all publishers

NinjaSln-labs

@ninjasln-labs source repo

97 published skills

  1. ▌
    Version Management · ninjasln-labs bundle
    Universal version management for any software artifact, independent of any VCS. Decides the next version from the change set under Semantic Versioning (MAJOR/MINOR/PATCH, prerelease, build metadata), keeps exactly one version source, maintains a Keep-a-Changelog CHANGELOG, and marks releases — VCS tags when git is available, otherwise a RELEASES manifest. Judges breaking versus compatible changes against the public contract (including implicit interfaces), applies deprecate-then-remove policies, handles immutable releases (yank/deprecate, never re-release), audits version consistency across files, and aligns multi-artifact releases. Use when choosing or bumping a version number, writing a CHANGELOG or release notes, marking a release, planning a deprecation, or checking that version numbers agree across a project — including projects without version control. NOT for: git branching / commit / PR flow, or dependency pinning and vulnerability scanning.
    4 repo stars
  2. ▌
    Env Check · ninjasln-labs bundle
    Environment check: read-only health inspection of the local dev environment — toolchain presence/version/shadowing, PATH and proxy env vars, disk space and inodes, dev-port occupancy (--ports), dependency-tree integrity (node_modules, broken venvs), and WSL2/Windows interop (PATH injection, autocrlf, wsl.conf). Produces a structured report with fix commands; never executes fixes itself. Use when builds fail with "works on my machine" symptoms, commands resolve to wrong binaries, a proxy blocks installs, disk/inode space runs out, a dev port is occupied, or WSL PATH is polluted. NOT for: system performance tuning, security scanning (secrets/dependencies/config), or AI session health.
    4 repo stars
  3. ▌
    Skill Fit · ninjasln-labs bundle
    Skill fit (v2): derives a project's skill needs — tier T0–T4, evidence-backed requirement table against a versioned lexicon (count bounded by tier), coverage four-ways (served / in-catalog-unmounted / poor-fit / gap), and mount-tier advice with a two-value budget. Confirm gate (ask-user; scripts/sf-gate.py apply/verify/rollback): mount/move from 2.1.0, unmount from 2.2.0. Judges fit from skill bodies, not descriptions; catalog.yaml=supply, lexicon=demand. Writes feedback (and applied log when executing); optional privacy-stripped upstream issue. USER-INVOKED ONLY (/skill:skill-fit; no auto-invoke). Use to audit skill needs and, on confirm, apply reversible mount/move/unmount. NOT for: authoring skills; deleting skill source files.
    4 repo stars
  4. ▌
    Perf Check · ninjasln-labs bundle
    Machine performance check: read-only sampling diagnosis of the dev machine's speed — memory pressure (MemAvailable gauge, swap thrash rate), CPU (load vs cores, utilization sampling), WSL2 resource tuning (cgroup ceilings, .wslconfig with autoMemoryReclaim advice), disk IO await per device, top CPU/memory processes, and macOS memory pressure (compressor gauge). Judgements follow the USE method; every threshold carries a basis tag (consensus vs heuristic). Read-only, tuning suggestions are commands for the user — never executed. Use when the machine feels slow, builds stall, memory pressure or swap activity is suspected, a process eats CPU/memory, disk latency is suspect, or WSL2 vmmem/VM sizing needs review. NOT for: runnability checks (env-check), application load testing, or AI session health.
    4 repo stars
  5. ▌
    Pipeline 0to1 · ninjasln-labs
    NeonForge 本仓的 0→1 阶段流水线推进器(ADR-026):9 段+横切审计/经验沉淀, 工件冻结为唯一接口、出口闸红不放行、闸结果记 .handoff。当开始新一段、段内产出 工件、段出口过闸、或需要判断「现在在哪段/下一步做什么」时使用。只管推进与拦截, 不替段内技能干活(各段有自己的执行技能,见段表)。仅适用于 NeonForge 仓——正文绑 ADR-026、docs/decisions、docs/audits、.handoff 与段6 闸这套布局,别的仓没有即不适用。 NOT for: 段内干活本身(写阶段契约用 stage-spec、拆计划用 writing-plans、执行计划用 executing-plans、跑阶段 DoD 门禁用 stage-gate)——本件只判「现在在哪段、能不能放行」。
    4 repo stars
  6. ▌
    Agent Dispatch · ninjasln-labs bundle
    User-invoked only: run it when the user explicitly asks to hand work to an external agent CLI, never on your own initiative. On enable it probes the machine first — which agent CLIs are on PATH, and which LLM each one runs, read from that CLI's own --help / --list-models, never from memory or this file — then asks the user, one question at a time, to pick the agents, their model modes, and whether to append. It drives the loop after that: a task brief carrying only checked-in artifact paths plus an output format, an isolated worktree, a background run, and admission only after the calling project's own gates pass. Four rules hold whoever is picked: no self-review, outputs gated before merge, briefs carry no secrets or handoff stores, and the current driver may do work but never audits this session's output. Use for 派给外部 agent / 换个模型来审 / 调遣 agent. NOT for: doing the work yourself, or accepting the output (that stays with the caller), or dispatching where no gates were declared — ask first.
