feature-spec

Feature specification and planning guidelines for software engineers. This skill should be used when writing PRDs, defining requirements, managing scope, prioritizing features, or handling change requests. Triggers on tasks involving feature planning, specification writing, stakeholder alignment, or scope management.

설치로 이동 파일 검토

저장소: pproenca/dot-skills
최근 소스 활동: 2026년 5월 27일 09:50
감지된 SKILL.md 언어: 영어
스타: 211
포크: 18

설치 방법

기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.

AI 어시스턴트로 설치

이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/pproenca/dot-skills/tree/master/skills/.experimental/feature-spec.

직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.

npx skills add https://github.com/pproenca/dot-skills --skill feature-spec

명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.

로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.

소스 파일 검토

설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.

파일 탐색기

48 개 파일

SKILL.md

소스 지침 · 읽기 전용 미리보기

name: feature-spec
description: Feature specification and planning guidelines for software engineers. This skill should be used when writing PRDs, defining requirements, managing scope, prioritizing features, or handling change requests. Triggers on tasks involving feature planning, specification writing, stakeholder alignment, or scope management.

# Software Engineering Feature Specification and Planning Best Practices Comprehensive feature specification and planning guide for software engineers, product managers, and technical leads. Contains 42 rules across 8 categories, prioritized by impact to prevent scope creep and ensure project success. ## When to Apply Reference these guidelines when: - Writing PRDs or feature specifications - Defining requirements or user stories - Managing scope and preventing scope creep - Prioritizing features and backlog items - Handling change requests - Aligning stakeholders on project goals ## Rule Categories by Priority | Priority | Category | Impact | Prefix | |----------|----------|--------|--------| | 1 | Scope Definition | CRITICAL | `scope-` | | 2 | Requirements Clarity | CRITICAL | `req-` | | 3 | Prioritization Frameworks | HIGH | `prio-` | | 4 | Acceptance Criteria | HIGH | `accept-` | | 5 | Stakeholder Alignment | MEDIUM-HIGH | `stake-` | | 6 | Technical Specification | MEDIUM | `tech-` | | 7 | Change Management | MEDIUM | `change-` | | 8 | Documentation Standards | LOW | `doc-` | ## Quick Reference ### 1. Scope Definition (CRITICAL) - `scope-define-boundaries` - Define explicit scope boundaries - `scope-document-assumptions` - Document all assumptions explicitly - `scope-work-breakdown` - Break scope into measurable work items - `scope-define-mvp` - Define MVP before full feature set - `scope-stakeholder-signoff` - Get stakeholder signoff on scope ### 2. Requirements Clarity (CRITICAL) - `req-specific-measurable` - Write specific, measurable requirements - `req-user-stories` - Structure requirements as user stories - `req-avoid-solution-language` - Avoid solution-specific language - `req-functional-nonfunctional` - Separate functional and non-functional - `req-consistent-terminology` - Use consistent terminology - `req-traceability` - Maintain requirements traceability ### 3. Prioritization Frameworks (HIGH) - `prio-moscow-method` - Use MoSCoW prioritization method - `prio-rice-scoring` - Apply RICE scoring for objectivity - `prio-value-vs-effort` - Map value vs effort explicitly - `prio-dependencies-first` - Identify and order dependencies - `prio-kano-model` - Apply Kano model for feature classification ### 4. Acceptance Criteria (HIGH) - `accept-given-when-then` - Use Given-When-Then format - `accept-testable-criteria` - Write testable acceptance criteria - `accept-edge-cases` - Include edge cases in acceptance - `accept-definition-of-done` - Define clear definition of done - `accept-avoid-over-specification` - Avoid over-specification ### 5. Stakeholder Alignment (MEDIUM-HIGH) - `stake-identify-stakeholders` - Identify all stakeholders early - `stake-early-feedback` - Gather feedback early and often - `stake-conflict-resolution` - Resolve conflicts explicitly - `stake-communication-plan` - Establish communication cadence - `stake-success-metrics` - Align on success metrics ### 6. Technical Specification (MEDIUM) - `tech-system-context` - Document system context and dependencies - `tech-api-contracts` - Define API contracts before implementation - `tech-data-model` - Specify data models and schema changes - `tech-error-handling` - Plan error handling and recovery - `tech-performance-requirements` - Specify performance requirements - `tech-security-considerations` - Document security considerations ### 7. Change Management (MEDIUM) - `change-formal-process` - Use formal change request process - `change-impact-assessment` - Assess full impact before approval - `change-version-tracking` - Version all specification documents - `change-scope-freeze` - Implement scope freeze periods - `change-defer-log` - Maintain deferred items log ### 8. Documentation Standards (LOW) - `doc-single-source` - Maintain single source of truth - `doc-consistent-templates` - Use consistent document templates - `doc-decision-records` - Document key decisions with context - `doc-accessible-format` - Keep documentation accessible - `doc-glossary-terms` - Define project terminology

