SP

Creates validated technical specifications for new features and bug fixes.

Install

mkdir -p .claude/skills/spec-creation && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13636" && unzip -o skill.zip -d .claude/skills/spec-creation && rm skill.zip

Installs to .claude/skills/spec-creation

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Шаг ① workflow: Создание ТЗ + ветка + коммит. Triggers: "создай ТЗ", "new feature", "новая фича", "bugfix". Использует IEEE 29148:2018 для валидации требований (≥85%). После валидации создаёт ветку feature/* или bugfix/* и коммитит spec.
237 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Create technical specifications (ТЗ)
  • Validate requirements using IEEE 29148:2018 standards
  • Create feature or bugfix branches
  • Perform initial commits of spec files
  • Refine requirements through multi-round validation
  • Assess requirements quality based on core attributes, context, description completeness, traceability, and prioritization

How it works

This skill creates technical specifications by iteratively validating requirements against IEEE 29148:2018 standards, then creates a new git branch and commits the validated spec.

Inputs & outputs

You give it
User request for a new feature or bugfix, or to create a technical specification
You get back
A validated technical specification file (`.ai/specs/{branch-type}-{slug}.md`), a new git branch (`feature/{slug}` or `bugfix/{slug}`), and an initial commit of

When to use spec-creation

  • Creating technical specifications
  • Initializing feature branches
  • Validating project requirements

About this skill

Spec Creation Skill

Шаг ① workflow — создание ТЗ с валидацией по IEEE 29148:2018, ветки и коммита.

Workflow Contract

entry:
  branch: main | master
  trigger:
    - "создай ТЗ"
    - "new feature"
    - "новая фича"
    - "bugfix"
    - "исправь баг"

exit:
  artifacts:
    - .ai/specs/{branch-type}-{slug}.md
  branch: feature/* | bugfix/*
  commit: "docs: add spec for {feature-name}"

recommended_next_skill: spec-implementer  # Рекомендуемый следующий skill для Codex

When to Use This Skill

  • User requests creating a technical specification (ТЗ, техническое задание)
  • User says "создай ТЗ", "напиши спецификацию", "создай spec"
  • User reports a bug → создать bugfix spec с красным тестом
  • Starting workflow step ① (per project workflow guide)

Output Location

Specifications are created in .ai/specs/ directory with naming pattern:

  • feature-{slug}.md for new features
  • bugfix-{slug}.md for bug fixes

A git branch will be created with pattern:

  • feature/{slug} for new features
  • bugfix/{slug} for bug fixes

The spec file will be committed to the new branch.

Core Principles

Iterative Requirement Refinement

This skill uses multi-round validation with IEEE 29148:2018 quality criteria:

Critical: A specification is NOT complete until validation achieves ≥85% score.

Progressive Disclosure

  • Keep spec template concise in SKILL.md
  • Reference detailed templates in references/ directory
  • Load templates only when needed

IEEE 29148:2018 Quality Assessment Framework

The requirements quality score is calculated from 5 sections, each containing specific criteria with maximum weight of 5 per criterion.

Section 1: Core Quality Attributes (40 points total)

CriterionWeightCheck
Necessary5Does the requirement define an essential capability/characteristic?
Unambiguous5Is there only one possible interpretation?
Complete5Are all necessary capabilities/characteristics/constraints described?
Consistent5Is it free of conflicts with other requirements?
Singular5Does it address only one concern (not compound)?
Feasible5Is it achievable with given constraints (time, budget, technology)?
Traceable5Can it be linked to stakeholder needs and business objectives?
Verifiable5Can fulfillment be measured through testing/inspection?

Section 2: Context & Rationale (20 points total)

CriterionWeightCheck
Implementation-free5Does it avoid dictating HOW to implement (WHAT vs HOW)?
Affordable5Is it within budget/resource constraints?
Bounded5Are scope boundaries clearly defined?
Rationale stated5Is the reason for this requirement explained?

