Best verification before completion skills, page 2

Carries out an approved plan for an agtx-managed task: implements the changes, runs tests, commits, writes a summary to .agtx/execute.md and then stops.

fynnfluegge/agtx

A skill your agent uses when reviewing a conformance PR that adds or changes scenario .ts files for a SEP — before approving, before requesting changes, or as a self-check before opening one.

modelcontextprotocol/conformance

Generates a project-local skill that launches your app, exercises a feature the way a user would and captures evidence, for web, CLI, API or desktop projects.

cursor/plugins

Has the agent build, test and lint a change, re-read the request and check for regressions before it says a coding task is done, then report exactly what it ran.

duckbugio/flock

Runs a pass, revise or block acceptance review on lo2cin4bt work, checking a deliverable against the request, repo contracts, tests, docs and the public GitHub boundary.

lo2cin4/lo2cin4bt

Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

sickn33/agentic-awesome-skills

An instruction-only discipline for Trae that forces evidence-based work when an agent keeps failing, gives up or declares a task finished without proof.

tanweai/pua

Reconciles documentation with code at the end of a change or as a periodic audit, following a repo rule that code changes and doc changes land in one commit.

fancyboi999/open-tag

Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human.

cobusgreyling/loop-engineering

Finds what a code change could break outside its diff and proves the single fact that makes it safe by running real code instead of writing an explanation.

cursor/plugins

Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing.

CamusGIT/EvoQuant

Takes over one selected project on request, reports progress in a fixed Chinese-language format, and runs bounded reviews, handoffs and verifications from explicit sources.

adand-91/gpt-6-astra-skill

Designs a step-by-step playbook for large or unfamiliar work, runs it as a loop of hypotheses and measurements, and logs decisions so a human can review them later.

cursor/plugins

Audits a project's verification skill and its feature map against the source and the live app, then ships at most one pull request of proven corrections.

cursor/plugins

Create distinctive, production-grade frontend interfaces with high design quality and accessible markup.

spinspire/pocketbase-sveltekit-starter

Chooses how much validation a TiDB change needs: scoped checks while iterating, required checks at delivery, and expensive runs only when explicitly needed.

pingcap/tidb

A workflow for Google Cloud changes: pick gcloud, bq or gsutil, check the command against official docs, preview with a dry run and ask for approval before executing.

rominirani/antigravity-skills

A step-by-step workflow for changing the CodFlow repository: read the AGENTS.md contract, respect package boundaries, verify before claiming done and keep PRs small.

bighadj22/codflow

Plans and runs material repository changes with the AI SAFE2 method: classify delivery shape and risk, isolate the work, collect test evidence and finish with a completion receipt.

CyberStrategyInstitute/ai-safe2-framework

Collects prior Nucleus task evidence into a candidate-only delivery closure package and PR/MR draft text, blocking if any feature's design, review or verification evidence is missing.

protect-my-hair/nucleus-marketplace

The opencode binding of the AutoMCM-Pro math modeling pipeline for CUMCM and MCM/ICM contests, with tool mappings, install prompts and checkpointed runs.

RealSeaberry/AutoMCM-Pro

A Japanese-language prompt that scolds the agent like a harsh manager to stop it giving up, and pushes it to investigate, verify and finish tasks end to end.

tanweai/pua

Runs Warp's terminal UI for real, drives it with keystrokes and reads the rendered screen back to confirm that a change looks and behaves as intended.

warpdotdev/warp

Runs an autonomous loop that extracts requirements with proof obligations, builds a walking skeleton, then audits sprint by sprint against real behavior evidence.

prime-radiant-inc/iterative-development

Pre-PR code review gate. An agent skill from ByteDance-Seed/VeOmni.

ByteDance-Seed/VeOmni

Runs an iterative verification loop on Google Antigravity: make one edit, run a test command, and reschedule until the command passes or the iteration budget runs out.

jtaroreh/agystack

Structured code review family for explicit heavy review requests and architecture-sensitive review/evaluation requests.

HorizonRobotics/RoboOrchardLab

Compact version of the PUA persona skill that pushes an agent to act like a high-ownership engineer, with level roles, extra-work markers and corporate-style commentary.

tanweai/pua

Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff.

majiayu000/spellbook

Three rules for multi-step work with DeepSeek V4 thinking models: verify references, use a verifier subagent before big edits, and write plans with exact path and line.

codewhale-hq/Codewhale

Runs a long task as a checkpointed goal loop: it creates goals, mirrors each step into a todo list, gathers evidence per criterion and lands every goal before the next.

code-yeongyu/oh-my-openagent

Plans and implements a feature through four phases, specify, design, tasks and execute, with testable requirements, atomic commits and a separate verifier checking the work.

tech-leads-club/agent-skills

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or…

wshobson/agents

Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

HKUDS/OpenSpace

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and…

JuliusBrussee/caveman

Works through a plan file task by task, updating each task's status inside the file, then re-reads it at the end to confirm nothing was left undone.

tailcallhq/forgecode

Executes a phased implementation plan by acting as an orchestrator that hands each step to subagents, verifies the results and commits only after verification passes.

thedotmack/claude-mem

Sets the rules for a worker agent spawned by a boss mission: stay in scope, verify before finishing, report blockers quickly and end with a clear status.

Th0rgal/sandboxed.sh

Teaches staged, verifiable coding habits for multi-file tasks and ships a hook that blocks tests from touching live data.

assafkip/kipi-system

Runs a light task loop where each goal criterion passes only when a real evidence artifact exists, with progress stored in a `.superloopy` folder.

beefiker/superloopy

Headless self-verification gate a Foreman worker runs before it claims an issue is done.

VisionForge-OU/foreman

Runs OpenWork's agent-first test specs one at a time, locally or on Daytona, and records exact results, skips and runtime mismatches instead of reporting a loose pass.

different-ai/openwork

Carries out a plan, spec or clear build request end to end with local verification, then hands off to shipping or returns a structured result to a caller.

EveryInc/compound-engineering-plugin

Proves a RuView result is real by running a deterministic SHA-256 proof and a witness bundle, and by checking reports for untagged or unreproducible accuracy claims.

ruvnet/RuView

Structured work modes for agent sessions. An agent skill from 0xNyk/lacp.

0xNyk/lacp

Compares a finished feature with its plan, the project's architecture and design rules, and production-readiness checks, then reports issues without fixing them.

jsmastery-pro/jsm-agent-skill

Teaches an agent on MiniMax M3 to ground visual claims in attached images, screenshots, mockups and clips, and to re-read results after a visual change.

madebyaris/advance-minimax-m3-cursor-rules

Turns a vague intention into a /goal objective with one outcome, numbered yes-or-no checks, guardrails, a budget and a block protocol, without starting the work.

QwenLM/qwen-code