spec-feature 1.0.2 → 1.0.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +36 -23
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -1,6 +1,26 @@
1
1
  # SpecFeature
2
2
 
3
- SpecFeature is a sequential process for preparing and maintaining features: from formulating business context to verifying completed tasks. It helps synchronize product, engineering, and QA teams, reduce the number of "on-the-fly" changes, and establish success criteria before development begins. All artifacts are generated by LLM based on a single input context.
3
+ SpecFeature helps you create feature specifications automatically. Just describe what you want to build, and it generates a complete specification, technical plan, and task list for your development team. All documents are created by AI from a single description.
4
+
5
+ ## Why use SpecFeature?
6
+
7
+ ### **Clearer starting point**
8
+ The specification becomes the single source of truth — you guess less about what you intended to build.
9
+
10
+ ### **Fewer misunderstandings between human and AI**
11
+ Clear "contracts" / specifications help avoid "vibe coding" — when AI "guesses" your intention and often builds something not quite what you need.
12
+
13
+ ### **Architecture and decisions are documented**
14
+ "Why did we choose this solution?" will be captured in the specification / constitution, not in emails, chats, or someone's head.
15
+
16
+ ### **Controlled task breakdown**
17
+ Small tasks are easier to review, test, and correct — fewer "big commits that are hard to understand".
18
+
19
+ ### **Flexibility and evolution**
20
+ Specifications are not "dead" — they can be updated, refactored, and revised when requirements change.
21
+
22
+ ### **AI assistant integration**
23
+ Specification + plan + tasks gives AI "context" and boundaries within which it can generate code more safely.
4
24
 
5
25
  ## Installation
6
26
 
@@ -85,37 +105,30 @@ npm install spec-feature
85
105
 
86
106
  ## Getting started
87
107
 
88
- To launch specification creation, use `spec/feature.md`. It will create a specification, plan, and task list in one request.
108
+ To create a feature specification, use `spec/feature.md` template with any AI Assistant that can create folders and files (such as `Claude Code`, `Gemini CLI`, `Codex CLI`, `Copilot`, `Cursor`, etc.).
89
109
 
90
- **Usage example:**
91
- ```
92
- Use the template from spec/feature.md.
93
- @user-auth@ Need to add user authentication via email and password. The user should be able to register, log in, and recover their password. Integration with the existing notification system is mandatory.
94
- ```
95
-
96
- This will create the `spec/features/user-auth/` folder with three files: `spec.md`, `plan.md`, and `tasks.md`.
97
-
98
- ## Input parameter format
110
+ ### Input parameter format
99
111
 
100
112
  Pass parameters in one line in the format `@<feature>@ <context>`:
101
113
 
102
114
  - the value between the first two `@` symbols is used as **FEATURE** and determines the feature folder (`@payments@` → `spec/features/payments`);
103
115
  - everything following the second `@` is **CONTEXT**. It can span multiple lines, include lists, links, and additional clarifications.
104
116
 
105
- ## How to launch specification creation
117
+ ### Usage example
118
+
119
+ ```
120
+ Use the template from spec/feature.md.
121
+ @user-auth@ Need to add user authentication via email and password. The user should be able to register, log in, and recover their password. Integration with the existing notification system is mandatory.
122
+ ```
123
+
124
+ ### What happens next
106
125
 
107
- Use any AI Assistant that can create folders and files, such as: `Claude Code`, `Gemini CLI`, `Codex CLI`, `Copilot`, `Cursor`, etc.
126
+ The AI assistant generates three Markdown documents in sequence:
127
+ - `spec/features/{FEATURE}/spec.md` — specification describing value and user scenarios.
128
+ - `spec/features/{FEATURE}/plan.md` — technical plan based on specification and context.
129
+ - `spec/features/{FEATURE}/tasks.md` — checklist of tasks for implementation and testing.
108
130
 
109
- 1. **Pass it a prompt in this format**
110
- ```
111
- Use the template from spec/feature.md.
112
- @<feature>@ <context>
113
- ```
114
- 2. **What happens next**
115
- The AI assistant generates three Markdown documents in sequence:
116
- - `spec/features/{FEATURE}/spec.md` — specification describing value and user scenarios.
117
- - `spec/features/{FEATURE}/plan.md` — technical plan based on specification and context.
118
- - `spec/features/{FEATURE}/tasks.md` — checklist of tasks for implementation and testing.
131
+ For example, the above command will create the `spec/features/user-auth/` folder with three files: `spec.md`, `plan.md`, and `tasks.md`.
119
132
 
120
133
  ## How to launch task execution based on created specifications
121
134
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "spec-feature",
3
- "version": "1.0.2",
3
+ "version": "1.0.3",
4
4
  "bin": {
5
5
  "spec-feature": "./bin/cli.js"
6
6
  },