Verification before completion

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

Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output.

jnMetaCode/superpowers-zh

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

Checks the quality of behavior evidence after each iteration in three tiers, using two auditor subagents in parallel to review the same work and find gaps.

prime-radiant-inc/iterative-development

Gives a fast single-pass quality verdict on any artifact, with a score from 0 to 1, PASS, REVISE or FAIL, and suggestions for what to change.

Q00/ouroboros

Builds the result.json file for a Nucleus V2 workflow run from its context, gates, blockers and step status, and exits non-zero when the run is blocked.

protect-my-hair/nucleus-marketplace

Acts as an independent checker for drafted release notes, comparing them with the scan data and returning an APPROVE, REVISE or ESCALATE_HUMAN verdict with evidence.

cobusgreyling/loop-engineering

Defines the agent roles, prompts and output schemas for a two-layer validation of a plan, ending in a PASS, CONDITIONAL or BLOCKED verdict.

withkynam/vibecode-pro-max-kit

Verifies and repairs a feature by using the real Peri terminal UI as a user would, looping verify, decide, fix and review until a fresh round shows no blockers.

KonghaYao/peri

Builds one working slice of a new project from the brief, runs the affected checks and the user journey, and reports what was and was not verified.

KhazP/vibe-coding-prompt-template

Works through the task files of a feature's implementation plan one at a time, with a TODO list and a verification step and commit for each task.

imbue-ai/bouncer

Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and Simon Willison's agent loop. Use when managing…

bybren-llc/safe-agentic-workflow

Pre-submit 自检——envelope 提交 commit gate 前必跑。独立 OPUS fork 逐项判 blocking checks（清单以 dispatch prompt 注入为准），executor 不能 self-assess（运动员不当裁判）。

Towow-ai/Flowness

Installs Reticle's dev-only SDK in a running web app and verifies user-facing changes by driving a real flow, returning a verdict with the file and line to fix.

reticlehq/reticle

Climbs a focused-to-broad set of verification rungs, from formatting checks to budget scripts CI enforces, so a Codewhale change is called done only with quoted command output behind it.

codewhale-hq/Codewhale

Runs a gated Spec, Plan, Build, Test, Review, Ship workflow so non-trivial changes are specified, verified and reviewed before they ship, with a named artifact per phase.

LichAmnesia/lich-skills

Run verification commands and confirm output before claiming success

bobmatnyc/claude-mpm

A skill your agent uses when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.

GanyuanRan/Aegis

Delivery pipeline from mission brief to verified change: writes a spec, splits it into tickets, runs them in parallel, verifies and reports a decision log after a repo audit gate.

Yeachan-Heo/oh-my-claudecode

Prepares a local self-review report for a System1-Agents change before a PR is opened, checking the full diff, tests, docs, artifacts and claims against evidence.

ThinkFlowLab/system1-agents

Takes an agreed task from intent to working code: splits it into units, implements the smallest correct change, verifies as it goes and reports what is left.

Yeachan-Heo/oh-my-claudecode

Vibe Coding 流水线的实现阶段(流水线终点,顺序 idea → interaction → architecture → design → prototype → implement)。当 interaction.md、architecture.md、design.md、prototypes/ 已就绪,用户说"开始实现""写代码""把设计落地""进入开发""implement /…

idiotLeoLYJ/Daliu-Awesome-Skills

Turns an already-planned ticket or spec into a checklist, builds it, and has a fresh verifier agent prove each check independently.

tech-leads-club/agent-skills

Splits substantial coding or repository-review work between a Sol commander that decides and verifies and a separate Luna Max worker that implements, with an auditable run log.

majiayu000/spellbook

Has the agent prove that a feature, fix or refactor works, using existing tests first, then narrow commands and manual checks, and report only what was actually verified.

Yeachan-Heo/oh-my-claudecode

Combines the evidence from completed Nucleus workflow steps into a final evidence report and result package, without scheduling steps, updating trackers or opening pull requests.

protect-my-hair/nucleus-marketplace

M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。

Towow-ai/Flowness

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

EvoScientist/EvoSkills

A skill your agent uses when about to claim a result, effect, significance, or that an analysis reproduces, before reporting or writing it up - requires running the analysis fresh and reading the…

K-Dense-AI/science-superpowers

Has a fresh-context adversary attack a blog post, recommendation, analysis brief or piece of code before you ship it, using a profile suited to that kind of artifact.

oaustegard/claude-skills

A skill your agent uses when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or…

Peiiii/nextclaw

Review a PR in this repo against the house conventions before it is marked ready.

portabletext/editor

About to say done, fixed, or passing?. An agent skill from christopherarter/superpowers-reasonix.

christopherarter/superpowers-reasonix

Protocolo de revisão editorial para eliminar AI slop em textos PT-BR e EN.

Hermes-brasil/hermes-brasil

Convention for building a reproducible demo artifact co-located with each implementation spec, so acceptance has something concrete to read.

goern/forgejo-mcp

Use before claiming work is complete, fixed, or passing — before committing, opening a PR, or handing off.

Archive228/loopkit

This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before submission", or mentions systematic paper quality…

brycewang-stanford/Auto-Empirical-Research-Skills

After writefile, re-read the deliverable (or ls + hexdump/line-print) and re-check the last format clauses before finishing.

ashutoshsinghpr7/wikiskill

Sets up eval-driven development for Claude Code workflows: capability and regression evals, three grader types and pass@k reliability metrics.

affaan-m/ECC

Adversarial self-review of your own conclusion, fix, or root-cause verdict before handoff — alternative causes, neighboring cases, blast radius, environment gap, hypothesis lock, subtraction, and a…

happier-dev/happier

A skill your agent uses when the operator needs DNS-Shop electronics data — search or a product card.

Vladimir-Human/ru-marketplace-mcp

Ghostwrite content in a specific person's voice from a VALIDATED voice profile — tweets, replies, short posts, launch copy, recruiting blurbs, emails.

garrytan/gbrain

Chorus Development workflow — claim tasks, report work, self-check acceptance criteria, and submit for verification.

Chorus-AIDLC/Chorus

Trigger this skill when a systematic review of an enterprise’s internal compliance management system is needed to identify gaps in policies, process defects, and data-privacy compliance risks.

THUYRan/Legal-Skills-Chinese