    4 repo stars
  7. ▌
    LLM Gateway Ops · ninjasln-labs bundle
    Operate the standing configuration of an application's model calls: multi-provider access over openai-compatible endpoints, capability matrices, routing and fallback chains, quota and rate-limit budgets, inference cost attribution, and the seven provider-specific failure classes (rate limits, auth, bad request, content filtering, server error, timeout, response-shape drift). Use when wiring a second provider, choosing a fallback chain, capping spend or throughput, or naming which model tier served a request. NOT for: triaging one reported model call that failed — root-cause tracing, severity grading, shipping a fix, closing it out; prompt design or model evaluation; fine-tuning and training; domain modelling; general observability beyond LLM-specific amounts. Platform model names, endpoints, prices, and timeouts change often — verify against the provider's current documentation. No skill name implied: the boundary is the task.
    4 repo stars
  8. ▌
    Problem Handling · ninjasln-labs
    Problem handling: one evidence-driven pipeline from a reported symptom to a shipped fix — evidence-first intake, root-cause tracing (5 Whys plus RCA tools, falsifiable experiments), cognitive-bias defenses, dual-channel research, severity grading with a P0/P1 restore-first fast path, classify and scope, workaround-vs-permanent-fix decision, TDD fix, verification, and a blameless close with known-error capture plus a 3-strikes design escalation. Use when a problem, bug, error, UX complaint, or behavior gap is reported, before jumping to a fix. NOT for: a pure code bug whose root cause is all you need — reproduce, isolate, fix; designing the standing configuration of a system that repeatedly calls an external service (provider choice, routing order, quota and budget, the provider-shaped failure classes) — that is configuration work, not incident triage. No skill name implied: the boundary is the task.
    4 repo stars
  9. ▌
    Release Pipeline · ninjasln-labs bundle
    Release guardrails and multi-target release orchestration for packages and repos: OIDC / trusted publishing setup for PyPI and npm, provenance and attestation verification, single-version-source consistency, immutability checks, idempotent multi-registry release plans, and recovery from half-finished releases. Use when you are about to publish a version, wire a release workflow, or resume a release that failed partway across several registries. NOT for: choosing a version number (SemVer/CalVer choices and yank/deprecate semantics), branch and PR sequencing, configuring CI test stages, or writing a press release. USER-INVOKED ONLY.
    4 repo stars
  10. ▌
    Experiment Handoff · ninjasln-labs bundle
    Experiment handoff for mid-project experiments and spikes. Isolates a trial in a git worktree (default), an in-place branch, or a project copy; records a small experiment doc (.experiments/<slug>.md plus a generated index); supports handing off to another agent/session; and on close merges the validated change back into the project (full or partial) or discards it, then cleans up the sandbox. Auto-detects VCS and the isolation strategy, and records the base revision. This skill is mounted but USER-INVOKED ONLY: the agent must NOT auto-invoke it — the user runs it explicitly as /experiment-handoff. Use when the user explicitly invokes /experiment-handoff to start, hand off, or close an experiment/spike. NOT for: the project-wide handoff store or resuming prior work on a project.
    4 repo stars
  11. ▌
    Product Marketing · ninjasln-labs bundle
    > Creates and updates `.agents/product-marketing.md` — shared product, audience, and positioning context that other marketing skills reference so users avoid repeating foundational information. Use when the user wants to create or update their product marketing context document, or mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' 'who is my target audience,' 'describe my product,' 'ICP,' 'ideal customer profile.' Use at the start of any new project before other marketing skills.
    4 repo stars
  12. ▌
    Playwright Best Practices · ninjasln-labs bundle
    Playwright best practices for E2E, component, API, visual, and accessibility testing: flaky-test fixes, Page Object Model, CI/CD, mocking, auth/OAuth, axe-core, uploads, WebSockets, mobile, GraphQL, PWA, Electron, and extensions. Use when writing or debugging Playwright tests. NOT for: non-Playwright frameworks (Cypress/Selenium-only) or general CI without Playwright.
    4 repo stars
  13. ▌
    Grill Me · ninjasln-labs bundle
    User-invoked entry that runs a /plan-grilling session — a relentless interview to sharpen a plan or design. Use when the user wants to stress-test a plan, decision, or idea before committing to it.
    4 repo stars
  14. ▌
    Ddd Scope · ninjasln-labs bundle
    DDD scope: converge vague requirements into executable DDD modeling inputs — problem statement, goals/non-goals, constraints, term seeds, and risk list. Use when converging fuzzy requirements into DDD modeling inputs or defining modeling scope.
    4 repo stars
  15. ▌
    Audit Item · ninjasln-labs
    Track audit/review findings as numbered issue files (.scratch/neonforge-v1/audit-items/NNN-slug.md) with id, severity, source audit, status (open/fixed/recorded), fix commit, regression test, and closing evidence, plus a summary index README that stage-gate enumerates. Use when an audit or review produces findings ("把审计发现入账" / "审计项"). NOT for: finding the issues (use code-review or the audit itself) — this skill only tracks them.
