Engineering
abvx-agent-skills
Auditable cross-platform coding-agent skillpack for smaller diffs, evidence-led debugging, token control, browser verification, and reviewable `SKILL.md` workflows with static secu…
Productivity
Pm Requirement Review Simulator
PRD review stress-test simulator: 5 cross-functional roles challenge your requirements and outputs a scored HTML or Markdown survival report with radar chart...
Research
paper-agent
Full academic manuscript skill for quantitative-science papers, currently calibrated for hydrology and water-resources (Hydrogeology Journal, JHRS) and extensible to other quantita…
Engineering
staged-spec-review
Review one stage of a multi-stage specification against the full plan to catch forward-compatibility gaps before they compound. Use whenever the user asks for a review of a single …
Productivity
skill-reviewer
Skill 质量审查与规范脚手架。审查 Claude/Cursor Agent Skill 是否符合高质量规范（渐进式加载、description 关键词、工作流 checklist、确认节点、脚本封装、参数系统、references 组织、Pre-Delivery、CLI+Skill 模式、反 Slop），并按 P0–P3 分级输出报告；也能 --temp…
Content
courseware-review-beta
Experimental beta of courseware-review with full optimizations: tail-read via APPEND_HERE anchor, three-terminal-state interaction (A/B/C), model-aware image budgets, XL path for l…
Productivity
darwin-skill
Use when the user wants to evaluate, score, review, or automatically improve an existing Claude Code skill (a SKILL.md) — e.g. \"optimize this skill\", \"score my skill\", \"review…
Engineering
claude-code-agents
Invoke Claude Code from Codex for bounded delegation to Claude Code agents or subagents. Use when the user explicitly asks to run, invoke, compare with, or delegate work to Claude …
Engineering
brutal-agent
Orchestrate subsystem-by-subsystem project hardening by combining brutal-project-review and task-worker in a strict loop: review one subsystem, create CRITICAL/MAJOR tasks, run all…
Productivity
pm-prd-drafter
Draft or critique a PRD against the repo's PRD template and problem-framing rubric. Use when starting a PRD, sharing a draft for review, or stuck on a section such as problem state…
Documentation
akteneinsicht-auswerten
Systematically reviews received administrative or court files: chronological examination, identification of key documents (applications, decisions, objections, medical reports, exp…
Engineering
pr-review-respond
Respond to all code review comments on a pull request, implement fixes, run tests, commit, reply on GitHub (in Chinese), and resolve conversations. Supports multi-round review loop…
Security
security-focused-review
Scoped security review establishing assets, trust boundaries, and attacker prerequisites with evidence-backed findings across auth, authorization, validation, injection, path handl…
Engineering
cross-review
Run a cross-review using the opposite CLI reviewer for proposal review and change assessment. Use when the user asks for cross review, 交叉 review, 交叉评审, second-opinion review, Codex…
Business
pm-red-team
Adversarially re-review a PM artifact, recommendation, or AI-generated critique that already exists. Use as a second pass after another skill has produced output, or on any externa…
Security
data-flow-review
Expert review pass examining data-flow, state ownership, lifetime, and boundary topology across every non-trivial entity—flagging ownership mismatches, incorrect dependency directi…
Business
coi-compliance-review
Reviews CRE insurance certificates (ACORD 25) and endorsements against Access Agreement insurance requirements, producing a pass/fail compliance determination with broker-ready def…
Engineering
codex
Review code changes, implementation plans, or specific files using OpenAI Codex CLI. Triggers on "review", "check", "validate", "codex". Perfect for maker-checker workflows where y…
Productivity
pm-metrics-critic
Critiques a metrics dashboard, success-criteria section, or proposed North Star metric against the repo's metrics guide. Surfaces common failures: aggregate metrics hiding segment …
Productivity
grill
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree, and then implementing the plan in reviewable…
Productivity
rz-quarterly-review
Triggers on first Sunday of January/April/July/October or explicit quarterly review commands. Runs an 80-100 minute process: pulls metrics, re-scores channels on a 5-criteria frame…
AI / ML
superthink
IPC-based multi-agent review via Crispy's internal dispatch. Dispatches parallel child sessions (claude + codex by default) through the running Crispy host — no subprocess spawning…
Engineering
kitty-review
Delivers structured code reviews powered by distributed reviewer swarms. Trigger manually when code needs inspection or before Pull Request submission. Inline-first analysis identi…
Documentation
kr-patent-consistency-check
Reviews Korean patent specifications, drawings, and claims for consistency. Checks claim-to-drawing numeric alignment, symbol mapping, text-to-drawing concordance, guideline violat…
Productivity
utility-pm-critic
Runs adversarial review on a PM artifact via the pm-critic sub-agent. Dispatches natively on Claude Code with the pm-skills plugin; on other clients reads agents/pm-critic.md and e…
Data
analytical-self-review
Final analytical gate: runs after sensitivity and multiverse checks, before any summary or finding. Scans for Simpson's paradox, base-rate fallacy, leakage, p-hacking, ecological f…
Productivity
grill-me-codex
Two-phase review workflow: first, an agent interviews you question-by-question to harden a plan or design until all branches are resolved; second, it writes the plan to PLAN.md and…
DevOps
ai-sdlc-quality-lenses
Applies structured quality lenses—pre-mortem, adversarial, edge-case, stakeholder, reversibility, abuse-case, operational-failure—to challenge requirements, designs, plans, tests, …
DevOps
ai-sdlc-evidence-council
Orchestrates multi-perspective AI reviews of high-impact topics, running simulated or independent reviewer executions to surface evidence-backed agreements, conflicts, proposals, o…
Research
verificacao-artigo
Adversarial multi-layer review for psychology papers: runs Semantic Scholar checks, universal criteria, domain-specific analysis, Reviewer 2 critique, and Devil's Advocate stress-t…
Productivity
notifications-review
