agentsclimarketplace

Review & quality

19,169 rows, by stacks then stars

1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid

  • Feature development

    wchen02/cursor-agent-learning/.cursor/skills/feature-development Skill

    no license3★ repo

    Implements a feature using plan → implement → verify. Use when the user wants to add a new feature with a clear plan and verification.

  • Pr

    skrrt-sh/skills/skills/ship/pr Skill

    3★ repo

    Push a branch and open or update its GitHub pull request or GitLab merge request. Use when the user asks to open a PR, or to create or update a merge request.

  • Grill me

    b-mendoza/agent-skills/.agents/skills/grill-me Skill

    no license3★ repo

    A relentless interview to sharpen a plan or design.

    The same file is in 19 other repositories

  • Pr creator

    b-mendoza/agent-skills/skills/pr-creator Skill

    no license3★ repo

    A collection of reusable skills for AI-assisted development workflows

    The same file is in 2 other repositories

  • Receiving code review

    b-mendoza/agent-skills/.agents/skills/receiving-code-review Skill

    no license3★ repo

    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

    The same file is in 6 other repositories

  • Recency guard

    b-mendoza/agent-skills/skills/recency-guard Skill

    no license3★ repo

    A collection of reusable skills for AI-assisted development workflows

    The same file is in 2 other repositories

  • Responding to pr review comments

    b-mendoza/agent-skills/skills/responding-to-pr-review-comments Skill

    no license3★ repo

    A collection of reusable skills for AI-assisted development workflows

    The same file is in 2 other repositories

  • Review pull request

    b-mendoza/agent-skills/skills/review-pull-request Skill

    no license3★ repo

    A collection of reusable skills for AI-assisted development workflows

    The same file is in 2 other repositories

  • Analyzing recent project state

    b-mendoza/agent-skills/skills/analyzing-recent-project-state Skill

    no license3★ repo

    A collection of reusable skills for AI-assisted development workflows

  • Review software engineer cv

    b-mendoza/agent-skills/skills/review-software-engineer-cv Skill

    no license3★ repo

    A collection of reusable skills for AI-assisted development workflows

  • Cross model review

    i-stack/ai-coding-kit/skills-engineering/cross-model-review Skill

    3★ repo

    跨模型对抗审查已锁定的 PLAN.md——自动发现可用 CLI(codex/gemini/claude),推荐两个不同 provider 的组合并让用户选择,reviewer 只读运行输出 VERDICT:APPROVED|REVISE,主 agent 仲裁并把理由写进 PLAN-REVIEW-LOG.md,MAX_ROUNDS 不收敛输出 deadlock。基于 chaseai-yt/grill-me-codex(MIT)的 Act 2 思路。

  • Historical recall

    i-stack/ai-coding-kit/skills-engineering/historical-recall Skill

    3★ repo

    每个用户任务消息进入处理后、动手前,按门控 best-effort 召回 .plan-reviews/ 知识库历史线索(plan-grill / cross-model-review / auto-code-review 产物),作为待验证 上下文。独立全局门控,不绑定 plan-grill 进入或显式审查授权。全局适用。

  • Plan grill

    i-stack/ai-coding-kit/skills-engineering/plan-grill Skill

    3★ repo

    需求对齐/盘问锁定计划。收到非平凡构建、修改或方案请求时,先评估是否存在无法从代码或上下文确定、且会实质改变结果的阻塞性决策;有则自动进入逐问盘问,无则直接回复或执行。显式 grill/锁定计划触发语始终强制进入。确认前不执行,产出 PLAN.md 供 cross-model-review 接力。基于 Matt Pocock 的 grilling(MIT)。

  • Db schema

    Adit-Jain-srm/skill-forge/skills/db-schema Skill

    3★ repo

    Enforce schema discipline: queries-first design, index-every-filter, safe migrations, verify-at-scale thinking. Prevents the common failure of designing schemas for demos that break in production. Use when creating tables, planning migrations, designing data models, or when user mentions database, schema, migration, indexing, multi-tenant.

    The same file is in 1 other repository

  • Git workflow

    Adit-Jain-srm/skill-forge/skills/git-workflow Skill

    3★ repo

    Enforces disciplined git practices on every commit. Small atomic commits, conventional messages, branch hygiene, and PR readiness checks. Changes how the agent HANDLES git — not just what commands it knows. Auto-triggers on any git operation. Use when committing, branching, merging, or preparing PRs. Also use when git history is messy, commits are too large, or PRs get rejected for poor git hygiene.