    4 repo stars
  16. ▌
    Core Rules · ninjasln-labs
    Global rules applicable to all projects/sessions across AI coding tools (Deep Code / Cursor, etc.). Four bottom lines: credential safety (no plaintext secrets), permission confirmation (confirm before write ops), long-task feedback (progress update within 60s), session progress (maintained in .agents/session.md). Use when handling passwords/credentials, write operations, long-running tasks, session records, or at any project start/end.
    4 repo stars
  17. ▌
    Skill Eval · ninjasln-labs
    Behaviorally evaluate a skill: define 3-5 representative tasks, run each N>=3 times with and without the skill loaded in fresh agents, compare pass rates, and report a comparison table plus concrete improvement items that feed back into the skill's SKILL.md. Use when a skill changes, at quarterly evaluation, or when accepting a new skill. NOT for: static description compliance — use skill-description-audit.
    4 repo stars
  18. ▌
    Stage Gate · ninjasln-labs
    Run a stage-completion gate for staged delivery (spec-kit): read the stage spec's DoD assertions and execute each one — unit tests, dual tsc, interaction tests, behavioral acceptance, coverage matrix, open audit items, push state — reporting PASS/FAIL per assertion with fresh command evidence. Verifies only, never fixes. Use when a stage is claimed complete or on "run the stage gate" / "跑阶段门禁". NOT for: single-shot verification (use verification-before-completion) or executing a plan (use executing-plans).
    4 repo stars
  19. ▌
    Stage Spec · ninjasln-labs
    Write or backfill a stage spec for staged delivery (spec-kit): turn a stage row of the phased design into a machine-verifiable contract — DoD assertions directly executable by stage-gate, a TDD grid (spec assertion -> failing test -> implementation -> refactor), deliverables, and explicit non-goals. No prose "done" statements. Use when starting a new stage ("写 S{N} spec" / "回填阶段 spec") or after the design's stage plan changes. NOT for: generic implementation plans (use writing-plans) or running the gate (use stage-gate).
    4 repo stars
  20. ▌
    To Tickets · ninjasln-labs bundle
    Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker. ACs written as machine-verifiable predicates (AI-ready, not prose — directly verifiable post-implementation). Use when the user wants to turn a plan or PRD into agent-ready tickets, split work with explicit blockers, or publish a tracer-bullet breakdown to a local issues folder or issue tracker.
    4 repo stars
  21. ▌
    Write Spec · ninjasln-labs
    Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.
    4 repo stars
  22. ▌
    Code Review · ninjasln-labs bundle
    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. Stage-end mode: fixed point is the parent of the stage's first commit, Spec axis checks the stage spec's DoD, output is a statusized open/fixed/recorded findings list. Use when the user wants to review a branch, a PR, work-in-progress changes, asks to "review since X", or at a stage completion ("阶段末评审").
    4 repo stars
  23. ▌
    Config Scan · ninjasln-labs
    Config scan: detect security misconfigurations in config files, Docker, and IaC. Use when reviewing configuration security for containers, Kubernetes, Terraform, or application settings.
    4 repo stars
  24. ▌
    Ddd Contexts · ninjasln-labs bundle
    Design bounded contexts and their ubiquitous language: boundaries, responsibilities, glossary, team ownership, and boundary ADRs. Use when defining bounded contexts.
    4 repo stars
  25. ▌
    Ddd Discover · ninjasln-labs bundle
    Collaborative domain discovery via event storming or domain storytelling, producing event streams, command/event candidates, hotspots, and ambiguity lists. Use when doing domain discovery (identifying events/commands/aggregates).
    4 repo stars
  26. ▌
    Ddd QA Chain · ninjasln-labs
    Run the quality verification chain—5 abstract verification layers (domain logic / contract / component interaction / E2E user journeys / visual regression) mapped onto the project's own test stack (unit runner, type checker, contract tests, e2e suite, visual regression), each with a gate, plus a run-all delivery gate and a DoD quality gate (deterministic assertions + probabilistic sample/threshold for model-driven behavior). Use when delivering or verifying a feature, before claiming work complete, or when asked to run full self-tests / quality checks. NOT for: stage-level DoD aggregation (use stage-gate) or single-shot verification (use verification-before-completion).
    4 repo stars
  27. ▌
    Decision Log · ninjasln-labs
    Record or query architecture decision records (ADR) — Nygard template (context/decision/consequences) with a proposed/accepted/superseded/rejected status state machine, written to docs/decisions/NNN-slug.md plus the index table update and HANDOFF reference sync. Use when a semantic ruling or adjudication happens in a stage, or on "记录裁定" / "写进决策日志" / "ADR" / querying "决策 X 的现状". NOT for: writing handoff docs (use project-handoff) — HANDOFF references ADR numbers, never copies them.
