
24330

specify-meta

Scaffold, status-check, and manage specification directories. Handles auto-incrementing IDs, README tracking, phase transitions, and decision logging in .start/specs/. Falls back to docs/specs/ for legacy specs. Used by both specify and implement workflows.

rsmdt
rsmdt
24330

specify-plan

Create and validate implementation plans (PLAN). Use when planning implementation phases, defining tasks, sequencing work, analyzing dependencies, or working on plan files in .start/specs/. Generates per-phase files (plan/README.md + plan/phase-N.md) for progressive disclosure. Includes TDD phase structure and specification compliance gates.

rsmdt
rsmdt
24330

specify-requirements

Create and validate product requirements documents (PRD). Use when writing requirements, defining user stories, specifying acceptance criteria, analyzing user needs, or working on requirements.md files in .start/specs/. Includes validation checklist, iterative cycle pattern, and multi-angle review process.

rsmdt
rsmdt
24330

specify-solution

Create and validate solution design documents (SDD). Use when designing architecture, defining interfaces, documenting technical decisions, analyzing system components, or working on solution.md files in .start/specs/. Includes validation checklist, consistency verification, and overlap detection.

rsmdt
rsmdt
24330

test

Use when completing implementation, fixing bugs, refactoring code, or any time you need to verify the test suite passes. Also use when tests fail and you hear "pre-existing" or "not my changes" — enforces strict code ownership. Ensures MECE coverage (no overlap, no gaps) and that ALL test categories including E2E are executed.

rsmdt
rsmdt
24330

validate

Validate specifications, implementations, constitution compliance, or understanding. Includes spec quality checks, drift detection, and constitution enforcement.

rsmdt
rsmdt
24330

writing-skills

Use when creating new skills, editing existing skills, auditing skill quality, converting skills to markdown conventions, or verifying skills before deployment. Triggers include skill authoring requests, skill review needs, or "the skill doesn't work" complaints.

rsmdt
rsmdt
24330

feature-prioritization

RICE, MoSCoW, Kano, and value-effort prioritization frameworks with scoring methodologies and decision documentation. Use when prioritizing features, evaluating competing initiatives, creating roadmaps, or making build vs defer decisions.

rsmdt
rsmdt
24330

pattern-detection

Identify existing codebase patterns (naming conventions, architectural patterns, testing patterns) to maintain consistency. Use when generating code, reviewing changes, or understanding established practices.

rsmdt
rsmdt
24330

project-discovery

Unified codebase discovery across structure navigation, tech-stack detection, and documentation extraction. Use when onboarding to a project, locating implementation paths, identifying frameworks/tooling, or validating docs against code reality.

rsmdt
rsmdt
24330

requirements-elicitation

Requirement gathering techniques, stakeholder analysis, user story patterns, and specification validation. Use when clarifying vague requirements, resolving conflicting needs, documenting specifications, or validating requirements with stakeholders.

rsmdt
rsmdt
24330

user-research

User research and insight synthesis for interviews, usability testing, personas, journey mapping, and actionable product/design recommendations. Use when planning studies, collecting evidence, synthesizing patterns, or converting findings into prioritized decisions.

rsmdt
rsmdt
24330

Page 422 of 1446 · 72294 results