@leeovery/claude-technical-workflows 2.0.7 → 2.0.9
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.
package/README.md
CHANGED
|
@@ -45,6 +45,8 @@ Review → Validate against spec
|
|
|
45
45
|
|
|
46
46
|
**This is a work in progress.** The workflow is being refined through real-world usage. Expect updates as patterns evolve.
|
|
47
47
|
|
|
48
|
+
**Model compatibility:** These skills have been developed and refined for Claude Code running on **Opus 4.5**. Different models may exhibit different edge cases, and future model releases may require adjustments to the prompts and workflows.
|
|
49
|
+
|
|
48
50
|
## How do I use this?
|
|
49
51
|
|
|
50
52
|
You have two entry points:
|
|
@@ -70,25 +72,44 @@ Each phase builds on the previous. Specification validates your discussions into
|
|
|
70
72
|
|
|
71
73
|
Each phase has a command designed as its entry point:
|
|
72
74
|
|
|
73
|
-
| Phase
|
|
74
|
-
|
|
75
|
-
| Research
|
|
76
|
-
| Discussion
|
|
77
|
-
| Specification
|
|
78
|
-
| Planning
|
|
75
|
+
| Phase | Command |
|
|
76
|
+
|----------------|-------------------------|
|
|
77
|
+
| Research | `/start-research` |
|
|
78
|
+
| Discussion | `/start-discussion` |
|
|
79
|
+
| Specification | `/start-specification` |
|
|
80
|
+
| Planning | `/start-planning` |
|
|
79
81
|
| Implementation | `/start-implementation` |
|
|
80
82
|
|
|
81
83
|
Run the command directly or ask Claude to run it. Each command gathers the context it needs, asking what you're researching, discussing, or planning. Where relevant, it looks at outputs from the previous phase and offers you a choice from the list.
|
|
82
84
|
|
|
83
85
|
## Installation
|
|
84
86
|
|
|
85
|
-
|
|
87
|
+
Two installation methods are available:
|
|
88
|
+
|
|
89
|
+
| Method | Best for | Trade-off |
|
|
90
|
+
|--------|----------|-----------|
|
|
91
|
+
| **Marketplace** | Local Claude Code | Simple install, skills cached globally |
|
|
92
|
+
| **npm** | Claude Code for Web | Skills copied to repo, requires npm |
|
|
93
|
+
|
|
94
|
+
### Option 1: Claude Marketplace
|
|
95
|
+
|
|
96
|
+
```
|
|
97
|
+
/plugin marketplace add leeovery/claude-plugins-marketplace
|
|
98
|
+
/plugin install claude-technical-workflows@claude-plugins-marketplace
|
|
99
|
+
```
|
|
100
|
+
|
|
101
|
+
> **Note:** Marketplace plugins are cached globally (`~/.claude/plugins/`) and won't be available in Claude Code for Web since files aren't in your repository.
|
|
102
|
+
|
|
103
|
+
### Option 2: npm (Recommended for Web)
|
|
86
104
|
|
|
87
105
|
```bash
|
|
88
106
|
npm install -D @leeovery/claude-technical-workflows
|
|
89
107
|
```
|
|
90
108
|
|
|
91
|
-
|
|
109
|
+
Skills are copied to `.claude/` in your project and can be committed to your repository—making them available in Claude Code for Web.