    4 repo stars
  28. ▌
    Git Workflow · ninjasln-labs bundle
    Git workflow skill: branching strategies, Conventional Commits, creating or reviewing PRs, resolving PR review comments, merging PRs (CI verification, auto-merge queues, post-merge cleanup), PR review threads, signed commits, merge conflicts, Git+CI/CD integration, git hooks (lefthook, captainhook, husky, pre-commit), and debugging hook-install failures in git worktrees. Use when doing any of the above. NOT for: creating releases (use github-release) or diagnosing BLOCKED/won't-merge PRs (use github-project).
    4 repo stars
  29. ▌
    Problem Dive · ninjasln-labs
    收到问题/异常/体验反馈时的问题深挖方法论:先看证据(日志/trace/记录)→ 顺序全读找全问题 → 根因追问(为什么×N + RCA 工具可选映射 + 实测证伪不猜)→ 拒绝特判/穷举(找通用机制)→ 尽调调研(≥2 独立渠道交叉验证)→ 项目语境检验 → 完整性审视(记录/复用/单源)→ 决策清单+小步推进 → 持续盘点闭环。含认知偏差防御(反例清单/可证伪预期)。当用户反馈 「体验完毕」「有问题」「报错」「卡住」「失败」「异常」「先看看」「分析一下」「怎么回事」等触发。 产出:根因 + 方案对比 + 决策清单(不直接修——修复落地归 problem-resolution-flow)。
    4 repo stars
  30. ▌
    Secrets Scan · ninjasln-labs
    Secrets scan: detect API keys, passwords, tokens, and other secrets in code. Use when you need to find hardcoded credentials and sensitive data in source code.
    4 repo stars
  31. ▌
    UI Animation · ninjasln-labs
    > Encodes Emil Kowalski's design-engineering philosophy: UI polish, component design, animation decisions, and the invisible details that make software feel great. Use when building or reviewing interfaces, improving UI polish, auditing animation timing/easing/motion, checking animation accessibility (prefers-reduced-motion), or making components feel responsive and deliberate.
    4 repo stars
  32. ▌
    Cicd Pipeline · ninjasln-labs
    Configure testing in CI/CD pipelines for GitHub Actions, Jenkins, and GitLab CI: shards, parallelization, wait-on health checks, and service containers. Use when configuring tests in CI/CD pipelines (GitHub Actions, Jenkins, GitLab).
    4 repo stars
  33. ▌
    Company Intel · ninjasln-labs bundle
    Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills.
    4 repo stars
  34. ▌
    Pixel Perfect · ninjasln-labs bundle
    Visual regression testing — pixel-by-pixel screenshot comparison against a baseline. TRIGGER when: user mentions "pixel-perfect", "visual regression", "screenshot diff", "snapshot mismatch", "toHaveScreenshot", "UI looks broken after changes", "compare before/after screenshots", "visual QA", "catch visual bugs", "design implementation check", "tests failing with screenshot", or wants to verify that code changes didn't break the UI visually. DO NOT TRIGGER when: user wants functional/behavioral testing (use playwright-skill), just wants a single screenshot (use screenshots skill), or asks about accessibility.
    4 repo stars
  35. ▌
    Plan Grilling · ninjasln-labs bundle
    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
    4 repo stars
  36. ▌
    Press Release · ninjasln-labs bundle
    Write an Amazon-style press release that defines customer value before building. Use when aligning stakeholders on a new product, feature, or strategic bet.
    4 repo stars
  37. ▌
    Proto Persona · ninjasln-labs bundle
    Create a proto-persona from current research, market signals, and team knowledge. Use when you need a working customer profile before deeper validation.
    4 repo stars
  38. ▌
    Security Scan · ninjasln-labs bundle
    Security scan: scan code for security vulnerabilities including OWASP Top 10, secrets, and misconfigurations, with severity thresholds. Use when you need comprehensive security analysis of a codebase.
    4 repo stars
  39. ▌
    UI Typography · ninjasln-labs bundle
    UI Typography: professional typography rules for UI design, web apps, software interfaces, and screen-based text — quotes, dashes, spacing, hierarchy, layout. ENFORCEMENT MODE: when generating any HTML/CSS/React/JSX UI with visible text, auto-apply silently. AUDIT MODE: when reviewing interfaces, flag violations and fixes. Trigger on UI/landing/component/dashboard/document generation or "fix the typography". NOT for: marketing copywriting strategy, print-only typesetting, or non-UI prose.
    4 repo stars
  40. ▌
    UI UX Pro Max · ninjasln-labs bundle
    UI/UX Pro Max design intelligence for web and mobile: searchable local database with styles, color palettes, font pairings, product types, UX guidelines, icons, GSAP motion presets, and chart types across major stacks (React, Next.js, Vue, Nuxt, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and more). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization — including design system and stack-guideline steps.
    4 repo stars
  41. ▌
    User Research · ninjasln-labs
    Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs help with any aspect of understanding their users through research.
