agentsclimarketplace

Review & quality

19,016 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

  • Ship readiness

    motao123/dev-workflow-kit/ship-readiness Skill

    1★ repo

    Use when work is nearly complete and needs a final readiness check for merge, release, or deployment. This skill focuses on remaining blockers, verification state, risks, rollback awareness, and documentation gaps.

  • Test strategy gap review

    motao123/dev-workflow-kit/test-strategy-gap-review Skill

    1★ repo

    Use when the main question is whether current verification is sufficient for a change, which test layers are missing, and where the smallest high-value regression protection should be added.

  • Code review and quality

    shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/code-review-and-quality Skill

    1★ repo

    Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

    The same file is in 9 other repositories

  • Git workflow and versioning

    shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/git-workflow-and-versioning Skill

    1★ repo

    Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.

    The same file is in 9 other repositories

  • Biters

    dylanmccavitt/loom/skills/biters Skill

    1★ repo

    Adversarial reviewer that attacks a change before merge — probing for correctness bugs, regressions, maintainability rot, scope creep, and missing tests by default, with security, minimal-diff, and workflow-drift passes available as lenses. Use when the user wants a change reviewed adversarially, risks found before merge, or a lens-focused review pass (correctness, security, minimal-diff, drift).

  • Github review

    zcccc-mxc/codex-skill-router/examples/skills/github-review Skill

    1★ repo

    Use when reviewing GitHub pull requests, issues, code review comments, repository changes, and CI failure context. Do not use for image generation, market analysis, deployment-only tasks, or UI layout work.

  • Security review

    zcccc-mxc/codex-skill-router/examples/skills/security-review Skill

    1★ repo

    Use when reviewing authentication, authorization, login permissions, access control, API security, and bypass risks. Do not use for visual layout, image generation, deployment, or documentation-only tasks.

  • Audit

    spacemata/codex-plugins-for-claude-code/plugins/product-design/skills/audit Skill

    1★ repo

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, placing them in Figma or a local folder, then reporting UX, design, and accessibility findings from that evidence. Use when the user asks to audit, critique, review, inspect, assess, or evaluate a product experience.

  • Review forecast

    spacemata/codex-plugins-for-claude-code/plugins/sales/skills/review-forecast Skill

    1★ repo

    Generate a forecast review with risk analysis, recommendation posture, and change detection using CRM truth, pasted or exported pipeline context, account notes, and optional meeting, email, document, or internal-message evidence.

  • Review rep call trends

    spacemata/codex-plugins-for-claude-code/plugins/sales/skills/review-rep-call-trends Skill

    1★ repo

    Analyze a sales or customer-facing rep’s recent calls to detect improvement, regression, and stable patterns with objective evidence and practical coaching actions.

  • Git essentials

    LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/git-essentials Skill

    1★ repo

    Essential Git commands and workflows for version control, branching, and collaboration.

  • Git pr

    glyphs-ai/glyph/first-party/skills/git-pr Skill

    1★ repo

    Git branch management and GitHub PR workflow using worktrees

  • Thermo nuclear code quality review

    glyphs-ai/glyph/first-party/skills/thermo-nuclear-code-quality-review Skill

    1★ repo

    Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

  • Git insight

    jassonbla/skills/skills/git-insight Skill

    1★ repo

    Analyze git commit history and summarize recent activity from a mission or project perspective. Use for commit summaries, daily or weekly progress reviews, author-specific work summaries, team activity reviews, release-note prep, or understanding what changed in a repository over a time window.

  • Codebase prune review

    jimtin/production-ai/skills/codebase-prune-review Skill

    1★ repo

    Review an existing codebase for redundant, legacy, dead, superseded, or attack-surface-increasing code paths and guide progressive removal with behavior mapping, test coverage, security review, and validation. Use when asked to remove old providers or integrations, clean redundant code paths, reduce tech debt, reduce attack surface, review dead code, retire obsolete routes, remove stale compatibility layers, or clean up after migrations such as Google Drive uploads to Vercel Blob.