|
|
110
|
+
|
|
111
|
+
<details>
|
|
112
|
+
<summary>pnpm users</summary>
|
|
92
113
|
|
|
93
114
|
pnpm doesn't expose binaries from transitive dependencies, so install the manager directly:
|
|
94
115
|
|
|
@@ -97,16 +118,17 @@ pnpm add -D @leeovery/claude-manager @leeovery/claude-technical-workflows
|
|
|
97
118
|
pnpm approve-builds # approve when prompted
|
|
98
119
|
pnpm install # triggers postinstall
|
|
99
120
|
```
|
|
121
|
+
</details>
|
|
100
122
|
|
|
101
|
-
|
|
123
|
+
<details>
|
|
124
|
+
<summary>Removal (npm/pnpm)</summary>
|
|
102
125
|
|
|
103
126
|
Due to bugs in npm 7+ ([issue #3042](https://github.com/npm/cli/issues/3042)) and pnpm ([issue #3276](https://github.com/pnpm/pnpm/issues/3276)), preuninstall hooks don't run reliably. Remove files manually first:
|
|
104
127
|
|
|
105
128
|
```bash
|
|
106
129
|
npx claude-manager remove @leeovery/claude-technical-workflows && npm rm @leeovery/claude-technical-workflows
|
|
107
130
|
```
|
|
108
|
-
|
|
109
|
-
The [Claude Manager](https://github.com/leeovery/claude-manager) copies skills, commands, and agents to `.claude/` automatically.
|
|
131
|
+
</details>
|
|
110
132
|
|
|
111
133
|
## The Six-Phase Workflow
|
|
112
134
|
|
|
@@ -199,14 +221,14 @@ agents/
|
|
|
199
221
|
|
|
200
222
|
## Skills
|
|
201
223
|
|
|
202
|
-
| Skill
|
|
203
|
-
|
|
204
|
-
| [**technical-research**](skills/technical-research/)
|
|
205
|
-
| [**technical-discussion**](skills/technical-discussion/)
|
|
206
|
-
| [**technical-specification**](skills/technical-specification/)
|
|
207
|
-
| [**technical-planning**](skills/technical-planning/)
|
|
208
|
-
| [**technical-implementation**](skills/technical-implementation/) | 5
|
|
209
|
-
| [**technical-review**](skills/technical-review/)
|
|
224
|
+
| Skill | Phase | Description |
|
|
225
|
+
|------------------------------------------------------------------|-------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
226
|
+
| [**technical-research**](skills/technical-research/) | 1 | Explore ideas from their earliest seed. Investigate market fit, technical feasibility, business viability. Free-flowing exploration across technical, business, and market domains. |
|
|
227
|
+
| [**technical-discussion**](skills/technical-discussion/) | 2 | Document technical discussions as expert architect and meeting assistant. Captures context, decisions, edge cases, competing solutions, debates, and rationale. |
|
|
228
|
+
| [**technical-specification**](skills/technical-specification/) | 3 | Build validated specifications from discussion documents through collaborative refinement. Filters hallucinations, enriches gaps, produces standalone spec. |
|
|
229
|
+
| [**technical-planning**](skills/technical-planning/) | 4 | Transform specifications into actionable implementation plans with phases, tasks, and acceptance criteria. Supports multiple output formats. |
|
|
230
|
+
| [**technical-implementation**](skills/technical-implementation/) | 5 | Execute implementation plans using strict TDD workflow. Writes tests first, implements to pass, commits frequently, and gates phases on user approval. |
|
|
231
|
+
| [**technical-review**](skills/technical-review/) | 6 | Review completed implementation against specification requirements and plan acceptance criteria. Uses parallel subagents for efficient chain verification. Produces structured feedback without fixing code. |
|
|
210
232
|
|
|
211
233
|
### technical-research
|
|
212
234
|
|
|
@@ -305,21 +327,21 @@ Reviews completed work with fresh perspective. Validates implementation against
|
|
|
305
327
|
|
|
306
328
|
Slash commands to quickly invoke the workflow.
|
|
307
329
|
|
|
308
|
-
| Command
|
|
309
|
-
|
|
310
|
-
| [**/start-research**](commands/start-research.md)
|
|
311
|
-
| [**/start-discussion**](commands/start-discussion.md)
|
|
312
|
-
| [**/start-specification**](commands/start-specification.md)
|
|
313
|
-
| [**/start-planning**](commands/start-planning.md)
|
|
314
|
-
| [**/start-implementation**](commands/start-implementation.md) | Start implementing a plan. Executes tasks via strict TDD, committing after each passing test.