    4 repo stars
  42. ▌
    UX Heuristics · ninjasln-labs bundle
    Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "users are confused", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "is this easy to use". Also trigger when reviewing a design for usability issues, improving form-completion rates, or evaluating information architecture and navigation. Covers Krug''s laws, Nielsen''s 10 heuristics, severity ratings, dark-pattern recognition, and accessibility. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.
    4 repo stars
  43. ▌
    Writing Plans · ninjasln-labs bundle
    > Write comprehensive implementation plans from a spec or requirements—break multi-step work into bite-sized tasks with exact file paths, complete code, and verification steps (DRY, YAGNI, TDD, frequent commits; no placeholders). Save plans to docs/superpowers/plans/. Use when you have a spec or requirements for a multi-step task, before touching code. NOT for: stage contract specs (DoD/gate assertions + TDD grid) — those are stage-spec, executed by stage-gate.
    4 repo stars
  44. ▌
    Ddd Aggregates · ninjasln-labs bundle
    Design DDD aggregates and aggregate boundaries from invariants: aggregate roots, entities, value objects, transaction boundaries, and cross-aggregate consistency strategies. Use when designing aggregate boundaries, invariants, transaction boundaries, or cross-aggregate consistency.
    4 repo stars
  45. ▌
    Ddd Subdomains · ninjasln-labs bundle
    Identify business capabilities and classify subdomains (Core/Supporting/Generic), producing core-domain declarations and ownership recommendations. Use when partitioning core/supporting/generic subdomains.
    4 repo stars
  46. ▌
    Event Storming · ninjasln-labs bundle
    EventStorming facilitation knowledge and reference across Big Picture, Process Modeling, and Design-Level formats. Use when: 'run EventStorming', 'model a domain', 'discover bounded contexts', 'Big Picture session', 'map domain events', 'find aggregates', 'DDD workshop', 'bounded context heuristics'. Actions: --big-picture / --process / --design-level (format guidance), --patterns (facilitation patterns/anti-patterns), --glossary, --notation, --remote. No args: interactive discovery — checks Miro for boards (if available), asks goal, recommends format. Not for agentic simulation — use /event-storming:simulation.
    4 repo stars
  47. ▌
    K6 Performance · ninjasln-labs
    k6 performance testing: modern load testing with thresholds, scenarios, custom metrics, and env-based BASE_URL. Use when load/performance testing with k6 (thresholds, scenarios, metrics).
    4 repo stars
  48. ▌
    Prd Driven Ddd · ninjasln-labs
    Transform product design documents (PRDs, flowcharts, prototypes, state machines, rules/AC) into a domain-driven design model: per-context ubiquitous language/glossary, event storming, bounded contexts and mapping, aggregates/entities/value objects, domain events and versioned integration events (Name:vN), read models, PRD-model traceability. Use when the user asks for DDD, domain modeling, event storming, aggregate design, bounded context mapping, versioned integration events, read models/CQRS, or PRD-driven strategic/tactical design. Also supports scenario-driven validation (post-modeling user scenario checks) and continuous ubiquitous-language management (term-to-code consistency, anti-drift).
    4 repo stars
  49. ▌
    Product Launch · ninjasln-labs bundle
    Plan a product launch with the ORB framework (owned, rented, borrowed channels) and a five-phase rollout, plus Product Hunt strategy and pre/post-launch checklists. When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' 'product update,' 'how do I launch this,' 'launch checklist,' 'GTM plan,' or 'we're about to ship.' Use this whenever someone is preparing to release something publicly. For ongoing marketing after launch, see marketing-ideas. For the offer being launched (bonuses, guarantees, scarcity, naming), see offers.
    4 repo stars
  50. ▌
    Project Intake · ninjasln-labs
    Take over a project as the receiving side — read HANDOFF.md and restore context by its 6 sections (metadata/snapshot/next steps/immediate ops/reference index/maintenance rules; snapshot deltas are one-liners — fetch details via git log or HANDOFF-ARCHIVE/ (pits.md / cycles.md / done.md; confirmed-fixed items live in the archive, not live HANDOFF). Execute suggested receiver actions (git init → .gitignore → first commit / read tickets / request credentials). Use when receiving a handoff, onboarding onto an existing repo, or resuming from HANDOFF.md.
    4 repo stars
  51. ▌
    Session Health · ninjasln-labs bundle
    Session Health: assess the current AI coding tool session — context compaction/condensation ratio, message count, context occupation cost, work nature, recoverability (git/handoff/runtime), and token economics — to judge continue vs new-session. Reads tool session storage read-only. Use when the user mentions context compaction, starting a new session, high context overhead, or long-session continuation (e.g. "go" / "keep going"). NOT for: auditing skill descriptions, full-codebase architecture analysis, or product-doc set audits.