  • Full app review

    jimtin/production-ai/skills/full-app-review Skill

    1★ repo

    Orchestrate a full non-mutating app or repo review across architecture, live flows, frontend quality, testing and coverage, security, observability and error instrumentation, analytics, dependencies, deployment, validation readiness, and redundant code paths. The default outcome is an evidence-backed, severity-ordered report plus a prioritized remediation plan — no mutations. Use when the user asks to fully review an app or repo, perform a full app review, app audit, production readiness review, end-to-end review, comprehensive codebase review, or asks what should be fixed before implementation, push, merge, or production. Not for single-dimension requests — route those to the relevant specialist skill directly.

  • Repo testing setup

    jimtin/production-ai/skills/repo-testing-setup Skill

    1★ repo

    Design-then-execute setup of a repository's complete testing and security validation foundation. Containerized lanes for every test layer, canonical verify command, declared hook/gate enforcement model, repo-scoped secret scanning, dependency and image audits, deterministic provider stubs, deployment branch policy, repo-tracked testing inventories, pinned tool policy, and flake handling. Use after $clarify-before-build and $feature-design-preflight when a new project needs its testing approach designed, when a repo has no canonical containerized gate, when tests run on the host, or when security scanning is missing or mis-scoped. Use the short path to audit an adopted repo without mutation. Produces a confirmed Repo Testing Design, executes it, records rules in AGENTS.md/CLAUDE.md, and proves it with a green canonical gate. Not for writing feature tests or fixing individual failures; use $test-readiness-preflight.

  • Test readiness preflight

    jimtin/production-ai/skills/test-readiness-preflight Skill

    1★ repo

    Pre-test readiness workflow that finds and fixes predictable validation blockers before running expensive local or container test gates, then declares a READY, CONDITIONAL, or BLOCKED verdict. Use before full verification, before push readiness checks, after substantial implementation, or when work is likely to hit common failures such as missing unit/integration/E2E coverage, unseeded or stale test databases, unapplied migrations, production schema not ready for deployed code, missing fixtures, Playwright browser setup gaps, stale snapshots, container drift, env/test-double gaps, unsafe broad gitleaks scans, lockfile/package drift, or CI-only assumptions. Not for whole-app audits ($full-app-review) and not a substitute for writing the tests themselves.

  • User action coverage review

    jimtin/production-ai/skills/user-action-coverage-review Skill

    1★ repo

    Impact-scoped review that maps user actions, critical paths, roles, states, and mutations to Playwright/E2E plus unit/integration evidence. Use after an accepted plan and before implementation for substantial feature, frontend, workflow, route, mutation, auth/role, upload, save/delete, navigation, admin/user portal, or release-readiness work; rerun before final validation if scope changes.

  • Check breath

    sumitaich1998/slavex/.cursor/skills/check-breath Skill

    1★ repo

    Checks the breath by cupping a hand to the mouth, breathing into it, and sniffing. Use when the command mentions check your breath, smell your breath, breath check, or is my breath okay.

  • Check mailbox

    sumitaich1998/slavex/.cursor/skills/check-mailbox Skill

    1★ repo

    Mimes checking the mailbox, opening a flap at chest height and reaching in to pull mail out. Use when the command mentions check the mail, check the mailbox, get the post, or grab the mail.

  • Check phone time

    sumitaich1998/slavex/.cursor/skills/check-phone-time Skill

    1★ repo

    Mimes checking the time on a phone, raising it for a quick glance then lowering it. Use when the command mentions check the time, what time is it, glance at your phone, or check your phone for the time.

  • Check watch impatient

    sumitaich1998/slavex/.cursor/skills/check-watch-impatient Skill

    1★ repo

    Checks a wristwatch impatiently and slumps with a sigh. Use when the command mentions check your watch, what time is it, impatient waiting, or running late.

  • Finish task

    vecten/sdlc-toolkit/skills/finish-task Skill

    1★ repo

    Finalize an implementation for a ticket by preparing a branch, drafting a commit message from the actual changes, committing, pushing, and preparing or creating a PR. Use when the user says "finish task", "wrap up ticket", "prepare branch and PR", or asks to finish work for a ticket.

  • Prepare pr

    dor-rondel/agent-skills-mcp/resources/frontend/prepare-pr Skill

    1★ repo

    Use this skill when the user asks to run local CI verification checks (format, lint, typecheck, unit tests), commit changes, or push to GitHub.

