Loading...
Loading...
Found 2,002 Skills
Phase 3 of the feature workflow – Complete the acceptance closed loop. Two tasks: First, check layer by layer against {slug}-design.md to verify if the implementation deviates from the plan; if deviations are found, fix them immediately instead of just "noting them down" in the report. Second, integrate this feature into the project's overall architecture documentation. Finally, produce a {slug}-acceptance.md as the closed-loop proof for the entire workflow. Predecessor dependency easysdd-feature-implement must be completed. Trigger scenarios: User says "The feature is done, let's accept it", "Do the final check", "Prepare for merge", "Generate the acceptance report".
Grafana Mimir scalable long-term metrics storage. Covers architecture (distributor/ingester/compactor/querier/ query-frontend/store-gateway/ruler), deployment modes (monolithic/microservices), configuration, Prometheus remote write, PromQL querying, multi-tenancy, compaction, and operations. Use when working with Mimir for metrics storage, scaling Prometheus, configuring Mimir clusters, writing PromQL, or debugging Mimir.
Grafana Pyroscope continuous profiling platform. Covers instrumentation of Go/Java/Python/Ruby/Node.js/ .NET/Rust apps via SDKs or eBPF (Alloy), flame graph analysis, ProfileQL queries, server configuration and architecture, Grafana Cloud Profiles integration, and trace-profile linking (Span Profiles). Use when working with profiling data, instrumenting apps for Pyroscope, analyzing performance profiles, or deploying Pyroscope server.
Grafana Loki log aggregation and LogQL query language. Covers LogQL syntax (log queries, metric queries, label matchers, line filters, parsers: json/logfmt/pattern/regexp/unpack, label filters, line_format), Loki architecture, log ingestion via Alloy/Promtail/Fluent Bit, structured metadata, and Logs Drilldown. Use when writing LogQL queries, configuring Loki, troubleshooting log pipelines, or analyzing logs.
Grafana Tempo distributed tracing backend. Covers TraceQL query language (span selectors, attribute scopes, pipeline operators, structural operators, metrics functions), trace ingestion via OTLP/Jaeger/Zipkin, Tempo architecture (distributor/ingester/compactor/querier/metrics-generator), full configuration reference with YAML, metrics-from-traces (span metrics, service graphs, TraceQL metrics), deployment modes (monolithic/microservices/Helm/Kubernetes), multi-tenancy, performance tuning, caching, and HTTP API. Use when working with distributed traces, writing TraceQL queries, deploying Tempo, configuring trace pipelines, or setting up Grafana-Tempo integrations (traces-to-logs, traces-to-metrics, traces-to-profiles).
Implements CQRS with event sourcing on the iii engine. Use when building command/query separation, event-sourced systems, or fan-out architectures where commands publish domain events and multiple read model projections subscribe independently.
Draft or update requirement documents under `easysdd/requirements/` for the project — describe a capability's "reason for existence, solution approach, and boundaries" using **user stories + plain language**, so non-technical readers can quickly grasp the key highlights of the system. Layered with architecture: requirement is the "problem space" (why this capability is needed), while architecture is the "solution space" (what structure is used to implement it). Two modes: new (draft a new requirement doc from scratch), update (refresh an existing doc based on new materials or implementation changes). Single-target rule — only modify one document at a time. Trigger scenarios: when the user says "fill in a requirement doc", "write down the requirements for this capability", "update the requirements directory", or when it is found during the feature-design phase that there is no corresponding requirement for the capability to be implemented this time.
Phase 1 of the feature workflow — Draft a design document for the new feature, serving as the sole input for subsequent implementation and acceptance. First gather evidence (read architecture docs, review relevant code, grep to prevent term conflicts, check archives), then write a complete first draft in one go (including YAML frontmatter + three-tier structure + test design), submit it to the user for overall review, and iterate until approval. After approval, extract {slug}-checklist.yaml from {slug}-design.md for use in the next two phases. Trigger scenarios: "Start designing the solution", "Write design doc", "Prepare to implement XX", with the prerequisite that you already know what to do, who it's for, and how to define success.
Document the finalized tech stack selections, architecture decisions, long-term constraints, and coding conventions in the project into searchable permanent records. No one will remember why X was chosen six months later, but with decision documents, at least the background can be understood before making changes next time. Four categories: tech-stack (which tools/libraries/frameworks to use), architecture (how the system is organized), constraint (what is not allowed), convention (what is uniformly done). Trigger scenarios: Proactively trigger after making important choices during feature-design or issue-analyze, or when the user says "record the decision", "archive tech selection", "ADR", "record this constraint", "write down the convention". Only archive finalized decisions; do not archive proposed solutions under discussion.
Phase 3 of the feature workflow – Complete the acceptance closed-loop. Four tasks: 1. Check layer by layer against {slug}-design.md to verify if the implementation deviates from the plan; fix any deviations on the spot instead of just "noting them" in the report. 2. Incorporate this feature into the project's overall architecture documentation. 3. If this feature changes the user story or boundaries of the corresponding requirement, update the requirement doc accordingly. 4. If this feature originated from a roadmap item, change the status of the corresponding entry in roadmap items.yaml to done and sync it with the main document. Finally, produce a {slug}-acceptance.md as the closed-loop proof for the entire workflow. Prerequisite: cs-feat-impl is completed. Trigger scenarios: User says "The feature is done, let's accept it", "Do the final check", "Prepare for merge", "Generate the acceptance report".
Draft or update requirement documents under `codestable/requirements/` for the project — use **user stories + plain language** to describe a capability's "reason for existence, solution approach, and boundaries", so non-technical readers can quickly understand the highlights of the system. Layered with architecture: requirement is the "problem space" (why this capability is needed), while architecture is the "solution space" (what structure is used to implement it). Two modes: new (draft a new requirement doc from scratch), update (refresh an existing doc based on new materials or implementation changes). Single-target rule — only modify one document at a time. Trigger scenarios: the user says "fill in a requirement doc", "write down the requirements for this capability", "update the requirements directory", or during the feature-design phase, it is found that there is no corresponding requirement for the capability to be implemented this time.
Enter this sub-process when conducting code optimization — handle tasks where 'behavior remains unchanged, structure changes' (structure / performance / readability). Shift single-module internal optimization from 'AI random refactoring' to 'first scan to generate a checklist, confirm each item with the user, execute step-by-step according to the method library, and require manual approval for each step'. Trigger scenarios: Users mention phrases like 'optimize it / refactor / rewrite / split it / poor performance / code is too long' without any accompanying behavior changes. Do not handle new requirements (route to feature), bugs (route to issue), or cross-module architecture restructuring (route to architecture + decisions).