    4 repo stars
  52. ▌
    Codebase Design · ninjasln-labs bundle
    Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
    4 repo stars
  53. ▌
    Coverage Matrix · ninjasln-labs
    Generate or maintain the coverage matrix (docs/tests/coverage-matrix.md): scan unit test names (describe/it in tests/unit/), the timeline event registry (TIMELINE_EVENT_SPECS in src/domain/timeline.ts), and stage-spec DoD assertions, then produce the three-way matrix (invariants<->tests / events<->tests / DoD<->gate) and flag gaps (invariant without test, event without assertion) into audit items. Use when at a stage end ("更新覆盖矩阵") or after adding invariants/events. NOT for: runtime enforcement — the matrix is a human-checked artifact, never a test gate.
    4 repo stars
  54. ▌
    Ddd Context Map · ninjasln-labs bundle
    Map relationships and integration strategies between bounded contexts: pattern selection, contract ownership, failure modes, and versioning strategy. Use when mapping bounded-context relationships, integration patterns, or contract ownership.
    4 repo stars
  55. ▌
    Dependency Scan · ninjasln-labs
    Dependency scan: detect CVEs and security issues in project dependencies. Use when you need to analyze packages for known vulnerabilities across npm, pip, cargo, and other ecosystems.
    4 repo stars
  56. ▌
    Executing Plans · ninjasln-labs
    Executing Plans: execute a written implementation plan — load the plan, review it critically, execute all tasks with per-task commits and review checkpoints, and report when complete. Use when you have a written implementation plan to execute in a separate session (use subagent-driven-development instead if subagents are available). NOT for: verifying a stage against its spec — that is stage-gate, which only verifies and never executes.
    4 repo stars
  57. ▌
    Frontend Design · ninjasln-labs bundle
    Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. Use when working with this skill's domain.
    4 repo stars
  58. ▌
    Jobs To Be Done · ninjasln-labs bundle
    Uncover customer jobs, pains, and gains in a structured JTBD format. Use when clarifying unmet needs, repositioning a product, or improving discovery and messaging.
    4 repo stars
  59. ▌
    Prd Development · ninjasln-labs bundle
    PRD development: build a structured Product Requirements Document that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative or feature.
    4 repo stars
  60. ▌
    Project Handoff · ninjasln-labs
    Generate/update a project engineering handoff document (HANDOFF.md) — reference-style delta structure: metadata / snapshot / next steps / immediate ops (commands + pitfalls) / reference index / maintenance rules. Records only delta not already in docs or commit log; one-line entries (details in commit messages); never copies (anti-dual-source); desensitized. Maintenance rules: update timing, one-line deltas, rolling archive to HANDOFF-ARCHIVE/ (pits.md / cycles.md / done.md), confirmed-fixed pitfalls/todos must be archived, backfill, decision-log sync (stage rulings -> docs/decisions/ ADRs, referenced by number, never copied). Use when handing off across sessions/tools, generating or updating HANDOFF.md, capturing project delta state, or after stage rulings. NOT for: resuming prior work — that belongs to project-intake.
    4 repo stars
  61. ▌
    Ddd Model Review · ninjasln-labs bundle
    Global model quality assessment: consistency, completeness, coupling analysis, and feedback-loop triggers. Use when evaluating domain model quality, consistency/completeness/coupling checks, or model evolution review.
    4 repo stars
  62. ▌
    Roadmap Planning · ninjasln-labs bundle
    Plan a strategic roadmap across prioritization, epic definition, stakeholder alignment, and sequencing. Use when turning strategy into a release plan that teams can execute.
    4 repo stars
  63. ▌
    Problem Statement · ninjasln-labs bundle
    Write a user-centered problem statement with who is blocked, what they are trying to do, why it matters, and how it feels. Use when framing discovery, prioritization, or a PRD.
    4 repo stars
  64. ▌
    Product Doc Audit · ninjasln-labs
    Product Document Audit: three-layer audit of a product documentation set (0-1 phase docs): 1) completeness against the 0-1 delivery doc panorama (required/optional), 2) each doc by type-specific checkpoints and core review dimensions, 3) cross-validate alignment. Produces readiness score (0-100), Critical/Major/Minor grading, authority rulings, deliverability judgment, and PRODUCT-DOC-AUDIT.md without modifying audited docs. Supports final project acceptance (four-layer go/no-go). Use when auditing or cross-validating product docs (PRDs, design docs, specs, domain docs, launch docs) for readiness, grading, contradictions, or go/no-go delivery decisions.
    4 repo stars
  65. ▌
    Delegated Research · ninjasln-labs bundle
    Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
    4 repo stars
  66. ▌
    Task Loop Progress · ninjasln-labs bundle
    Generate config + adapter for the generic long-task progress loop (scaffold task_loop_scaffold.py / task_loop_poll.py / task_loop_start.sh from templates/). Config-driven: adapter extracts numeric/percentage/stage progress via progress_extract — zero code changes per task. Supports local files, remote SSH fetch, stdout JSON, and terminal matching. Requires successful poll validation before start; on AGENT_LOOP_TICK, Agent must post chat_line to Chat. Use when the user asks for a task loop, progress loop, AGENT_LOOP_TICK, config+adapter templates, long-task polling, or provides a custom poll command.
