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

  • Product abuse risk review

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

    1★ repo

    Design or audit a product-level abuse and fraud control system across identities, automation, promotions, referrals, trials, credits, purchases, refunds, content, inventory, scraping, collusion, account farming, evasion, and support exploitation. Use when the primary artifact is an adaptive abuse threat, decision, control, appeal, economics, and evidence contract spanning a product surface. Use account-recovery-review for legitimate recovery, developer-quota-credit-abuse-review for developer quota and credit policy, marketplace-trust-operations-review for marketplace participant policy/enforcement, and payment-platform-readiness for payment and ledger correctness.

  • Product analytics instrumentation review

    SylphxAI/skills/skills/product-analytics-instrumentation-review Skill

    1★ repo

    Design or audit a Product Analytics Event, Identity, and Metric Contract for decision questions, behavior events, identity, consent, delivery, product metrics, QA, dashboards, and drift. Use when trustworthy product measurement is the independent artifact. Do not use for service logs/traces/health/SLOs/alerts/operator diagnostics, generic data-pipeline reliability, active incidents, product strategy, or payment truth.

  • Product experiment review

    SylphxAI/skills/skills/product-experiment-review Skill

    1★ repo

    Design or audit one decision-grade product experiment protocol and learning memo covering the decision, mechanism, estimand, eligibility, assignment, exposure, interference, metrics, maturity, sample plan, guardrails, stopping, analysis, and action rule. Use for A/B tests, holdouts, switchbacks, cluster or staged experiments in product, growth, pricing, lifecycle, marketplace, game, and AI surfaces. Do not use for feature-flag engineering, instrumentation implementation, rollout without a causal question, or choosing the underlying product strategy.

  • Product recovery contract review

    SylphxAI/skills/skills/product-recovery-contract-review Skill

    1★ repo

    Design or audit a product-level user-data durability and recovery contract spanning backup, restore, same-product export/re-import, device replacement, version compatibility, entitlement recovery, deletion, and support-assisted recovery. Use when the independently accepted artifact is a user-facing recovery model plus requirements for downstream engineering. Do not use for infrastructure disaster recovery, database replication, deployment rollout, incident command, sync-conflict algorithms alone, account-authentication recovery, or customer data import and cutover from a different product.

  • Promotion campaign review

    SylphxAI/skills/skills/promotion-campaign-review Skill

    1★ repo

    Design or audit one promotion system—offer, discount, update benefit, cross-promotion, win-back, lifecycle push, app/game event, referral push, launch or seasonal campaign—across objective, audience, deterministic eligibility, user+offer cooldowns, placement, transparent message, economics, authoritative fulfillment, reversal, fraud, support, experiments, automation, and shutdown. Use for one campaign artifact; use Marketing Automation for the whole channel and spend operating system.

  • Reference originality review

    SylphxAI/skills/skills/reference-originality-review Skill

    1★ repo

    Review originality against references: influence, copying risk, transformation quality, and disclosure needs. Use for originality/reference reviews. Not formal legal opinions and not running plagiarism software alone.

  • Referral loop review

    SylphxAI/skills/skills/referral-loop-review Skill

    1★ repo

    Design or audit one referral, invite, friend/team sharing, affiliate, ambassador, creator, waitlist, or viral loop across value moment, inviter/invitee states, consented channels, deep links, deterministic attribution, qualification, pending grants, caps, reversals, fraud/self-referral, privacy/contact handling, social interaction, support, experiments, and shutdown. Use when the independent artifact is a persistent referral state machine; use Marketing Automation for the full channel portfolio.

  • Refund and support flow review

    SylphxAI/skills/skills/refund-and-support-flow-review Skill

    1★ repo

    Design or audit one customer/account consequence flow after authoritative cancellation, refund, revocation, chargeback, or dispute events: entitlement outcome, grace, repayment, repurchase, commerce restriction, abuse ladder, appeal, support, trust recovery, and product feedback for SaaS, apps, games, utilities, marketplaces, and subscriptions. Use when post-event treatment is the primary artifact; use Payment Platform for provider ingestion, money ledger, settlement, and authoritative event projection.

