复制这段 Prompt，发给你正在使用的 AI 助手。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/TheSoftwareHouse/agentic-collections.正在加载仓库 README…
已展示 40 / 58 个已收集 Skill。
Writes TSH's implementation plan as a committed file at specifications/<task-id>/<task-name>.plan.md: phased tasks that each name their files and a verifiable Definition of Done, technical context persisted for implementers, explicit parallel groups. Use when…
原文语言：英语
Finds and fixes the root cause of a bug: pins the symptom, reproduces it, secures a failing test — existing, corrected or new — narrows to the cause with evidence rather than plausibility, measures how far the fix reaches before applying it minimally, and…
原文语言：英语
Implements a feature, ticket, or plan end to end from the main conversation: confirms a plan file exists, delegates each task to implementer subagents — in parallel where the plan allows — gates on their reports, then closes with the plan's final verification…
原文语言：英语
Creates a new workspace in a project's `<project>-context` knowledge base — the folder, its README index, its CLAUDE.md with exactly one named owner, and its row in the area map, all in one change. Use when a new layer or area of such a project needs its own…
原文语言：英语
Scaffolds a project's context repository — a knowledge base with named owners per project and delivery layer, one folder for all decision records, a link-and-table quality gate, and a Claude Code marketplace for the project's own extensions — then enables it,…
原文语言：英语
Reads a project's knowledge base — the `<project>-context` repository beside its code: scope, accepted decisions, vocabulary, who owns what — before work that depends on it, and cites the document behind every project fact. Use when a task in a repository of…
原文语言：英语
Finds and repairs broken references in a project's `<project>-context` knowledge base — relative links that no longer resolve, filenames that are not kebab-case, and markdown tables that render wrongly — using the repository's own checker scripts. Use when…
原文语言：英语
Adds or updates a document in a project's knowledge base — the `<project>-context` repository — picking the owning workspace, applying the state-of-today rule, updating the workspace index, and naming the owner who reviews it. Use when something learned,…
原文语言：英语
Sets up and maintains the project-context files Claude Code loads — root and nested `CLAUDE.md`, path-scoped rules in `.claude/rules/`, and a decision-record index — so a repository's conventions reach the model without bloating every session. Use when a…
原文语言：英语
Configures TypeScript for browser-targeted frontend projects: which version to pin, the tsconfig baseline for a bundler-resolved app, and the React + Vite project layout. Use when starting a frontend project, editing a frontend tsconfig, diagnosing JSX or…
原文语言：英语
Runs an exhaustive evidence-based GCP cost and labelling audit: reads Terraform first, then validates against the live project with read-only gcloud calls, finds drift and shadow resources, walks every service family for waste and right-sizing, checks label…
原文语言：英语
Configures TypeScript for Node.js server projects: which version to pin, the tsconfig baseline for a Node-resolved runtime, and the decorator-metadata settings NestJS and TypeORM require. Use when starting a Node service, editing a server tsconfig, diagnosing…
原文语言：英语
TSH practices for defining an AWS Lambda service on OSLS: which libraries we use and which we avoid, how a serverless project is structured, service and stage configuration, least-privilege IAM without wildcard resources, per-function reserved concurrency,…
原文语言：英语
Decides which Claude Code extension a need calls for — skill, subagent, hook, or plugin — and then writes it. Use when building or changing any of those four, when Claude should do something automatically or every time, when a workflow keeps getting pasted…
原文语言：英语
One-shot setup of a project's Claude Code context. Audits what already loads, then creates or repairs root and nested `CLAUDE.md`, path-scoped rules, and the decision-record archive with its index by running the owning tsh-core skills in order, and wires…
原文语言：英语
Applies TSH's writing standard to any technical document — README, CHANGELOG, ADR, RFC, runbook, PR description, ticket, user story, bug report or test plan — so it leads with the conclusion, states only verified facts, and is short enough to be read. Use…
原文语言：英语
Configures Kubernetes workloads to a production standard: choosing between Deployment, StatefulSet, DaemonSet and Job, resource requests and limits and the QoS class they produce, readiness/liveness/startup probes, PodDisruptionBudgets and anti-affinity,…
原文语言：英语
Selects cloud services and a multi-cloud topology using an explicit decision framework: which of the six multi-cloud patterns fits the actual driver, how AWS, Azure and GCP services map onto each other, where a cloud-agnostic abstraction pays for itself and…
原文语言：英语
Designs and implements CI/CD pipelines on GitHub Actions, GitLab CI, Bitbucket Pipelines, Azure Pipelines or Jenkins: stage structure and caching, deployment strategy (rolling, blue-green, canary), OIDC federation for cloud credentials instead of stored keys,…
原文语言：英语
Implements metrics, logs, traces and alerting to a standard that supports an on-call rotation: choosing a stack (Prometheus/Grafana, Loki, Tempo or Jaeger, CloudWatch, Datadog, OpenTelemetry), RED and USE metrics, SLOs with error budgets, alerts that fire on…