Section 3: Completeness of Description (20 points total)

CriterionWeightCheck
Inputs defined5Are all inputs clearly specified (data, parameters, user actions)?
Outputs defined5Are expected outputs clearly described (return values, UI changes, side effects)?
Constraints identified5Are technical/business/environmental constraints noted?
Edge cases covered5Are error scenarios and boundary conditions addressed?

Section 4: Traceability & Stakeholders (10 points total)

CriterionWeightCheck
Stakeholder mapping5Can the requirement be linked to specific stakeholders/users?
Business value5Does it align with stated business objectives or user needs?

Section 5: Acceptance & Prioritization (10 points total)

CriterionWeightCheck
Prioritization clear5Is priority level specified (must-have vs nice-to-have)?
Success criteria5Are measurable acceptance criteria defined?

Maximum Score: 100 points Threshold: 85 points minimum to proceed

Iterative Validation Process

Round Structure

For each validation round:

  1. Display Current Requirements Version - Show the accumulated requirements in markdown format
  2. Calculate IEEE 29148 Score - Evaluate each criterion and calculate total
  3. Decision Point:
    • If score ≥ 85: Proceed to next phase
    • If score < 85: ask the user a concise clarification question
  4. Enrich & Re-evaluate - Update requirements with answers and re-score

Round 1: Core Requirements Validation

Initial Requirements Gathering:

## Initial Requirements

### Feature Overview
- **Feature name**: {from user}
- **Type**: {new feature/bug fix/enhancement}
- **Vision**: {one sentence}

### Core Requirements
- {Must-have requirements from user}

### Stakeholders
- {Target users, roles}

### Constraints
- {Technical/business constraints}

Evaluate using Section 1 (Core Quality Attributes) + Section 2 (Context & Rationale)

Common Gaps to Address via direct user questions:

  • Unambiguous: "Which specific notification channels?" (email, in-app, SMS?)
  • Complete: "What data needs to be stored for each notification?"
  • Feasible: "Are there rate limits or API constraints?"
  • Implementation-free: "What business outcome, not which library?"

Round 2: Technical Completeness Validation

Extended Requirements:

## Technical Requirements

### Functional Requirements
- {Specific functional behaviors}

### Non-Functional Requirements
- {Performance, security, usability}

### API & Database Changes
- {Endpoints, schemas, migrations}

### Frontend Changes
- {Pages, components, templates}

Evaluate using Section 3 (Completeness of Description)

Common Gaps to Address:

  • Inputs defined: "What parameters does the API accept?"
  • Outputs defined: "What response format/status codes?"
  • Constraints identified: "Are there authentication requirements?"
  • Edge cases covered: "What happens if the external service is down?"

Round 3: Traceability & Acceptance Validation

Final Requirements:

## Implementation Plan

### Stages
- {Logical breakdown with dependencies}

### Acceptance Criteria per Stage
- {Measurable, testable criteria}

### File Changes
- {Concrete paths: src/...}

### Documentation Updates
- {ARCHITECTURE.md, API docs, etc.}

Evaluate using Section 4 (Traceability) + Section 5 (Acceptance)

Common Gaps to Address:

  • Stakeholder mapping: "Which user role triggers this workflow?"
  • Business value: "What problem does this solve for the user?"
  • Success criteria: "How do we verify this works?" (not "it works")
  • Prioritization: "Is this must-have for MVP or can it wait?"

Output Format

After all validation rounds pass, generate the specification file AND create branch with commit:

Step 1: Confirm Branch Creation with User

Ask the user directly for confirmation:

ТЗ готово (оценка IEEE 29148: ≥85%). Создать ветку и закоммитить ТЗ?
- Да, создать ветку и закоммитить
- Только создать файл спецификации (без ветки и коммита)

Step 2: Determine Branch Type

If user confirms "Да", determine branch type:

  • Feature: for new functionality, enhancement (feature/{slug})
  • Bugfix: for fixing bugs (bugfix/{slug} or bugfix/{issue-id}-{slug})
  • Refactor: for code restructuring without behavior change (feature/refactor-{area})
  • Hotfix: for urgent production fixes (hotfix/{description})

Infer from spec type or ask the user directly if unclear:

Какой тип ветки создать?
- feature (новая функциональность)
- bugfix (исправление бага)
- refactor (рефакторинг)
- hotfix (срочный фикс для production)

Step 3: Check Current Branch

git branch --show-current
git status

Protection Policy: If on main or master, warn user:

⚠️ Вы находитесь на ветке main/master. Прямые изменения не рекомендуются.
Создать feature branch?