  • Retention cohort review

    SylphxAI/skills/skills/retention-cohort-review Skill

    1★ repo

    Diagnose a general product retention cohort or curve and turn it into decisions by validating cohort eligibility, value events, observation windows, metric type, censoring, identity, segment mix, uncertainty, lifecycle mechanisms, monetization, and experiment evidence. Use when cohort analysis itself is the independent artifact and no approved price-change migration owns the causal program. Do not use for a live subscription price-increase cohort or renewal readback, event instrumentation implementation, notification design alone, pricing architecture, broad board reporting, or a full product blueprint.

  • Revenue operations review

    SylphxAI/skills/skills/revenue-operations-review Skill

    1★ repo

    Design or audit a trustworthy revenue operating system across account/contact/opportunity data, lifecycle and pipeline stages, source attribution, qualification and discovery, owner/agent routing, technical-sales handoffs, forecast and capacity, required evidence, automation, incentives or commissions, reporting, data quality, permissions, and change governance. Use when the primary artifact is the end-to-end go-to-market revenue truth and decision system. Use marketing-automation-blueprint for demand generation, enterprise-contract-operations-review for contract obligations, customer-success-operations-review for post-sale value, and saas-subscription-pricing for packaging and price.

  • Review solicitation policy

    SylphxAI/skills/skills/review-solicitation-policy Skill

    1★ repo

    Design or audit platform-specific public rating and review request eligibility, native request surfaces, cooldowns, policy-required audience exclusions, no-display behavior, and request-state evidence for apps, games, web products, and storefronts. Use when the requested artifact is an authentic public review solicitation policy or request state machine, including an audit of sentiment gating, star steering, review rewards, suppression, or retaliation. For private feedback intake, review ingestion or response, evidence clustering, support routing, product action, or close-loop learning, use product-feedback-learning-loop; compose both only when the request asks for both artifacts.

  • Risk matched verification standard

    SylphxAI/skills/skills/risk-matched-verification-standard Skill

    1★ repo

    Select evaluation, replay, simulation, model, and canary evidence in proportion to the actual failure model and residual uncertainty. Use when deterministic unit and integration tests cannot fully verify AI, probabilistic, distributed, concurrent, or time-dependent behavior. Use CI Admission for flaky-check attribution or quarantine; do not add expensive verification machinery to an ordinary deterministic code path.

  • Search discovery quality review

    SylphxAI/skills/skills/search-discovery-quality-review Skill

    1★ repo

    Design or audit one search, browse, recommendation, or marketplace-discovery quality contract covering corpus and intent, retrieval and eligibility boundaries, ranking evidence, query/result slices, zero and low-confidence recovery, freshness, cold start, personalization, sponsored/editorial separation, abuse, fairness, diagnostics, and release decisions. Use when the primary artifact is a discovery-quality scorecard and improvement plan. Do not use for search implementation, SEO, seller enforcement, analytics instrumentation, or campaign merchandising alone.

  • Security assurance operations review

    SylphxAI/skills/skills/security-assurance-operations-review Skill

    1★ repo

    Prepare or audit one truthful customer security-assurance packet and its claim-evidence operating loop across questionnaires, procurement responses, trust-center content, gated reports, control mappings, gaps, exceptions, commitments, freshness, access, and revocation. Use when the primary artifact is what the company may say and prove about current security. Do not use for security implementation, threat modeling, penetration testing, vulnerability remediation, incident response, compliance audit execution, or contract redlining.

  • Social media operations review

    SylphxAI/skills/skills/social-media-operations-review Skill

    1★ repo

    Design or audit one recurring operating model for already-selected official social-media and community channels across account authority, publishing and platform readback, listening, replies, moderation routing, rights and disclosures, crisis correction, impersonation or takeover response, automation, measurement, archive, recovery, and shutdown. Use when the independent artifact is a Social Media Operating Model. Use Marketing Automation for channel strategy, audience, message, campaigns, spend, and incrementality; use specialists for one post, media pack, support case, review-learning loop, or product-wide trust policy.