  • Python langgraph workflow

    dor-rondel/agent-skills-mcp/resources/langgraph/python-langgraph-workflow Skill

    1★ repo

    Use this skill when managing a Python LangGraph repository using uv and a Makefile. Covers dependency syncing, running quality controls (lint, format, typecheck, tests), generating agent graphs, and executing the git commit/push workflow.

  • Evm deployment and verification

    dor-rondel/agent-skills-mcp/resources/solidity/evm-deployment-and-verification Skill

    1★ repo

    Use this skill when deploying to live testnets/mainnets, verifying source code on block explorers, or exporting ABIs for frontend integration.

  • Foundry git workflow

    dor-rondel/agent-skills-mcp/resources/solidity/foundry-git-workflow Skill

    1★ repo

    Use this skill when running local pre-commit checks (compile, format, test), analyzing contract changes, committing smart contract updates, or pushing to GitHub.

  • Design review

    aictrl-dev/skills/skills/design-review Skill

    1★ repo

    Professional design review of any UI — a marketing page OR a product internal (dashboard, table, list, detail view, settings, a flow). Actionable, located critique against orientation, information architecture, primary task, visual hierarchy, friction/cognitive load, accessibility, and — for app screens — density, states, navigation, consistency, and data legibility. Use when the user says "review this design", "review this screen", "review this dashboard", "critique this UI", "is this UI good", "review this mock", "design review", "roast my design", "roast my landing page", or drops an HTML file / screenshot for feedback.

  • Judge review findings

    aictrl-dev/skills/skills/judge-review-findings Skill

    1★ repo

    Judge untriaged code-review findings for the current pull-request head as TRUE, FALSE, or UNCERTAIN and choose FIX, DEFER, or IGNORE without changing code. Use when the user says "triage review findings", "judge these comments", "which findings are real", or "decide what to fix from this review".

  • Reply to code review

    aictrl-dev/skills/skills/reply-to-code-review Skill

    1★ repo

    Judge current-head review findings, fix accepted defects, run verification, post evidence-backed replies, and request bounded re-review. Use when the user says "address review comments", "reply to code review", "fix accepted findings", or "get this PR through review".

  • Spec review

    aictrl-dev/skills/skills/spec-review Skill

    1★ repo

    Review an engineering issue or specification against repository evidence for ambiguity, missing acceptance criteria, hidden scope, test gaps, and implementation risk. Use when the user says "review this spec", "check issue 123", "is this ready to build", or "find gaps in this ticket".

  • Verify

    pleaseai/run-verify-plugin/skills/verify Skill

    1★ repo

    Verify that a code change actually does what it's supposed to by exercising it end-to-end and observing behavior — drive the affected flow, not just tests or typecheck. Run before committing nontrivial changes; bootstraps this repo's project verify skill if none exists yet. Don't invoke it on a diff that only touches tests, docs, or other code with no runtime surface to drive (a change to product source always has one) — there's nothing to observe.

  • Gsd

    mwgg/skills/plugins/gsd Skill

    1★ repo

    Get-shit-done workflow — plan a whole coding project start to finish, then run it autonomously through a research→plan→execute→verify loop with durable .gsd/ artifacts and per-task verification gates. The main session acts as a thin orchestrator that delegates heavy work to subagents, so large projects complete without filling its context. It analyzes the task dependency graph and runs independent tasks concurrently (in waves) to save wall-clock time, keeping conflicting/dependent tasks sequential. Use whenever the user says "gsd", "/gsd", "get shit done", "gsd this", "ship this with gsd", or asks to plan and autonomously implement + verify a feature/bug/refactor/migration end-to-end. Adapts: a lightweight inline loop for small tasks; an orchestrated, fire-and-forget run for large ones that only stops for genuine design forks.

  • Account recovery review

    SylphxAI/skills/skills/account-recovery-review Skill

    1★ repo

    Design or audit a secure, humane account-access recovery protocol for lost credentials, passkeys, MFA devices, recovery codes, email or phone access, social login, enterprise SSO, compromised accounts, locked users, ownership disputes, and support-assisted recovery. Use when the primary artifact is recovery eligibility, proof, risk, channel, state, authority, containment, communication, appeal, and post-recovery protection. Use enterprise-access-governance-review for tenant/admin role lifecycle and product-abuse-risk-review for cross-product abuse controls.