Ensure no uncommitted changes remain before creating new branch.

Step 4: Create Branch

git checkout -b {branch-type}/{slug}

Examples:

  • feature/thermocalc-response-differentiation
  • bugfix/login-validation-error
  • bugfix/142-auth-token-expiry
  • feature/refactor-user-service
  • hotfix/payment-gateway-timeout

Branch naming conventions:

  • Use lowercase letters
  • Separate words with hyphens
  • Keep descriptions short but descriptive
  • For bugfixes, include issue ID if available
  • For hotfixes, use prefix hotfix/ for urgent production fixes

Step 5: Verify Branch Creation

git status

Ensure:

  • New branch is created
  • It's based on the correct starting point (typically main)
  • No uncommitted changes remain on main branch

Step 6: Write Spec File and Commit

# Write spec to .ai/specs/{filename}.md
git add .ai/specs/{filename}.md
git commit -m "docs

---

*Content truncated.*

When not to use it

  • When the user does not want to create a technical specification
  • When the project does not follow a workflow guide with specific steps

Limitations

  • Requires validation score of ≥85% to proceed
  • Spec template is concise and references detailed templates externally
  • Commit in small chunks (≤250 lines) during implementation

How it compares

This workflow integrates IEEE 29148:2018 validation directly into spec creation and branch initialization, ensuring high-quality requirements and a structured start to development, unlike a manual, less standardized approach.

Compared to similar skills

spec-creation side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
spec-creation (this skill)04moReviewIntermediate
sdd02moNo flagsIntermediate
project-planner3210moReviewIntermediate
spec-kit-workflow118moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

sdd

Tai-ch0802

本專案標準開發流程:分級 Spec-Driven Development (SDD)。動工前先做分級判定 — T0 直接做(typo/文案/樣式微調)、T1 單檔 SPEC.md 與實作同步並隨 PR 審(一般 bug fix / 小中型功能,預設層級)、T2 完整 PRD → SA 先審後寫(storage schema / 權限 / 跨 context 協定 / 大型功能)。產出物放 /docs/specs/{type}/{ID-PREFIX}_{desc}/,目錄前綴採 ISSUE-/PR-/BASE- 三類。當使用者提到「新功能、修 bug、重構、SDD、規格驅動、要做一個 X、開新功

00

project-planner

adrianpuiu

Comprehensive project planning and documentation generator for software projects. Creates structured requirements documents, system design documents, and task breakdown plans with implementation tracking. Use when starting a new project, defining specifications, creating technical designs, or breaking down complex systems into implementable tasks. Supports user story format, acceptance criteria, component design, API specifications, and hierarchical task decomposition with requirement traceability.

32115

spec-kit-workflow

jmanhype

Guides specification-driven development workflow. Automatically invoked when discussing new features, specifications, technical planning, or implementation tasks. Ensures proper workflow phases (specify → clarify → plan → checklist → tasks → analyze → implement).

11111

specification-architect

adrianpuiu

A rigorous, traceability-first system that generates five interconnected architectural documents (blueprint.md, requirements.md, design.md, tasks.md, and validation.md) with complete requirements-to-implementation traceability. Use this skill when users need to architect systems, create technical specifications, or develop structured project documentation with guaranteed traceability.

1388

architecture

davila7

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

1244

context-driven-development

wshobson

Use this skill when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md, and workflow.md files.

744

Search skills

Search the agent skills registry