    The same file is in 1 other repository

  • Grill

    Adit-Jain-srm/skill-forge/skills/grill Skill

    3★ repo

    Use when about to create a skill, start a feature, design a system, or plan any non-trivial work. Also use when user says grill me, question my plan, challenge this, stress-test, or validate my thinking. Prevents building the wrong thing by resolving decisions before implementation.

    The same file is in 1 other repository

  • Self review

    Adit-Jain-srm/skill-forge/skills/self-review Skill

    3★ repo

    After every code change, automatically review your own work before presenting it. Catches bugs, style issues, and missed requirements BEFORE the user sees them. Use when implementing features, fixing bugs, refactoring, or any code modification. Auto-triggers on code changes. Reduces back-and-forth by catching issues first-pass.

    The same file is in 2 other repositories

  • Session guard

    Adit-Jain-srm/skill-forge/skills/session-guard Skill

    3★ repo

    Prevents long-session corruption AND context compaction amnesia. Monitors session health, detects instruction drift, enforces critical-rule recitation, and splits proactively before degradation hits. Use when working on complex multi-step tasks, when a session is getting long, when the agent starts ignoring rules it followed earlier, when CLAUDE.md conventions drift, when output quality seems to degrade, or after any context compaction event.

    The same file is in 1 other repository

  • Askit build hook

    product-on-purpose/agent-skills-toolkit/skills/askit-build-hook Skill

    3★ repo

    Creates and improves event-driven hooks (Advanced tier) for a plugin to the Advanced Skill Library Standard. Use when you need to add a hook, enforce a guard on a tool or session event, inject context, or document a hook's event, scope, and failure behavior.

  • Privacy notice review

    product-on-purpose/agent-skills-toolkit/tests/fixtures/anti/seeded-defects/privacy-notice-toolkit/skills/privacy-notice-review Skill

    3★ repo

    Reviews a published privacy notice against a seven-point disclosure checklist and the US state privacy statutes, and returns a redline with a per-item verdict. Use when a user asks to review, redline, or gap-check a privacy notice or privacy policy before publishing it.

  • Metrics review

    nemanli/ux-metrics-skills/skills/metrics-review Skill

    3★ repo

    Stress-tests a metric claim against five common failure modes — definition, sample & power, comparison, window, counter-metric — so the user can trust, distrust, or follow up on the number. Works on incoming claims (vendor case studies, PM dashboards, "industry benchmarks", leadership quotes) AND on the user's own draft before they publish. Triggers on "is this claim true?", "review this metric", "vet this benchmark", "is +15% real?", "check this case study". Skip for diagnosing a metric movement on data you own (use metrics-diagnose) or for picking metrics (use metrics-ux).

  • Zod

    DobroslavRadosavljevic/skills/skills/zod Skill

    3★ repo

    Build, review, debug, migrate, or plan Zod v4 validation and TypeScript schema code with current docs. Use for zod, zod/v4, zod/mini, zod/v4/core, parse, safeParse, parseAsync, safeParseAsync, z.infer, z.input, z.output, object schemas, records, enums, unions, refinements, check, transforms, codecs, preprocess, defaults, prefaults, catch, brands, readonly, error customization, error formatting, metadata, registries, JSON Schema, Zod Mini, library-author APIs, and Zod 3 to Zod 4 migrations.

  • Spec evaluator

    nguyenvanphituoc/shapeup-sdlc-plugin/skills/spec-evaluator Skill

    3★ repo

    Use this skill whenever the user wants to evaluate, QA, or verify that an implemented task actually matches its spec and acceptance criteria — the judge in a planner→generator→evaluator harness. Trigger on: "evaluate task TASK-NNN", "QA TASK-NNN", "verify against spec", "check acceptance criteria", "does this match the spec", "grade this build", "run evaluator", or a tech-lead --order dispatch. Skeptical by default — absence of evidence is a FAIL; probes the running app and files file:line bugs.

  • Translator

    nguyenvanphituoc/shapeup-sdlc-plugin/skills/translator Skill

    3★ repo

    Use this skill whenever intake for the harness (pitch, PRD, requirement, transcript, or any spec input) is in a non-English language and must be normalized to English BEFORE planning/building. The single language gate for the planner→generator→judge harness. Triggers on: "translate this pitch", "normalize to English", "this requirement is in Vietnamese", "prepare intake for the harness", "make the spec English", "check if this is English", and Vietnamese "dịch sang tiếng Anh", "chuẩn hoá tiếng Anh", "dịch pitch", "chuyển yêu cầu sang tiếng Anh". Produces faithful English copies (original never overwritten) plus a glossary and verification report. tech-lead auto-invokes it at GATE L0 when intake is non-English; also runs standalone.