  • Ad monetization review

    SylphxAI/skills/skills/ad-monetization-review Skill

    1★ repo

    Design or audit one complete in-product advertising system for apps, games, web, and content products: rewarded ads, interstitials, banners/native placements, offerwalls, mediation, payer suppression, reward authority, consent, age/territory modes, frequency and fatigue budgets, IAP/IAA cannibalization, fraud, experiments, and shutdown. Use when deciding ad formats, placements, rewards, provider portfolio, or ad economics; combine with an App or Game Blueprint only when whole-product coherence is also unresolved.

  • Agent planning system review

    SylphxAI/skills/skills/agent-planning-system-review Skill

    1★ repo

    Design or audit the planning and control mechanism of an autonomous agent or multi-step agent workflow, producing an Agent Planning and Control Contract. Use when choosing or evaluating BDI, HTN, partial-order or causal-link planning, Plan-and-Execute, ReAct, receding-horizon control, bounded search, replanning, execution monitoring, or stop conditions. Do not use merely to plan one ordinary task, schedule a current work queue, design agent memory, or review a finished code candidate.

  • Ai product risk review

    SylphxAI/skills/skills/ai-product-risk-review Skill

    1★ repo

    Design or audit one AI product behavior and launch contract covering the user job, AI necessity, model role, autonomy and action rights, data use, affected parties, failure and abuse, UX disclosure, fallback, cost and latency, support, evidence dependencies, and release boundaries. Use when an assistant, copilot, generator, classifier, recommender, or agent needs a product-risk dossier. Do not use for eval implementation, adversarial red teaming, security threat modeling, provider selection, a whole-product blueprint, or incident response.

  • Board metrics operating review

    SylphxAI/skills/skills/board-metrics-operating-review Skill

    1★ repo

    Prepare or audit the operating-metrics evidence packet behind a board or executive review: metric definitions, source reconciliation, period snapshots, cohort and segment cuts, variance bridges, forecast confidence, owner signoff, decisions, and action closure. Use when leadership needs board-ready operating truth. Do not use to invent company numbers, produce audited financial statements, design product analytics instrumentation, analyze one retention chart, or write investor persuasion detached from evidence.

  • Convergent review

    SylphxAI/skills/skills/convergent-review Skill

    1★ repo

    Run a finite, high-coverage formal review of an exact candidate against a frozen acceptance contract, using independent perspectives and executable oracles, batching repairs, and closing without moving the goalposts. Use when review convergence itself is the job. Do not use for open-ended exploration, root-cause hypothesis generation, option selection, or one quick opinion.

  • Customer data migration review

    SylphxAI/skills/skills/customer-data-migration-review Skill

    1★ repo

    Design a customer-data migration/cutover contract: discovery, mapping, validation, rehearsal, execution, reconciliation, and rollback/forward-fix. Not architecture rewrites, same-product backup/restore, or CS value programs.

  • Customer success operations review

    SylphxAI/skills/skills/customer-success-operations-review Skill

    1★ repo

    Design or audit an outcome-led customer success operating system across segmentation, onboarding after technical migration, activation, adoption, health, risk intervention, education, business reviews, renewal and expansion signals, champion or stakeholder change, playbooks, automation, and product-learning handoffs. Use when the primary artifact is the recurring post-sale customer-value system for B2B SaaS, developer tools, platforms, or enterprise products. Use customer-data-migration-review for import/cutover execution, customer-support-operations for reactive support queues, and enterprise-contract-operations-review for contractual obligations and renewal mechanics.

  • Daily reward and streak review

    SylphxAI/skills/skills/daily-reward-and-streak-review Skill

    1★ repo

    Design or audit one daily reward, check-in, streak, calendar, mission, repair, comeback, or return-ritual system for apps and games, including time semantics, progression gates, reward economy, notifications, paid repair/VIP/gacha interaction, abuse, fairness, recovery, experiments, and support. Use when the recurring artifact is a return-loop state machine; use Game/App Design for whole-product retention and Notification Strategy for channel delivery.