  • Software distribution readiness

    SylphxAI/skills/skills/software-distribution-readiness Skill

    1★ repo

    Check whether software can be distributed safely: artifacts, signing, channels, updates, rollback, and install verification. Use for distribution/release packaging readiness. Not store listing conversion copy alone.

  • Subscription price increase retention review

    SylphxAI/skills/skills/subscription-price-increase-retention-review Skill

    1★ repo

    Plan, audit, diagnose, or recover the retention-safe rollout of an already proposed subscription price change across cohorts, contracts, discounts, billing channels, regions, renewal windows, notices, consent, grandfathering, offers, cancellation, refunds, support, experiments, and net revenue. Use when the price-change program owns sequencing, renewal-maturity cohort readback, or recovery. Do not use to choose the underlying price/package architecture, analyze retention unrelated to a price change, operate refunds alone, or create a general notification strategy.

  • Trust me bro

    paranoidandroid2124/sounds-like-a-skill-issue/skills/trust-me-bro Skill

    1★ repo

    Run controlled, paired evaluations of an Agent Skill against a no-skill baseline or previous revision, using isolated contexts, raw artifacts, deterministic verification, and blind comparison. Use when validating a new or edited skill, testing whether instructions improve pass rate enough to justify tokens or latency, resolving competing skill versions, or producing reproducible efficacy evidence. Do not use for a quick structural lint or an upgrade-only smoke check.

  • Gpt orchestration

    SYMBaiEX/skills/skills/gpt-orchestration Skill

    1★ repo

    Coordinate hierarchical coding-agent fleets for repository-wide audits, implementation sprints, migrations, and complex work that benefits from parallel specialists. Use when a user asks for subagents, a fleet, parallel delegation, GPT-5.6 Sol, Terra, or Luna routing, broad codebase completion, or independent implementation and verification passes. Enforce bounded ownership, concurrency-aware waves, dirty-worktree safety, runtime-honest model handling, and evidence-based integration.

    The same file is in 1 other repository

  • Top cs polishing

    zhiming33416/top-cs-paper-skills/skills/top-cs-polishing Skill

    1★ repo

    Polish, translate, tighten, structurally revise, or diagnose existing computer-science manuscript prose and LaTeX for WWW, ICLR, ICML, or a generic venue while preserving evidence. Use for Chinese-to-English academic rewriting, paragraph flow, section-level revision, claim calibration, concision, terminology consistency, reducing generic AI prose, revision ledgers, and LaTeX layout or float-placement problems. Do not use to invent a paper from sparse notes, simulate peer review, or write a reviewer response.

  • Top cs reviewer

    zhiming33416/top-cs-paper-skills/skills/top-cs-reviewer Skill

    1★ repo

    Perform a confidential pre-submission audit of a computer-science manuscript against WWW, ICLR, ICML, or generic top-conference expectations. Use for reviewer-style assessment, rejection-risk analysis, claim verification, experimental and reproducibility audits, venue or track fit, anonymity checks, paper readiness, and actionable revision priorities. This is an author-side simulation, not an official review and not a substitute for domain experts.

  • Aise review

    jiayx01/PhysisAI/plugins/physisai/skills/aise-review Skill

    1★ repo

    审阅 PhysisAI 候选经验的来源、适用范围、重复项、冲突、时效、上下文成本和建议去向。用户要求看看学到了什么、候选是否正确、该写进哪里或为什么被阻止时使用;只审阅不晋升。

  • Vibe review

    Cashmeran/hlvibes-skills/vibe-review Skill

    no license1★ repo

    Use when project code exists and needs comprehensive review after build. Implements agent-separated audit with 6 parallel reviewers (including adversarial auditor), cross-validation debate, and convergence-based fix loop (max 5 rounds). "The agent that writes never reviews." Produces .vibe/doc/REVIEW.md.

  • Issue pr templates

    Paldom/github-skills/skills/issue-pr-templates Skill

    1★ repo

    Builds structured GitHub contribution intake - YAML issue forms with required fields and auto-labels, config.yml routing, a pull request template with a working checklist, and starter labels like good first issue. Use when the user asks for issue templates, bug report forms, a PR template, or to stop blank issues. Not for CONTRIBUTING or other prose community files, and not for issue triage.