|
|
315
|
-
| [**/interview**](commands/interview.md)
|
|
330
|
+
| Command | Description |
|
|
331
|
+
|---------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
332
|
+
| [**/start-research**](commands/start-research.md) | Begin research exploration. For early-stage ideas, feasibility checks, and broad exploration before formal discussion. |
|
|
333
|
+
| [**/start-discussion**](commands/start-discussion.md) | Begin a new technical discussion. Gathers topic, context, background information, and relevant codebase areas before starting documentation. |
|
|
334
|
+
| [**/start-specification**](commands/start-specification.md) | Start a specification session from an existing discussion. Validates and refines discussion content into a standalone specification. |
|
|
335
|
+
| [**/start-planning**](commands/start-planning.md) | Start a planning session from an existing specification. Creates implementation plans with phases, tasks, and acceptance criteria. Supports multiple output formats (markdown, Linear, Backlog.md, Beads). |
|
|
336
|
+
| [**/start-implementation**](commands/start-implementation.md) | Start implementing a plan. Executes tasks via strict TDD, committing after each passing test. |
|
|
337
|
+
| [**/interview**](commands/interview.md) | Shift into focused questioning mode during research or discussion. Probes ideas with non-obvious questions, challenges assumptions, and surfaces concerns. |
|
|
316
338
|
|
|
317
339
|
## Agents
|
|
318
340
|
|
|
319
341
|
Subagents that skills can spawn for parallel task execution.
|
|
320
342
|
|
|
321
|
-
| Agent
|
|
322
|
-
|
|
343
|
+
| Agent | Used By | Description |
|
|
344
|
+
|------------------------------------------------|------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
323
345
|
| [**chain-verifier**](agents/chain-verifier.md) | technical-review | Verifies a single plan task was implemented correctly. Checks implementation, tests (not under/over-tested), and code quality. Multiple chain-verifiers run in parallel to verify ALL tasks efficiently. |
|
|
324
346
|
|
|
325
347
|
## Requirements
|
|
@@ -56,13 +56,15 @@ Which specification would you like to create a plan for?
|
|
|
56
56
|
|
|
57
57
|
**Important:** Only completed specifications should proceed to planning. If a specification is still being built, advise the user to complete the specification phase first.
|
|
58
58
|
|
|
59
|
+
**Auto-select:** If exactly one specification exists, automatically select it and proceed to Step 4. Inform the user which specification was selected. Do not ask for confirmation.
|
|
60
|
+
|
|
59
61
|
Ask: **Which specification would you like to plan?**
|
|
60
62
|
|
|
61
63
|
## Step 4: Choose Output Destination
|
|
62
64
|
|
|
63
65
|
Ask: **Where should this plan live?**
|
|
64
66
|
|
|
65
|
-
Load **[output-formats.md](skills/technical-planning/references/output-formats.md)** and present the available formats to help the user choose. Then load the corresponding output adapter for that format's setup requirements.
|
|
67
|
+
Load **[output-formats.md](../skills/technical-planning/references/output-formats.md)** and present the available formats to help the user choose. Then load the corresponding output adapter for that format's setup requirements.
|
|
66
68
|
|
|
67
69
|
## Step 5: Gather Additional Context
|
|
68
70
|
|
package/package.json
CHANGED
|
@@ -6,6 +6,8 @@
|
|
|
6
6
|
|
|
7
7
|
Plans can be stored in different formats. **Ask the user which format they prefer** - present the benefits from each adapter file and let them decide.
|
|
8
8
|
|
|
9
|
+
**IMPORTANT**: Only offer formats listed below. Do not invent or suggest formats that don't have corresponding `output-*.md` files in this directory.
|
|
10
|
+
|
|
9
11
|
## Available Formats
|
|
10
12
|
|
|
11
13
|
- **[Local Markdown](output-local-markdown.md)** - Single markdown file, no external tools
|