  • Data quality observability review

    SylphxAI/skills/skills/data-quality-observability-review Skill

    1★ repo

    Design or audit a recurring Data Reliability Contract for data products and pipelines—datasets, streams, imports, transformations, warehouses, and search/operational projections—across freshness, completeness, semantic drift, reconciliation, trust state, repair, and consumer impact. Use when ongoing data fitness is the primary artifact. Do not use for one bounded customer/tenant migration, search relevance/ranking quality, a general provenance/custody graph, product analytics metrics, ledger truth, privacy, or active incident response alone.

  • Data rights operations review

    SylphxAI/skills/skills/data-rights-operations-review Skill

    1★ repo

    Design or audit an auditable operating system for individual or account data-rights requests: access, export/portability, correction, deletion/erasure, restriction, objection or opt-out, consent withdrawal, appeal, identity and authority checks, shared-account scope, legal/security exceptions, subprocessors, deadlines, communication, and proof. Use when the primary artifact is the end-to-end request case protocol. Use privacy-data-lifecycle-review for proactive product data design and retention policy; do not use this skill as jurisdiction-specific legal advice.

  • Developer product experience review

    SylphxAI/skills/skills/developer-product-experience-review Skill

    1★ repo

    Design or audit the end-user developer journey for an API, SDK, CLI, plugin, app integration, or developer platform across discovery, docs, installation, credentials, sandbox, first success, production readiness, diagnostics, support, certification, recertification, and retained use. Use when the primary artifact is a Developer Adoption Contract joining those surfaces into one measurable experience. Do not use for API or SDK implementation, API versioning policy alone, infrastructure capacity, developer quota or credit abuse policy, generic product abuse, or product analytics instrumentation alone.

  • Developer quota credit abuse review

    SylphxAI/skills/skills/developer-quota-credit-abuse-review Skill

    1★ repo

    Design or audit the reusable product policy for developer quotas, free or promotional credits, costly-operation access, trust-tier graduation, abuse-resistant ledgers, adaptive friction, throttling, review, appeals, cost controls, and legitimate production scale-up. Use when generosity, activation, and abuse economics must be balanced across a developer platform. Do not use for one account's 429 debugging or limit-increase ticket, low-level rate-limiter implementation, infrastructure capacity planning, DDoS response, package pricing, payment settlement, or a fraud investigation alone.

  • Enterprise access governance review

    SylphxAI/skills/skills/enterprise-access-governance-review Skill

    1★ repo

    Govern enterprise access across roles, joiner-mover-leaver, least privilege, access reviews, break-glass, and audit evidence. Use for tenant/admin access lifecycle. Not end-user account recovery or product-wide abuse economics.

  • Enterprise contract operations review

    SylphxAI/skills/skills/enterprise-contract-operations-review Skill

    1★ repo

    Design or audit an enterprise contract operating system across authoritative document intake, versions and precedence, clause and obligation extraction, redlines/deviations, approvals, commitments, amendments, notice windows, renewals, true-ups, cancellations, expiries, exceptions, evidence, and handoffs to pricing, billing, entitlements, security, privacy, support, product, finance, sales, and customer success. Use when the primary artifact is the executable contract and obligation lifecycle. This skill does not provide legal advice or approve terms.

  • Game economy review

    SylphxAI/skills/skills/game-economy-review Skill

    1★ repo

    Design or audit one complete game economy artifact for mobile, PC, console, web, casual, premium, or live-service games: currencies, inventory, sources/sinks, progression pacing, rewards, gacha/pity, battle passes, IAP/ads, events, refunds/revocation, inflation, concentration, anti-abuse, newcomer/veteran fairness, simulations, and live tuning. Use for economy ownership and balance; use Game Design for whole-game coherence and Payment Readiness for provider transactions.

  • Game soft launch review

    SylphxAI/skills/skills/game-soft-launch-review Skill

    1★ repo

    Design or audit a game soft-launch learning and exposure program across regions, cohorts, acquisition sources, FTUE, core/meta loops, retention, economy, IAP/IAA, live events, store creative, crashes/performance, support/community, global-transfer risk, and automated scale/hold/pause/withdraw gates. Use when a production-shaped game is entering bounded real-player exposure; use Game Design for the game itself and Distribution Readiness for store submission/certification.

  • Launch readiness review

    SylphxAI/skills/skills/launch-readiness-review Skill

    1★ repo

    Produce or audit one cross-domain launch admission verdict for an app, game, SaaS, desktop product, developer tool, marketplace, major release, beta, or campaign. Integrate exact product, quality, performance, security/privacy, payments, distribution, analytics, support, marketing, legal/authority, rollback, and post-launch evidence into go, conditional-go, hold, or no-go gates. Use when launch-day decision ownership is the artifact; use specialist skills to create missing domain evidence.

  • Marketplace payouts review

    SylphxAI/skills/skills/marketplace-payouts-review Skill

    1★ repo

    Design and audit marketplace payout, earnings, fee, revenue share, seller balance, creator payout, refund, chargeback, hold, clawback, split payment, ledger, tax/compliance handoff, payout support, and dispute flows for creator marketplaces, app/plugin stores, gig marketplaces, game marketplaces, affiliate programs, and two-sided platforms. Use when money moves from buyers through the platform to sellers or creators.

  • Marketplace seller performance review

    SylphxAI/skills/skills/marketplace-seller-performance-review Skill

    1★ repo

    Design or audit a marketplace seller-performance system covering opportunity-normalized quality evidence, confidence, cold start, category baselines, explanations, coaching, badges, ranking inputs, enforcement referrals, appeals, recovery, anti-gaming, fairness, buyer harm, and marketplace health. Use when the primary artifact is recurring seller assessment and performance-intervention governance. Do not use for one seller's content-policy, moderation, fraud, or dispute case; payout-ledger design; a general search-ranking algorithm; or transaction refund operations.

  • Marketplace trust operations review

    SylphxAI/skills/skills/marketplace-trust-operations-review Skill

    1★ repo

    Design or audit a two-sided marketplace trust operating system across participant and listing policy, content or commerce risk, moderation and fraud-review queues, temporary controls, disputes, evidence, enforcement ladders, notices, appeals, restoration, policy/model learning, fairness, trust economics, and marketplace health. Use when the primary artifact is a Marketplace Trust Operating Contract joining those decisions across buyers and sellers, creators, developers, or partners. Do not use for payout-ledger mechanics, generic product abuse outside a marketplace, seller performance coaching, or a general search/recommendation ranking algorithm alone.

  • Notification strategy review

    SylphxAI/skills/skills/notification-strategy-review Skill

    1★ repo

    Set product notification strategy across channels, eligibility, frequency caps, personalization, consent, and effectiveness. Use when notification policy is the job. Not one promotional blast and not the full CRM/marketing OS.

  • Offline sync conflict review

    SylphxAI/skills/skills/offline-sync-conflict-review Skill

    1★ repo

    Design or audit one offline/local-first synchronization and conflict protocol: local storage, queued mutations, idempotency, causality/order, reconnect, tombstones, optimistic states, multi-device/collaborative merges, attachments, auth expiry, encryption, schema migration, data-loss recovery, UX, sync-domain evidence, and chaos tests. Use when unreliable connectivity or concurrent edits need an independently acceptable sync artifact; use App Design for whole-product workflows.

  • Operational observability review

    SylphxAI/skills/skills/operational-observability-review Skill

    1★ repo

    Design operational observability with protected operator evidence and intentional audience-safe customer/public projections. Use when an end-to-end service operating and diagnostic-access contract—logs, metrics, traces, health/readiness, SLOs, alerts, and actions—is the primary artifact. Do not use for product analytics, one feature instrumentation edit, an active incident, recurring data-product quality, or agent tracing alone.

  • Optimization objective review

    SylphxAI/skills/skills/optimization-objective-review Skill

    1★ repo

    Design or audit a metric, KPI, score, reward, ranking, completion predicate, gate, evaluator, or automated optimization target for Goodhart effects, reward hacking, specification gaming, and harmful trade-offs, producing an Optimization Objective Contract. Use when agents, models, teams, or automation will actively optimize a measurable target. Do not use for ordinary analytics instrumentation, one product experiment, or a decision that has no optimization mechanism.

  • Privacy data lifecycle review

    SylphxAI/skills/skills/privacy-data-lifecycle-review Skill

    1★ repo

    Design the privacy data lifecycle—collection, purpose limits, retention, sharing, minimization, and deletion. Use for privacy lifecycle programs. Not a single DSAR ticket and not a security threat model session.