  • Code review

    IvanGomezMartinez/MatStudyLab/.agents/skills/code-review Skill

    1★ repo

    Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

    The same file is in 12 other repositories

  • Grill me

    IvanGomezMartinez/MatStudyLab/.agents/skills/grill-me Skill

    1★ repo

    A relentless interview to sharpen a plan or design.

    The same file is in 19 other repositories

  • Grill with docs

    IvanGomezMartinez/MatStudyLab/.agents/skills/grill-with-docs Skill

    1★ repo

    A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

    The same file is in 19 other repositories

  • Prototype

    IvanGomezMartinez/MatStudyLab/.agents/skills/prototype Skill

    1★ repo

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    The same file is in 4 other repositories

  • Code review workflow

    2702207741-dev/agent-skills-pipeline/code-review-workflow Skill

    1★ repo

    Use when the user asks to review code, a diff, pull request, patch, branch, implementation, or change set for bugs, regressions, security risks, data loss, concurrency issues, performance problems, maintainability risks, API contract drift, or missing tests. Do NOT use for reviewing SKILL.md quality; use skill-review-workflow for skill files.

  • Cross model verification

    2702207741-dev/agent-skills-pipeline/cross-model-verification Skill

    1★ repo

    Use when correctness matters more than speed, when working on high-stakes changes (production, security, data migration), or any time the first model's confidence feels unverified. Use when the user says "换个模型检查", "cross-model", "cross-validation", "second opinion", or "verify with another model".

  • Release notes review

    2702207741-dev/agent-skills-pipeline/examples/end-to-end-maintenance/repository-after/skills/release-notes-review Skill

    1★ repo

    Review release-note behavior, regression evidence, and package readiness for this repository before a release.

  • Documentation release review

    2702207741-dev/agent-skills-pipeline/examples/external-repos/documentation-site/skills/documentation-release-review Skill

    1★ repo

    Review documentation releases for navigation, command accuracy, evidence links, and compatibility notes.

  • Javascript library review

    2702207741-dev/agent-skills-pipeline/examples/external-repos/javascript-library/skills/javascript-library-review Skill

    1★ repo

    Review a JavaScript library for ESM compatibility, tests, public API changes, and release safety.

  • Python library review

    2702207741-dev/agent-skills-pipeline/examples/external-repos/python-library/skills/python-library-review Skill

    1★ repo

    Review changes to this Python library for API compatibility, behavioral regressions, missing tests, and release readiness.

  • Git workflow for agents

    2702207741-dev/agent-skills-pipeline/git-workflow-for-agents Skill

    1★ repo

    Use when the user says 提交代码, 创建PR, 分支管理, 推到远程, commit, pull request, or any full-cycle git operation. Use when an agent has completed a feature and needs to commit, branch, and submit a PR following project conventions.

  • Skill review workflow

    2702207741-dev/agent-skills-pipeline/skill-review-workflow Skill

    1★ repo

    Use when the user says "审查这个skill""review skill""检查skill质量""这个skill写得怎么样". Use when a new SKILL.md is ready for pre-commit quality validation. Use when the user wants an objective quality score for an existing skill. Do NOT use during drafting stage, for reviewing non-SKILL.md code, or when the user asks how to use a skill (load and explain directly).

  • Production full stack

    notwld/engineering-baseline/skills/production-full-stack Skill

    1★ repo

    Design, scaffold, implement, review, and verify production-grade full-stack applications and substantial backend or frontend features. Use when creating an app, API, backend, frontend, dashboard, service, worker, queue, database-backed feature, or production deployment. Enforce scalable API/worker architecture, bounded concurrency, queues, caching, pagination, audit logging, rate limits, Docker and Docker Compose, environment and secret hygiene, consistent reusable UI, understandable end-to-end errors, documentation updates, code review, and production-readiness evidence.