Reviews GitHub notifications by pulling pre-classified items from a local gh-notify server, cross-referencing them with tasks in private/state.json, and suggesting next actions lik…
Research
paper-sprint-review
Scrum-inspired paper review, revision, and R&R workflow. Handles docx/tex/md/PDF in English or Chinese. Auto-detects manuscript stage, estimates sprint count, runs multi-lens revie…
Engineering
prepare-branch-context
Use when starting work on a branch and needing full context before answering questions, reviewing code, or implementing changes. Analyzes the diff from the base branch, commit hist…
Productivity
grill-with-docs-codex
Two-act plan hardening: first, an agent interviews you question-by-question against your domain model and glossary, sharpening terms and updating living docs; second, it writes the…
Content
通用-审阅人物传记
Reviews character biographies for identity, motivation, capability boundaries, relationships, psychological arcs, and index mapping. Outputs structured, reusable review reports wit…
Engineering
pr-war-stories
Activate when the user wants to teach their AI code reviewer from PR history, set up Cursor Bugbot rules (.cursor/BUGBOT.md), harvest review comments into review rules, or audit ex…
Engineering
ai-sdlc-requirements-readiness-review
Runs a final quality review on PRFAQ and BRD artifacts to surface gaps, contradictions, and readiness gaps before design begins. Supports quick assumption-driven or full question-d…
Productivity
windags-looking-back
Applies Polya's four questions after WinDAGs execution. Q1 and Q2 run on every DAG; Q3 and Q4 trigger only on quality and cost thresholds, asynchronously, without delaying delivery…
Engineering
dotnet-csharp-runtime-review
Reviews C# code for runtime correctness including nullable references, async patterns, disposal, allocations, LINQ usage, and AOT/trim safety. Accepts source or project files and i…
Research
referee2
Performs systematic audit and review in two modes: deck reviews for rhetoric, visual quality, and compile cleanliness; code reviews for cross-language replication and econometric a…
Engineering
psep
Practical Software Engineering Principles for architecture, design, review, and refactoring. Offers strict mode with seven principles plus decision framework, or relaxed mode with …
Engineering
tk-grill
Grills any plan, design, or architectural decision through relentless, one-branch-at-a-time questioning until shared understanding is reached, then emits a logged DEC-NNN entry. Us…
Engineering
salesforce-flow-automation-review-skill
Reviews Salesforce Flow XML, validation rules, approval processes, and record-triggered automations for correctness, safety, and maintainability. Detects recursion, unsafe bypasses…
Engineering
hv-review
Staff-engineer review of a feature branch before merge or PR — reads commits, diff, referenced item IDs, and matching knowledge topics; checks intent match, convention compliance, …
Automation
ralph-lisa-loop
Orchestrates plan-implement loops with expert review via subagents for planning, implementation, and self-review, plus external review. Human steers; a single knob tunes interrupti…
Productivity
tickets-review-loop
Runs a deterministic pre-dispatch review over every pending ticket: executes five specialized audits (slicing, dependencies, granularity, acceptance criteria, coverage) plus a hard…
Productivity
overnight-review-client-delivery
Runs an overnight autonomous session to generate a polished client delivery package by morning, using a parallel multi-agent review panel to catch errors before hand-off. Fits boun…
Engineering
backend-slop-audit
Post-generation audit for backend code that scans changesets against a catalogue of anti-patterns—swallowed errors, unvalidated input, missing timeouts, N+1 queries, unparameterize…
Productivity
pm-launch-reviewer
Reviews a launch plan against the repo's launch-criteria template and failure-management playbook. Surfaces missing gates, unowned criteria, vague readiness bars, and likely post-l…
Testing
review-gauntlet
Self-looping adversarial review pipeline that isolates topics, verifies findings, and gates each PR through dual independent SATISFIED verdicts plus CI before auto-merge. Supports …
Engineering
forge-fix
Fix rejected issues based on review or QA feedback. Reads rejection comments, applies scoped fixes, builds, re-tests, and pushes. Triggers on reopened issues, review feedback, QA f…
Security
library-fitness-review
Triggers a full-library fitness review using ten independent reviewer personas when governance or security docs undergo major changes or on a quarterly schedule. Surfaces prioritiz…
AI / ML
self-improvement-loop
Self-improving orchestrator that runs periodic cross-project reviews, identifies root causes, creates improvement issues, and executes them end-to-end. Operates in discovery mode f…
Productivity
minutes-weekly
Weekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week. Use when the user says weekly review, what happened this week, week…
DevOps
pr-cycle-deep
Multi-model PR lifecycle: auto-detects external LLMs and runs independent reviews, cross-model debate, aggregation, iterative fixes until unanimous LGTM, then human check, CI, merg…
Security
safety-review
Reviews code changes for functional safety impacts including e-stop logic, watchdog timers, actuator constraints, geofencing, tilt protection, and communication timeouts. Focuses o…
Engineering
delegate-review
Delegates code and documentation reviews for large diffs or multi-file changes to a specialized subagent, isolating context to reduce main agent load. Use only for substantive revi…
Productivity
discussion-review
Executes adversarial team-based discussion reviews using named agents, message passing, and shared whiteboards. Invoked on explicit requests for team discussion reviews or via auto…
Automation
judge-assignment
Assigns judges to project groups by matching expertise and balancing internal/external affiliations. Reads two Excel files (experts and groups), applies discipline and affiliation …
Research
reading-review
Reviews a reading curriculum chunk by demonstrating comprehension against primary text, updating the graph on contradictions or confirmations, then marks completion to retire the e…
Showing the top 60 of 2,013. See the full list →