    4 repo stars
  67. ▌
    Battle Card Builder · ninjasln-labs bundle
    Research and draft a competitive battle card from public evidence — every claim labeled and sourced. Use when a rep needs a field-action card, not a research report.
    4 repo stars
  68. ▌
    Ddd Openspec Bridge · ninjasln-labs bundle
    Map DDD tactical modeling artifacts into OpenSpec structured specifications for a smooth handoff from domain modeling to engineering implementation. Use when bridging domain modeling outputs to OpenSpec specs.
    4 repo stars
  69. ▌
    Ddd Tactical Review · ninjasln-labs bundle
    Detects anemic domain models, validates and refactors them into rich domain models, and enforces tactical DDD patterns (Entities, Value Objects, Aggregates, Domain Services, Domain Events). Use when the user asks to validate, review, or check domain models or DDD code; detect anemia; refactor domain objects; improve encapsulation; or mentions terms like "anemic model", "rich domain", "aggregate", "value object", "domain event", "ubiquitous language", "is this good DDD", "does this follow DDD", or "check my domain". Do NOT use for module or service boundary design, architectural decomposition, strategic DDD context mapping, or code outside the domain layer (DTOs, controllers, infrastructure adapters).
    4 repo stars
  70. ▌
    Customer Journey Map · ninjasln-labs bundle
    Create a customer journey map across stages, touchpoints, actions, emotions, and metrics. Use when diagnosing a broken experience or aligning a team on the full customer flow.
    4 repo stars
  71. ▌
    Positioning Workshop · ninjasln-labs
    Run a positioning workshop that surfaces target customer, unmet need, category, benefits, and differentiation. Use when your product messaging feels fuzzy, generic, or misaligned.
    4 repo stars
  72. ▌
    Systematic Debugging · ninjasln-labs bundle
    Systematic Debugging: find the root cause before proposing fixes — symptom fixes are failure; reproduce, isolate, and verify the fix addresses the actual cause. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
    4 repo stars
  73. ▌
    Test Data Generation · ninjasln-labs
    Test data strategies using Faker.js, factories, builders, and database seeding Use when generating test data, fixtures, or seeded databases.
    4 repo stars
  74. ▌
    Accessibility Auditor · ninjasln-labs
    Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification Use when running accessibility checks, WCAG compliance testing, or axe-core audits.
    4 repo stars
  75. ▌
    Architecture Patterns · ninjasln-labs bundle
    Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design (ports/adapters, dependency rule, in-memory adapters for unit tests). Use when designing clean architecture for a new microservice, refactoring a monolith to bounded contexts, implementing hexagonal or onion architecture, or debugging dependency cycles between application layers.
    4 repo stars
  76. ▌
    Market Landscape Scan · ninjasln-labs bundle
    Market Landscape Scan: map a market's segments, players, substitutes, and whitespace with cited evidence. Use when entering or re-evaluating a market before sizing, positioning, or picking competitors to study.
    4 repo stars
  77. ▌
    Marketing Copywriting · ninjasln-labs bundle
    Marketing copywriting: write, rewrite, or improve marketing copy for any page — homepage, landing, pricing, feature, about, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value proposition," "tagline," "subheadline," "hero section copy," "above the fold," "this copy is weak," "make this more compelling," or "help me describe my product." Use whenever website text must persuade or convert. NOT for: email copy, popup copy, or offer framing (bonuses/guarantees) — those belong to dedicated email/popup/offers skills when available.
    4 repo stars
  78. ▌
    Positioning Statement · ninjasln-labs bundle
    Create a Geoffrey Moore-style positioning statement. Use when clarifying who you serve, what problem you solve, your category, and why you're different from alternatives.
    4 repo stars
  79. ▌
    Web Design Guidelines · ninjasln-labs
    Review UI code for Web Interface Guidelines compliance (Vercel Labs guidelines via WebFetch or curl). Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
    4 repo stars
  80. ▌
    Workshop Facilitation · ninjasln-labs bundle
    Facilitate workshop sessions in a one-step, multi-turn flow. Use when an interactive skill needs consistent pacing, options, and progress tracking.
    4 repo stars
  81. ▌
    API Contract Validator · ninjasln-labs
    Validate API responses against OpenAPI/Swagger specifications, JSON Schema definitions, and consumer-driven contracts to prevent breaking changes Use when validating API responses against OpenAPI/JSON Schema/consumer contracts.
    4 repo stars
  82. ▌
    Deep Codebase Analysis · ninjasln-labs bundle
    Deep codebase analysis: read and analyze an entire software project's source to understand architecture, communication, design patterns, and business flows. Use when the user asks to analyze the overall structure of a whole codebase (exploring a new system, understanding architecture before maintenance, or scoping a refactor). NOT for: single-file edits, auditing one skill's SKILL.md, or reviewing a small diff — those belong to code-review / skill-description-audit.
    4 repo stars
  83. ▌
    Competitive Intel Watch · ninjasln-labs bundle
    Competitive Intel Watch: scheduled delta monitoring against a prior competitive snapshot. Use when tracking competitors on a cadence: material shifts only, cited evidence, battle-card update flags, runs unattended.