  • Address validation

    goshippo/ai/providers/codex/plugin/skills/address-validation Skill

    3★ repo

    Validate, parse, and standardize shipping addresses via the Shippo API

  • Address validation

    goshippo/ai/skills/address-validation Skill

    3★ repo

    Validate, parse, and standardize shipping addresses via the Shippo API

  • Code review

    davidlee/doctrine/plugins/doctrine/skills/code-review Skill

    3★ repo

    Use whenever reviewing code for quality and correctness — a diff, PR, module, or subsystem — producing verified, severity-ranked findings on the RV ledger. Not for comprehension tours (walkthrough) or doctrine-conformance hunts (inquisition, user-invoked only).

  • Feedback

    davidlee/doctrine/plugins/doctrine/skills/feedback Skill

    3★ repo

    Use when receiving feedback on your work — review findings, user corrections, audit results, external reviewer notes — to triage by authority, adjudicate each point on evidence, integrate without regressions, and close the loop with the source. Evidence flips positions; assertions don't.

  • Worktree

    davidlee/doctrine/plugins/doctrine/skills/worktree Skill

    3★ repo

    Use when work needs isolation from the current workspace — when /execute (mode=solo) or the /dispatch funnel must run a phase on its own branch without touching the main working tree. Detects existing isolation, creates a fork via `doctrine worktree fork` (the sole creation+provision+mark verb; coordination tier excluded), runs the commit-before-spawn / branch-point / baseline guards, and hands back the fork branch.

  • Auto learn

    ulpi-io/autonomous-engineering/auto-learn Skill

    no license3★ repo

    Close every autonomous run with a learning pass so the machine never repeats a mistake it already paid for: harvest the run's STRUCTURED artifacts (checkpoint register, blocked-task reasons, guard blocks, fix-loop counts, degradations), verify each candidate lesson adversarially, dedupe against what is already known, then WRITE each learning to the Claude Code memory that LOADS AUTOMATICALLY next session — a convention or plan-shape rule into CLAUDE.md, an area-specific lesson into a path-scoped .claude/rules file, an environment quirk into auto memory. Machine defects are surfaced to the user, never self-patched. Because those are native context files Claude Code already loads, the next run picks the lessons up with no extra step. Use as the closing phase of every run, or standalone.

  • Auto review

    ulpi-io/autonomous-engineering/auto-review Skill

    no license3★ repo

    Review a change across every dimension at once, then keep only the findings that survive an adversarial check — autonomously. It fans out independent reviewers over the diff (correctness, security, performance, maintainability/readability, test adequacy, API/contract & compatibility), dedups their findings, and puts each through a majority-refute verification so false positives never reach you or drive a fix. Survivors come back severity-labeled and actionable (file:line, why, suggested fix), and — if you ask — a bounded fix loop resolves the confirmed blockers. It fails closed: a dimension that didn't actually run is reported as a gap, never as "clean". This is the REVIEW phase. Composes fan-out-work (dimensions), adversarial-verify (confirm findings), converge-loop (optional fix), and checkpoint-resume.

  • Autonomous pipeline

    ulpi-io/autonomous-engineering/autonomous-pipeline Skill

    no license3★ repo

    Run the whole engineering lifecycle end-to-end from one request — spec → plan → build → simplify → test → review → performance → ship — as a single autonomous pass with ONE human approval (the plan) and hard-gated escalation for anything irreversible. It chains the auto-* phase skills, carries a durable pipeline checkpoint so a stop/crash resumes at the exact phase and task it left off, watches the signal between phases (a phase that misses its gate is recorded blocked and surfaces in the register — fail closed, no false-green downstream), and returns a verified findings register at the end. Autonomous: it AUTO-FIXES the confirmed findings in a bounded converge-loop (never asking permission to fix), returning only the residual it can't converge within budget or a fix needing an irreversible/ambiguous decision. This is the top-level "maximise autonomous agents" entry point. Composes every auto-* phase plus checkpoint-resume, budget-guard, watch-and-act, and adversarial-verify.