GitHub에서 보기

검색으로 돌아가기 설치로 돌아가기

ray-llm

LLM workloads on open-source Ray (pinned to 2.57) — OpenAI-compatible serving with ray.serve.llm (vLLM-backed LLMConfig + build_openai_app) and batch inference with ray.data.llm (build_processor). Corrects the stale defaults a model produces — the archived ray-llm repo and its YAML configs, hand-rolled vLLM engines inside plain Serve deployments, the removed build_llm_processor name, deprecated boolean stage flags, top-level LLMServer/LLMRouter imports, free-form accelerator strings, one-deployment-per-LoRA-adapter designs — with the 2.57 idioms (stage configs, placement_group_config over hand-rolled PGs, deployment_config autoscaling, dynamic LoRA multiplexing, prefix-cache-affinity routing, the full OpenAI endpoint surface). Use when writing, reviewing, or productionizing LLM serving or batch inference on Ray. Classic-ML Ray (Train/Tune/Data/Serve/clusters) lives in the sibling ray skill.

2026-08-15

ray

Production Ray (open-source, pinned to 2.57) for classic-ML workloads from training to serving — Ray Train, Tune, Data, Serve, Core, and cluster deployment on KubeRay. Corrects the older-corpus defaults a model reaches for (ray.air session reporting, Trainer-inside-Tuner, tune.run, map_batches concurrency=, DatasetPipeline/to_torch, max_concurrent_queries, RayServeHandle + ray.get, Deployment.deploy, ray.state, ray.get-in-a-loop) with the 2.57 idioms that replaced them (Train V2 defaults, driver-function tuning, compute strategies, streaming datasets, DeploymentHandle/DeploymentResponse, serve build/deploy, ray.util.state, KubeRay CRDs and Jobs API). Use when writing, reviewing, or productionizing Python code that touches Ray distributed training, data pipelines, hyperparameter tuning, model serving, or Ray cluster operations. LLM serving/batch-inference on Ray lives in the sibling ray-llm skill.

2026-08-15

mlflow-3

MLflow 3 (open-source, pinned to 3.15) for classic-ML MLOps — logging and registering models, promoting versions across dev/staging/prod, standing up a tracking server, evaluating with gates, and serving. Corrects the MLflow 2-era defaults a model reaches for (artifact_path, registry stages and get_latest_versions, top-level mlflow.evaluate with baseline_model, runs-URI registration, pickle serialization, mlruns file stores, MLServer serving) with the MLflow 3 idioms that replaced them (named LoggedModels, aliases and copy_model_version, models.evaluate plus validate_evaluation_results, skops/torch.export defaults, database backends, the FastAPI scoring server). Use when writing, reviewing, or migrating Python code that touches MLflow tracking, the model registry, evaluation, or serving.

2026-08-15

이 저장소의 모든 Skills 보기

feature-spec

소스 정보

설치 방법

AI 어시스턴트로 설치

소스 파일 검토

이 저장소의 다른 Skills

AI 어시스턴트로 설치

이 저장소의 다른 Skills