    4 repo stars
  84. ▌
    Ddd Domain Interactions · ninjasln-labs bundle
    Design collaboration mechanisms between building blocks: domain events, domain services, repository interfaces, and factories. Use when designing domain services, repositories, domain events, or factories.
    4 repo stars
  85. ▌
    Electron Best Practices · ninjasln-labs bundle
    Guide AI agents through Electron app development with React including security patterns, type-safe IPC, React integration, packaging with code signing, and testing. Keywords: electron, electron-vite, electron-forge, contextBridge, IPC, security, react, packaging, code signing, notarization, playwright, desktop app. Use when building secure Electron apps with React/TypeScript (IPC, packaging, testing).
    4 repo stars
  86. ▌
    Problem Resolution Flow · ninjasln-labs
    Problem Resolution Flow: end-to-end evidence-driven pipeline from symptom to shipped fix — locate, trace, grade severity first (P0/P1 fast path: restore before deep investigation), classify by type, scope, draft before research, cross-validate externally, decide workaround vs permanent fix, fix with a failing test, verify, close the loop with a no-blame lesson. Use when handling any bug, UX complaint, or behavior gap, before jumping to fixes. NOT for: root-cause investigation alone (use systematic-debugging) or the evidence-first intake methodology (use problem-dive).
    4 repo stars
  87. ▌
    Skill Description Audit · ninjasln-labs
    Skill Description Audit. User-level personal skill (canonical source in agent-skills). Cross-validation audit of an Agent Skill's SKILL.md description vs body: frontmatter compliance, capability claims matching the body, body non-emptiness (except thin-allowlist), trigger-word sufficiency, old-name residue via renames.yaml (boundary-aware, meta-mention filtered), H1 extraction that skips fenced code, and volatile-data externalization. Generates Problems/Recommendations/Acceptance-Criteria report in the target skill directory. Does not modify the audited SKILL.md. Use when auditing or cross-validating a skill description against SKILL.md body. NOT for: auditing product doc sets (PRDs/specs/launch docs) — use product-doc-audit.
    4 repo stars
  88. ▌
    Voice Of Customer Miner · ninjasln-labs bundle
    Mine public reviews, app stores, and forums for unmet needs, competitor weaknesses, and switching triggers — with quoted evidence. Use when you want customer voice without waiting on interviews.
    4 repo stars
  89. ▌
    Autonomous Investigation · ninjasln-labs bundle
    The protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs.
    4 repo stars
  90. ▌
    Discovery Interview Prep · ninjasln-labs
    Plan customer discovery interviews with the right goal, segment, constraints, and method. Use when preparing interviews for problem validation, churn research, or new product ideas.
    4 repo stars
  91. ▌
    Visual Regression Tester · ninjasln-labs
    Visual Regression Tester: screenshot comparison, diff detection, and CI integration using Playwright or Chromatic/Percy. Use when users request visual testing, screenshot testing, UI regression, visual diff, or Chromatic setup. Prefer pixel-perfect for free local flows; use this for Chromatic/Percy platform needs.
    4 repo stars
  92. ▌
    React Vite Best Practices · ninjasln-labs bundle
    React and Vite performance optimization guidelines. Use when writing, reviewing, or optimizing React components built with Vite. Triggers on tasks involving Vite configuration, build optimization, code splitting, lazy loading, HMR, bundle size, or React performance.
    4 repo stars
  93. ▌
    Typescript Best Practices · ninjasln-labs bundle
    Guide AI agents through TypeScript coding best practices including type safety, error handling, code organization, and architecture patterns. This skill should be used when generating TypeScript code, reviewing TypeScript files, creating new TypeScript modules, refactoring JavaScript to TypeScript, or when the user asks about TypeScript patterns, types, or coding standards. Keywords: typescript, types, coding standards, best practices, type safety, generics, architecture, refactoring. Use when working with this skill's domain.
    4 repo stars
  94. ▌
    Competitive Analysis Process · ninjasln-labs bundle
    Orchestrate a complete competitive analysis across six steps, from landscape to strategic direction. Use when you need the full picture, not a single scan or card.
    4 repo stars
  95. ▌
    Competitive Research Snapshot · ninjasln-labs bundle
    Research a competitive landscape with cited snapshots, a comparison matrix, and so-what implications. Use when a product decision needs competitive grounding, not a market report.
    4 repo stars
  96. ▌
    Verification Before Completion · ninjasln-labs
    > Run verification commands and confirm fresh output before claiming work complete—evidence before assertions, never claim done without verification. Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. NOT for: stage-level aggregation of a whole DoD spec — that is stage-gate, which runs the full gate and never fixes.
    4 repo stars
  97. ▌
    Intelligence Collection Disciplines · ninjasln-labs bundle
    Run competitive research like an intelligence agency: eight collection disciplines (OSINT to MASINT), signal-to-inference chains, and fusion. Use when one-source research isn't enough.
    4 repo stars