  • Security review

    notwld/engineering-baseline/skills/security-review Skill

    1★ repo

    Perform mandatory feature-level threat modeling and security verification using STRIDE, OWASP ASVS 5.0.0 Level 2, OWASP Top 10:2025, NIST CSF 2.0, and NIST SP 800-207 Zero Trust. Use for every new feature and material behavior change, and for reviews involving authentication, authorization, trust boundaries, APIs, untrusted input, sensitive data, secrets, cryptography, files, external URLs, dependencies, infrastructure, logging, or deployment. State mitigations before implementation and verify controls afterward.

  • Spot review trends

    Feedspace/Feedspace-Cookbook/plugins/feedspace-reviews/skills/spot-review-trends Skill

    1★ repo

    Track how customer reviews change over time - review volume, average rating, sentiment mix, and which themes are rising or fading - bucketed by period and grounded in real dated reviews. Reviews come from a Feedspace account (via the Feedspace MCP), a CSV, or pasted text, so anyone can use it. Trigger when someone asks how their reviews, ratings, sentiment, or feedback have changed over time, wants review trends, or asks about month-over-month or quarter-over-quarter movement.

  • Git ops

    ksed8/cc-loopkit/.claude/skills/git-ops Skill

    1★ repo

    Git workflow mechanics — clean commits, branching, rebasing, resolving conflicts, and authoring good pull requests. Use when committing, branching, rebasing, squashing, resolving merge conflicts, cleaning up history, or opening/updating a PR. For reviewing someone else's PR use `/review`; for reviewing your own diff use `/code-review`.

  • Loop verify

    ksed8/cc-loopkit/.claude/skills/loop-verify Skill

    1★ repo

    Outer-loop verification step for run.sh — checks the repo against PROMPT.md and .claude/IMPLEMENTATION_PLAN.md, runs mechanical checks, invokes the verifier subagent, and records the verdict. Invoked externally as `/loop-verify` by run.sh, once per outer-loop iteration. Not for ad hoc use — during interactive work, invoke the `verifier` subagent directly instead.

  • Customs validate

    FrancoisChastel/sydonia-toolkit/skills/customs-validate Skill

    1★ repo

    Validate, verify or audit the Sydonia Toolkit customs schema against its done-conditions — a clean load (schema + seed + end-to-end example, zero errors), every table carrying a provenance tag, and every cited source ID resolving in SOURCES.md. Use when the user wants to check the schema still loads cleanly, confirm it is fully grounded/sourced, or audit a fork after changes before committing.

  • Sql migration reviewer

    aneesh-a7/skill-lint/examples/good/sql-migration-reviewer Skill

    1★ repo

    Reviews a SQL migration file for safety before it ships to production, checking for locking risk, missing rollback statements, unsafe column drops, and index changes made without CONCURRENTLY. Use when the user asks to review, check, or sanity-test a migration file, a schema change, or a raw `.sql` file that alters a table. Not for writing migrations from scratch, and not for reviewing application-level ORM code that contains no raw SQL.

  • Github publish changes

    lilabrooks/lila-agent-skills/skills/github-publish-changes Skill

    1★ repo

    Safely check, commit, and push intended local Git changes to GitHub when the user explicitly invokes this skill, requests its basic or quick commit tier, asks for exact candidate identity, or needs its handling for partial staging, dirty push-only worktrees, forks, exact force leases, or CI monitoring. Leave ordinary commit, push, and pull-request requests to a host-native publisher when one is available unless the user selects this skill. Stop at the requested boundary, preserve unrelated work, verify the exact candidate, and require separate authority for pull requests, tags, releases, deployments, bypasses, and rewritten history.

  • Verify repository

    lilabrooks/lila-agent-skills/skills/verify-repository Skill

    1★ repo

    Perform evidence-based repository readiness and final-QA audits. Use when the agent is asked to assess whether a repository is ready for agent or production use, run final QA, verify nothing broke, audit before a commit or release, inspect coverage and quality gates, validate git and ignore hygiene, check generated-project workflows, or clean verification artifacts.