  • Budget guard

    ulpi-io/autonomous-engineering/budget-guard Skill

    no license3★ repo

    The discipline that keeps an autonomous run from becoming a runaway: before any unattended loop or workflow, declare the five stop conditions — done-condition, hard cap, token/time budget, no-progress rule, escalation triggers — then hold the run to them and stop the instant one fires. Fails closed: a capped run reports an honest partial, never fabricated success. Load at the start of ANY unattended run.

  • 淬火验真

    Biancuihuo/cuihuo-skills/skills/淬火验真 Skill

    no license3★ repo

    边淬火的概念翻转工具。帮用户看见一个"理所当然"的概念下面藏着的隐喻、规则、混淆和因果倒置,引导用户自己完成翻转。 两种入口:带一个旧概念来验、带一个已有翻转来深化。 翻转必须由用户自己说出来——AI 只追问,不替用户翻。 触发方式:/cuihuo-verification、「验真」「翻转这个概念」「这个说法对吗」「帮我翻一下」 Concept verification and flipping tool by 边淬火. Guides users to see hidden metaphors, rules, confusions and causal inversions beneath "taken for granted" concepts, and arrive at their own flip. Trigger: /cuihuo-verification, "verify this concept", "flip this", "is this really true"

  • Grill design

    Xuan0629/shared-skills/grill-design Skill

    no license3★ repo

    One source. Every agent. Zero drift. | 跨 Agent 共享 Skill 管理系统 — 单一数据源,同步到 Claude Code / Codex / Hermes / OpenClaw

  • Audit security

    urmzd/dotfiles/dot_agents/skills/audit-security Skill

    3★ repo

    Scans a repo and host for leaked keys and secrets (gitleaks, trufflehog), audits SSH/GPG/.env file permissions, checks git hygiene, investigates suspicious processes and listeners, and hardens config (FileVault, firewall, SIP, SSH). Use when auditing for leaked credentials or secrets, checking for security issues before a commit, investigating an unknown process or open port, or hardening a machine. Do NOT use for storing, injecting, or rotating secrets at rest (1Password, op read, vaults) -> use manage-secrets; this skill only detects and reports exposure.

  • Check project

    urmzd/dotfiles/dot_agents/skills/check-project Skill

    3★ repo

    Validate project structure against scaffold conventions -- check for required files, CI consistency, documentation completeness, sub-package/workspace members, and optional directory usage, reporting PASS/WARN/FAIL with fix suggestions. Use to audit an existing project or verify a scaffold was applied correctly. Do NOT use to create or modify project files; this is a read-only auditor (use the scaffold-* skills to generate structure).

  • Choose stack

    urmzd/dotfiles/dot_agents/skills/choose-stack Skill

    3★ repo

    Canonical tech-stack reference organized by purpose: release/versioning (sr), docs/demos (teasr, fsrc), codegen (oag), and per-language tools (cargo, clippy, clap, golangci-lint, biome, tsdown, uv, ruff, ty, pytest, pydantic, fastapi). Use when choosing a library, picking the standard CLI/linter/logging tool for a language, setting up a project, or asking "what do we use for X." Do NOT use for coding patterns or error-handling idioms (use write-code) or testing frameworks in depth (use test-code).

  • Community health

    urmzd/dotfiles/dot_agents/skills/community-health Skill

    3★ repo

    Scaffold the GitHub Community Standards files (CODE_OF_CONDUCT, SECURITY, ISSUE_TEMPLATE, pull_request_template) using $COMMUNITY_HEALTH_CONTACT or git config user.email as the contact. Use when bootstrapping a new repo or backfilling community-health coverage.

  • Manage detect secrets

    urmzd/dotfiles/dot_agents/skills/manage-detect-secrets Skill

    3★ repo

    Operate the detect-secrets pre-commit hook correctly: update the baseline with the right flags, break the "baseline file was updated, please git add" commit loop, allowlist false positives, and audit real findings. Use when a commit fails on detect-secrets, the .secrets.baseline keeps changing, or a false positive blocks a push. Do NOT use for storing or injecting secrets via 1Password (use manage-secrets) or repo-wide leak scanning with gitleaks and trufflehog (use audit-security).

  • Merge ready

    urmzd/dotfiles/dot_agents/skills/merge-ready Skill

    3★ repo

    Drive an existing pull request to a mergeable state: get CI green, resolve merge conflicts with the base branch, address and resolve review comments, trigger required bot reviews/approvals (e.g. commenting '@claude review'), link associated issues, and clean up the PR title and description. Ends with a readiness report listing any remaining human-only blockers (required reviewer approvals, CODEOWNERS). Uses the CLI matching the repo's forge: gh for GitHub, glab for GitLab merge requests, tea for Gitea/Forgejo. Use when the user says "get this PR ready to merge", "make this PR mergeable", "get the PR green", "address the review comments", "babysit this PR", "get this MR merged", or "why is this PR blocked". Do NOT merge the PR or enable auto-merge; do NOT open a new PR (use pr); do NOT use for a failing pipeline with no PR context (use fix-and-retry / diagnose-ci).

  • Pr

    urmzd/dotfiles/dot_agents/skills/pr Skill

    3★ repo

    Open a pull request via gh pr create with an auto-generated title and summary derived from the commits on the branch, grouped by conventional-commit type. Use when the user says "create a pull request", "open a PR", "gh pr create", "raise a PR", or "make a PR for this branch". Assumes commits already exist and only opens the PR. Do NOT commit changes or watch CI (use ship); do NOT diagnose or fix a failing pipeline (use fix-and-retry / diagnose-ci).

  • Review design

    urmzd/dotfiles/dot_agents/skills/review-design Skill

    3★ repo

    Pragmatic Programmer principles: DRY, orthogonality, ETC, reversibility, tracer bullets, design by contract, decoupling/Law of Demeter, pragmatic paranoia. The 'why' layer between assess-quality (framework) and write-code (operational). Use when reasoning about design tradeoffs, coupling, or whether a decision is reversible. Do NOT use for the underlying quality framework (use assess-quality) or for concrete tool/idiom/library picks (use write-code).

  • Review diff

    urmzd/dotfiles/dot_agents/skills/review-diff Skill

    3★ repo

    Standardized review of the CURRENT working-tree changes -- staged, unstaged, and untracked -- against an explicit five-dimension rubric (correctness, security, tests, scope-creep, conventions). Emits a prioritized findings list, each with file:line, severity, and a suggested fix. Read-only: it reviews and reports, it does not commit, push, or edit. Use when the user says "review my changes", "review the diff", "look over my staged changes before I commit", or "what's wrong with this PR locally". Do NOT use for red CI/pipeline failures (use diagnose-ci) or whole-repo quality-framework questions (use assess-quality); this reviews the working-tree diff only. assess-quality and review-design both EXCLUDE day-to-day review and name this skill as its home.

  • Ship

    urmzd/dotfiles/dot_agents/skills/ship Skill

    3★ repo

    Generate a conventional commit message from staged or unstaged changes and create an atomic commit, then optionally push and watch CI until it passes or fails. Use when the user says "write a commit", "generate a commit message", "commit this", "git add .", or "ship this". Push and CI-watch are optional and skipped if the user only wants a commit. Do NOT open a pull request (use pr); do NOT diagnose-then-fix a failing pipeline (use fix-and-retry); do NOT do a read-only CI investigation without committing (use diagnose-ci).

  • Triage dotfiles env

    urmzd/dotfiles/dot_agents/skills/triage-dotfiles-env Skill

    3★ repo

    Playbook of known failure modes in this dotfiles stack: pipx "bad interpreter" after Python rebuilds, gpg commit-signing failures, direnv/nix shellHook running bash instead of zsh, Powerlevel10k instant-prompt warnings, and Neovim plugin errors from removed Lua APIs. Use when a shell startup error, git signing failure, broken CLI shim, or nvim stack trace appears on this machine. Do NOT use for generic runtime debugging in projects (use diagnose-runtime), chezmoi naming and templating conventions (use dotfiles), or authoring pinned installers (use setup-devenv-with-chezmoi).

  • Use worktrees

    urmzd/dotfiles/dot_agents/skills/use-worktrees Skill

    3★ repo

    Create, enter, and clean up git worktrees under the mandatory layout: every worktree lives at <repo-root>/.worktrees/<name> in the target repo's primary checkout, .worktrees/ is always gitignored, and the primary checkout never leaves the default branch. Use when creating a worktree, working on parallel branches, isolating an agent's edits, or when the user says "worktree", "work in parallel", or "branch without switching". Do NOT use for commit/PR/merge flow (use ship, pr, merge-ready) or for plain single branch work that needs no isolation.

  • Launch risk review

    MedocMay/ai-native-builder-consultant-skills/ai-native-builder-consultant-skills/skills/build-skills/launch-risk-review Skill

    no license3★ repo

    Run a pre-launch risk review for an AI agent covering behavior, trust zones, failure modes, compliance, and rollback. Use before first launch or before expanding the agent's autonomy to a new action type.

  • Mvp validation

    MedocMay/ai-native-builder-consultant-skills/ai-native-builder-consultant-skills/skills/requirement-definition/mvp-validation Skill

    no license3★ repo

    设计和执行 MVP 最小验证,防止做着做着跑偏。包含验证说明卡、展示脚本和项目展示页三个工具。在技术实现阶段使用,确保每次迭代都在验证正确的事情。

  • Crypto fp check

    Yue-Zhou1/zkcrypto-audit/.codex/skills/crypto-fp-check Skill

    3★ repo

    Verifies suspected ZK and cryptographic findings before reporting. Use when deciding whether a suspected vulnerability is a TRUE POSITIVE or FALSE POSITIVE, assigning severity, or enforcing the Critical/High PoC gate.

  • Ecc pairing auditor

    Yue-Zhou1/zkcrypto-audit/.codex/skills/ecc-pairing-auditor Skill

    3★ repo

    Audit elliptic-curve, pairing, and BLS signature code for point-validation, subgroup, serialization, DST, and pairing-equation failures. Use when reviewing deserialization, `hash_to_curve`, aggregate verification, or batch pairing logic.

  • Fault injection auditor

    Yue-Zhou1/zkcrypto-audit/.codex/skills/fault-injection-auditor Skill

    3★ repo

    Audit cryptographic code for active fault-injection attacks: RSA-CRT Bellcore faults, ECDSA/EdDSA differential fault analysis, verification-skip glitches, redundant-computation bypass, and verify-after-sign gaps. Use when the threat model includes an attacker who can glitch computation, distinct from passive side-channel leakage.

  • Fix verification

    Yue-Zhou1/zkcrypto-audit/.codex/skills/fix-verification Skill

    3★ repo

    Use when a supplied patch claims to fix a previously verified ZK or cryptographic finding and the remediation needs independent verification.

  • Formal verification bridge

    Yue-Zhou1/zkcrypto-audit/.codex/skills/formal-verification-bridge Skill

    3★ repo

    Bridge validated audit findings into optional external formal-verification tooling (Ecne, Picus, Circomspect) with explicit environment checks, reproducible exports, and tool-scoped caveat capture.

  • Kani harness gen

    Yue-Zhou1/zkcrypto-audit/.codex/skills/kani-harness-gen Skill

    3★ repo

    Generate Kani proof harnesses for Rust crypto code. User-triggered only — never auto-invoked by the audit flow. Produces formal verification evidence for crypto-fp-check.

  • Signature scheme auditor

    Yue-Zhou1/zkcrypto-audit/.codex/skills/signature-scheme-auditor Skill

    3★ repo

    Audit classical signature schemes — generic ECDSA across curves, Schnorr/ BIP-340, EdDSA/Ed25519, RSA-PSS and PKCS#1 v1.5 — for verification-equation correctness, malleability, canonical encoding, public-key validation, and hash/prehash semantics. Use for standalone signature library review outside Ethereum application encoding, BLS, or threshold protocols.

  • Spec delta checker

    Yue-Zhou1/zkcrypto-audit/.codex/skills/spec-delta-checker Skill

    3★ repo

    Compare cryptographic code against a reference specification or paper. Use when implementation details look close to a standard but may have drifted in validation, transcript binding, parameter negotiation, or caller obligations.

  • Crypto fp check

    Yue-Zhou1/zkcrypto-audit/plugins/core-audit-flow/skills/crypto-fp-check Skill

    3★ repo

    Verifies suspected ZK and cryptographic findings before reporting. Use when deciding whether a suspected vulnerability is a TRUE POSITIVE or FALSE POSITIVE, assigning severity, or enforcing the Critical/High PoC gate.

  • Fix verification

    Yue-Zhou1/zkcrypto-audit/plugins/core-audit-flow/skills/fix-verification Skill

    3★ repo

    Use when a supplied patch claims to fix a previously verified ZK or cryptographic finding and the remediation needs independent verification.

  • Spec delta checker

    Yue-Zhou1/zkcrypto-audit/plugins/core-audit-flow/skills/spec-delta-checker Skill

    3★ repo

    Compare cryptographic code against a reference specification or paper. Use when implementation details look close to a standard but may have drifted in validation, transcript binding, parameter negotiation, or caller obligations.