原文语言：英语
Chooses and implements a secrets management approach for cloud and Kubernetes workloads: cloud-native secret stores versus Vault versus Sealed Secrets or External Secrets, OIDC federation for CI/CD instead of long-lived keys, rotation policy, and audit…
原文语言：英语
The cloud-agnostic cost framework TSH provisions against: matching a workload to a pricing model (reserved, committed-use, spot, serverless), storage tiering with lifecycle policies, the mandatory cost-allocation tag set and how to enforce it, right-sizing…
原文语言：英语
The mechanical capture contract for UI verification: drives the playwright-cli against the pinned dev server URL to collect actual.png, computed-styles.json and a11y-snapshot.yml into the iteration artifact directory. Works with no design reference at all;…
原文语言：英语
Runs one UI verification pass against Figma: delegates fresh Playwright-CLI capture of the running app to ui-capture-worker, then the design comparison to ui-reviewer, and returns PASS, FAIL, or VERIFICATION NOT RUN with a complete difference table. Read-only…
原文语言：英语
The standard for judging implemented UI against its Figma design: EXPECTED comes only from the Figma MCP, ACTUAL only from live Playwright-CLI capture artifacts, compared across structure, layout, dimensions, visual and components under strict tolerances,…
原文语言：英语
Transforms an approved epic and story list into Jira-ready issues against a benchmark template — field mapping, Jira markdown, completeness validation, the formatting review and the Gate 2 push approval — and imports an existing Jira backlog into the same…
原文语言：英语
Runs the business-analysis workflow end to end from the main conversation: turns discovery workshop material — transcripts, Figma, PDFs, codebase context — into Jira-ready epics and user stories and a delivery roadmap, behind five human review gates,…
原文语言：英语
Audits UI against WCAG 2.1 AA and reports violations with their success criterion: semantic structure and heading order, keyboard operability and focus management, ARIA correctness, colour contrast, text resize and reflow, and axe-core automated scanning. Use…
原文语言：英语
Azure-specific Terraform patterns and Well-Architected defaults: VNet with per-subnet NSGs, AKS with Workload Identity and Entra ID RBAC, PostgreSQL and MySQL Flexible Server on private DNS, Blob Storage with the right redundancy tier, Application Gateway…
原文语言：英语
GCP-specific Terraform patterns and Architecture Framework defaults: custom-mode VPC with secondary ranges for GKE, private clusters with Workload Identity and Dataplane V2, Cloud SQL on private IP, Cloud Storage with uniform bucket-level access, Cloud Run…
原文语言：英语
Guides implementation and review of NestJS 11 REST APIs with TypeScript, @nestjs/cqrs, TypeORM 0.3, and @nestjs/platform-express. Use when bootstrapping a service, organizing vertical feature slices, adding CQRS behavior, or implementing and reviewing REST…
原文语言：英语
Configures TypeScript for AWS Lambda services bundled by Serverless Framework or OSLS: which Node runtime and TypeScript version to target, the ESM tsconfig baseline for bundler-emitted handler code, and choosing between esbuild and webpack with ts-loader.…
原文语言：英语
Implements and reviews AWS Lambda handlers in TypeScript: the thin-handler and pure-service split, middleware chain ordering, schema validation at the event boundary, the error hierarchy that maps to HTTP responses, structured logging with the request id, and…
原文语言：英语
Gathers and expands the business context around a task or workshop topic: pulls what is known from task trackers, knowledge bases, documents and designs, finds the gaps, resolves them with the user, and writes a research report. Use before committing to a…
原文语言：英语
Entry point for producing, reviewing and maintaining a per-product domain dictionary — the canonical business-term glossary, not domain-driven design. Run /tsh-product-management:domain-dictionary with a project name, a workshop directory of transcripts, PDFs…
原文语言：英语
Turns processed workshop materials into a business-oriented backlog: an approved intent brief first, then epics as independently demonstrable vertical slices with a delivery contract, and user stories with source traceability and GIVEN/WHEN/THEN acceptance…
原文语言：英语
Produces, reviews and maintains a per-product domain dictionary — canonical business terms, their source-language surface forms, and where a UI label differs from the identifier — through Harvest, Reconcile and Interview modes, checked by eleven review passes…
原文语言：英语
Cleans a raw workshop or meeting transcript into a structured, business-relevant document — small talk and filler removed, content grouped by discussion topic, with decisions, action items and open questions extracted. Use before any backlog extraction when…
原文语言：英语
Systematically reviews an approved epic and story list for gaps, missing edge cases and delivery-readiness problems, then produces individually accept-or-reject suggestions that refine the backlog before Jira formatting. Runs Lite or Full analysis passes over…
原文语言：英语
Ship a change to a plugin in this marketplace — choose the version bump, write the CHANGELOG entry, and announce it. Use when releasing, shipping or publishing a plugin change, bumping a plugin version, adding a changelog entry, or when asked how teammates…
原文语言：英语
暂时无法加载仓库 README。你仍可浏览下方的 Skill 目录。