  • Architecture decisions

    Deadlymind/nanolama/skills/architecture-decisions Skill

    1★ repo

    Records an architecture decision as a numbered, immutable ADR under docs/adr — Status, Date, Context, Decision, Consequences, and the alternatives that lost — so the reasoning outlives the people who held it. Use when a choice is expensive to reverse or cross-cutting (Celery versus a cron, cookie JWT versus bearer tokens, one shared DB with a tenant FK versus schema-per-tenant), when a settled trade-off is being re-litigated in review, when superseding an earlier ADR, or when a PR needs a link to the reasoning behind it. Not for the commit message that carries the change (see commit-message) or the user-facing release notes (see changelog).

  • Changelog

    Deadlymind/nanolama/skills/changelog Skill

    1★ repo

    Maintains a Keep a Changelog CHANGELOG.md with an Unreleased section, SemVer version headings, and grouped human-readable entries (Added, Changed, Fixed, Removed, Security, Deprecated) with compare-URL links. Use when adding a changelog entry, cutting a release, rolling Unreleased into a dated version, turning Conventional Commits into release notes, or asking "what changed in this version". Not for writing the git commit messages themselves (see commit-message) or the pipeline that publishes a release (see ci-cd).

  • Ci cd

    Deadlymind/nanolama/skills/ci-cd Skill

    1★ repo

    Builds a GitHub Actions merge gate for the app stack — parallel backend/frontend jobs that run manage.py check, makemigrations --check --dry-run (fail on model drift), pytest, ruff lint, tsc typecheck, and pnpm build, with cached deps and required status checks blocking red PRs. Use when adding or fixing a workflow under .github/workflows, wiring CI for Django/DRF plus Next.js, catching migration drift or unformatted code before merge, running a dependency-audit gate, or asking how the pipeline blocks a broken branch. Not for deploying the built app to Beanstalk/Amplify (see deploy-aws) or authoring the tests themselves (see write-tests).

  • Code review

    Deadlymind/nanolama/skills/code-review Skill

    1★ repo

    Reviews the current git diff across four lenses (correctness, simplification, reuse, efficiency) and emits findings ranked by severity with file—line and a concrete failure scenario, plus nanolama-specific gates a generic reviewer misses (missing entreprise tenant filter, fail-closed regression, resource_action RBAC gap on a custom @action, DRF N+1, TanStack Query cache-key/invalidation bugs). Use when reviewing a diff or PR, doing a self-review before pushing, or asked to "review my changes" or "look over this diff". Not for exploit-focused auth/injection review (see security-review), query-plan/load profiling (see perf-review), or proving the change runs (see verify).

  • Commit message

    Deadlymind/nanolama/skills/commit-message Skill

    1★ repo

    Writes a Conventional Commits message from the staged git diff — type(scope) subject in the imperative under 72 chars, a body explaining WHY, and footers for BREAKING CHANGE and issue refs. Use when asked to write a commit message, "commit this", "conventionalize", or when deriving the type (feat, fix, chore, refactor, docs, test, perf, build, ci) and scope from what the diff actually changed. Not for the release-facing CHANGELOG rollup across many commits (see changelog) or judging whether the diff is correct (see code-review).

  • Git workflow

    Deadlymind/nanolama/skills/git-workflow Skill

    1★ repo

    Runs the daily branch to PR to merge loop safely on any git/GitHub repo — one branch per task, confirm the branch before every commit, rebase onto latest main before review, keep PRs small with a what/why/how-to-test description, and recover cleanly with amend, revert, and reflog. Use when starting a task branch, preparing or reviewing a pull request, deciding whether to amend or revert, undoing a bad commit, or recovering work that seems lost. Not for writing the commit text itself (see commit-message) or reviewing the diff's contents (see code-review).

  • Perf review

    Deadlymind/nanolama/skills/perf-review Skill

    1★ repo

    Finds and fixes performance problems in a Django/DRF app — hunts N+1 and unbounded queries on hot paths, fixes them with select_related (FK) and prefetch_related (M2M/reverse), paginates every list endpoint, and caches expensive dashboard aggregates with a short TTL over a bounded query. Use when a list endpoint or dashboard is slow, when a page fires hundreds of queries, when reviewing for N+1 with django-debug-toolbar, nplusone, or QuerySet.explain(), or when someone says "this is slow" or "too many queries". Not for diagnosing a specific crash or wrong result (see debug), row-locking and race conditions (see db-concurrency), or generic ViewSet/serializer wiring (see drf-api).

  • Security review

    Deadlymind/nanolama/skills/security-review Skill

    1★ repo

    Audits a diff for this stack's top risks — tenant isolation on every business queryset (fail-closed, no client-supplied tenant id trusted), RBAC on every custom endpoint and @action, PII leakage in list endpoints/logs/exports, file-upload validation (content-type, size, extension, private storage), and secrets not committed. Use when reviewing a Django/DRF change before merge, auditing a new ViewSet or upload handler, checking a PR for security issues, or asked "is this safe to ship". Findings are confidence-gated. Run only on TRUSTED diffs — not hardened against prompt injection. Not for generic correctness/quality review (see code-review) or proving behavior works (see verify).

  • Verify

    Deadlymind/nanolama/skills/verify Skill

    1★ repo

    Drives a change end to end and observes real behavior — exercising the actual flow through the API, UI, or logs, not just tests or typecheck — before it is called done. Use when about to claim a task is finished, working, or fixed, when the user asks to verify or confirm a change, or before opening a PR. Enforces a gate — no completion claim without a fresh proving-command run and its pasted output. Not for writing the tests themselves (see write-tests) or root-causing a failure (see debug).

  • Version check

    Deadlymind/nanolama/skills/version-check Skill

    1★ repo

    Verifies the current stable and LTS version and support window of a technology by deep research before it is installed, pinned, or upgraded — checking today's release status on official release notes, endoflife.date, PyPI, and npm rather than trusting a hardcoded number. Use when adding a dependency, choosing or bumping a version, starting a project, planning an upgrade, or asking which version or LTS to use for Django, Python, Node, PostgreSQL, Next.js, or any stack tool. Not for scanning installed dependencies for CVEs (see dependency-audit).

  • Webhook handler

    Deadlymind/nanolama/skills/webhook-handler Skill

    1★ repo

    Safely receives inbound third-party webhooks and provider callbacks by holding a four-step contract — verify authenticity with a constant-time HMAC or verify token before parsing, resolve the owning tenant from the verified payload before persisting anything, dedupe idempotently by the provider event id, then ACK 200 fast and do the real work in a background task. Use when adding or reviewing a webhook or callback endpoint, wiring signature verification, handling retried or duplicate deliveries, guarding against SSRF from payload URLs, or asking how inbound provider events are processed here. Not for calling out to a provider's API (see ai-integration) or the background worker mechanics themselves (see celery-tasks).

  • Zod forms

    Deadlymind/nanolama/skills/zod-forms Skill

    1★ repo

    Defines typed forms with Zod 4 where one z.object schema is the single source of both the TypeScript type and runtime validation, coercing string inputs with z.coerce.number() and resolving error messages through next-intl keys. Use when writing or reviewing a Zod schema, wiring react-hook-form or a Server Action validator, fixing a Select "all" sentinel that fails validation, coercing numeric or date inputs, translating validation messages, or migrating a schema from Zod 3 to Zod 4. Not for DRF-side field validation or the shared client/server contract (see drf-zod-contract), locale message wiring itself (see i18n-rtl), or mutation/query plumbing (see react-query).

  • Mcp security review

    alidevai/chiron_agent/.claude/skills/mcp-security-review Skill

    no license1★ repo

    Bir MCP sunucusunu veya tool'u sisteme baglamadan once guvenlik acisindan denetleme prosedurudur. MCP sunuculari dosya sistemi, terminal, e-posta, GitHub, veritabani veya broker gibi yuksek yetkili kaynaklara erisebildigi icin baglanti oncesi zorunlu incelemedir.

  • Formatter

    RudrenduPaul/skillguard/examples/skill-set-clean/formatter Skill

    1★ repo

    A second minimal, well-behaved fixture skill (Python hook) used to test SkillGuard's skill-set happy path (zero findings, exit code 0, no SG09).

  • Finishing a development branch

    yigityildiz0/universal-ai-skill-library/skills/archive-variants/finishing-a-development-branch Skill

    no license1★ repo

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting.