feat: Update skill references from issue-lifecycle to issue-discover and enhance inline status display in workflow skills

This commit is contained in:
catlog22
2026-02-15 14:05:31 +08:00
parent 8985894c22
commit 30753c7830
6 changed files with 29 additions and 30 deletions

View File

@@ -323,17 +323,17 @@ function parseMarkdownBody(body) {
### Clear Input (No Questions)
```bash
Skill(skill="issue-lifecycle", args="https://github.com/org/repo/issues/42")
Skill(skill="issue-discover", args="https://github.com/org/repo/issues/42")
# → Fetches, parses, creates immediately
Skill(skill="issue-lifecycle", args="\"Login fails with special chars. Expected: success. Actual: 500\"")
Skill(skill="issue-discover", args="\"Login fails with special chars. Expected: success. Actual: 500\"")
# → Parses structure, creates immediately
```
### Vague Input (1 Question)
```bash
Skill(skill="issue-lifecycle", args="\"auth broken\"")
Skill(skill="issue-discover", args="\"auth broken\"")
# → Asks: "Please describe the issue in more detail"
# → User provides details → saved to feedback[]
# → Creates issue

View File

@@ -319,13 +319,13 @@ function getPerspectiveGuidance(perspective) {
```bash
# Quick scan with default perspectives
Skill(skill="issue-lifecycle", args="--action discover src/auth/**")
Skill(skill="issue-discover", args="--action discover src/auth/**")
# Security-focused audit
Skill(skill="issue-lifecycle", args="--action discover src/payment/** --perspectives=security,bug")
Skill(skill="issue-discover", args="--action discover src/payment/** --perspectives=security,bug")
# Full analysis with external research
Skill(skill="issue-lifecycle", args="--action discover src/api/** --external")
Skill(skill="issue-discover", args="--action discover src/api/** --external")
```
## Post-Phase Update

View File

@@ -27,8 +27,7 @@ Optional specialized review for completed implementations. In the standard workf
| `action-items` | Requirements met, acceptance criteria verified | Pre-deployment verification |
**Notes**:
- For documentation generation, use `/workflow:tools:docs`
- For CLAUDE.md updates, use `/update-memory-related`
- For CLAUDE.md updates, use `memory-manage` skill
## Execution

View File

@@ -35,7 +35,7 @@ Unified planning skill combining 4-phase planning workflow, plan quality verific
┌───────────┐
│ Confirm │─── Verify ──→ Phase 5
│ (choice) │─── Execute ─→ Skill("workflow-execute")
└───────────┘─── Review ──→ /workflow:status
└───────────┘─── Review ──→ Display session status inline
```
## Key Design Principles
@@ -137,7 +137,7 @@ Plan Confirmation (User Decision Gate):
└─ Decision (user choice):
├─ "Verify Plan Quality" (Recommended) → Route to Phase 5 (plan-verify)
├─ "Start Execution" → Skill(skill="workflow-execute")
└─ "Review Status Only" → Route to /workflow:status
└─ "Review Status Only" → Display session status inline
```
### Verify Mode
@@ -242,7 +242,7 @@ Phase 4: task-generate-agent --session sessionId
Plan Confirmation (User Decision Gate):
├─ "Verify Plan Quality" (Recommended) → Route to Phase 5
├─ "Start Execution" → Skill(skill="workflow-execute")
└─ "Review Status Only" → Route to /workflow:status
└─ "Review Status Only" → Display session status inline
```
**Session Memory Flow**: Each phase receives session ID, which provides access to:
@@ -365,7 +365,7 @@ See phase files for detailed update code.
- **Plan Confirmation Gate**: Present user with choice (Verify → Phase 5 / Execute / Review Status)
- **If user selects Verify**: Read phases/05-plan-verify.md, execute Phase 5 in-process
- **If user selects Execute**: Skill(skill="workflow-execute")
- **If user selects Review**: Route to /workflow:status
- **If user selects Review**: Display session status inline
- **Auto mode (workflowPreferences.autoYes)**: Auto-select "Verify Plan Quality", then auto-continue to execute if PROCEED
- Update TodoWrite after each phase
- After each phase, automatically continue to next phase based on TodoList status
@@ -408,13 +408,13 @@ CONSTRAINTS: [Limitations or boundaries]
**Called by Plan Mode** (4 phases):
- `/workflow:session:start` - Phase 1: Create or discover workflow session
- `/workflow:tools:context-gather` - Phase 2: Gather project context and analyze codebase
- `/workflow:tools:conflict-resolution` - Phase 3: Detect and resolve conflicts (conditional)
- `phases/02-context-gathering.md` - Phase 2: Gather project context and analyze codebase (inline)
- `phases/03-conflict-resolution.md` - Phase 3: Detect and resolve conflicts (inline, conditional)
- `/compact` - Phase 3: Memory optimization (if context approaching limits)
- `/workflow:tools:task-generate-agent` - Phase 4: Generate task JSON files
- `phases/04-task-generation.md` - Phase 4: Generate task JSON files (inline)
**Follow-up Skills**:
- `/workflow:plan-verify` - Verify plan quality (can also invoke via verify mode)
- `/workflow:status` - Review task breakdown and current progress
- Display session status inline - Review task breakdown and current progress
- `Skill(skill="workflow-execute")` - Begin implementation of generated tasks (skill: workflow-execute)
- `/workflow:replan` - Modify plan (can also invoke via replan mode)

View File

@@ -35,7 +35,7 @@ Unified TDD workflow skill combining TDD planning (Red-Green-Refactor task chain
┌───────────┐
│ Confirm │─── Verify ──→ Phase 7
│ (choice) │─── Execute ─→ Skill("workflow-execute")
└───────────┘─── Review ──→ /workflow:status
└───────────┘─── Review ──→ Display session status inline
```
## Key Design Principles
@@ -128,7 +128,7 @@ Plan Confirmation (User Decision Gate):
└─ Decision (user choice):
├─ "Verify TDD Compliance" (Recommended) → Route to Phase 7 (tdd-verify)
├─ "Start Execution" → Skill(skill="workflow-execute")
└─ "Review Status Only" → Route to /workflow:status
└─ "Review Status Only" → Display session status inline
```
### Verify Mode
@@ -273,7 +273,7 @@ Phase 6: TDD Structure Validation (internal)
Plan Confirmation (User Decision Gate):
├─ "Verify TDD Compliance" (Recommended) → Route to Phase 7
├─ "Start Execution" → Skill(skill="workflow-execute")
└─ "Review Status Only" → Route to /workflow:status
└─ "Review Status Only" → Display session status inline
```
### Verify Mode
@@ -401,11 +401,11 @@ Similar to workflow-plan, a `planning-notes.md` can accumulate context across ph
| Error Type | Detection | Recovery Action |
|------------|-----------|-----------------|
| Parsing failure | Empty/malformed output | Retry once, then report |
| Missing context-package | File read error | Re-run `/workflow:tools:context-gather` |
| Missing context-package | File read error | Re-run Phase 2 (context-gathering) |
| Invalid task JSON | jq parse error | Report malformed file path |
| Task count exceeds 18 | Count validation ≥19 | Request re-scope, split into multiple sessions |
| Missing cli_execution.id | All tasks lack ID | Regenerate tasks with phase 0 user config |
| Test-context missing | File not found | Re-run `/workflow:tools:test-context-gather` |
| Test-context missing | File not found | Re-run Phase 3 (test-coverage-analysis) |
| Phase timeout | No response | Retry phase, check CLI connectivity |
| CLI tool not available | Tool not in cli-tools.json | Fall back to alternative preferred tool |
@@ -447,7 +447,7 @@ Similar to workflow-plan, a `planning-notes.md` can accumulate context across ph
- **Plan Confirmation Gate**: Present user with choice (Verify → Phase 7 / Execute / Review Status)
- **If user selects Verify**: Read phases/07-tdd-verify.md, execute Phase 7 in-process
- **If user selects Execute**: Skill(skill="workflow-execute")
- **If user selects Review**: Route to /workflow:status
- **If user selects Review**: Display session status inline
- **Auto mode (workflowPreferences.autoYes)**: Auto-select "Verify TDD Compliance", then auto-continue to execute if APPROVED
- Update TaskCreate/TaskUpdate after each phase
- After each phase, automatically continue to next phase based on TaskList status
@@ -465,17 +465,17 @@ Similar to workflow-plan, a `planning-notes.md` can accumulate context across ph
**Called by Plan Mode** (6 phases):
- `/workflow:session:start` - Phase 1: Create or discover TDD workflow session
- `/workflow:tools:context-gather` - Phase 2: Gather project context and analyze codebase
- `/workflow:tools:test-context-gather` - Phase 3: Analyze existing test patterns and coverage
- `/workflow:tools:conflict-resolution` - Phase 4: Detect and resolve conflicts (conditional)
- `phases/02-context-gathering.md` - Phase 2: Gather project context and analyze codebase (inline)
- `phases/03-test-coverage-analysis.md` - Phase 3: Analyze existing test patterns and coverage (inline)
- `phases/04-conflict-resolution.md` - Phase 4: Detect and resolve conflicts (inline, conditional)
- `/compact` - Phase 4: Memory optimization (if context approaching limits)
- `/workflow:tools:task-generate-tdd` - Phase 5: Generate TDD tasks with Red-Green-Refactor cycles
- `phases/05-tdd-task-generation.md` - Phase 5: Generate TDD tasks with Red-Green-Refactor cycles (inline)
**Called by Verify Mode**:
- `/workflow:tools:tdd-coverage-analysis` - Phase 7: Test coverage and cycle analysis
- `phases/07-tdd-verify.md` - Phase 7: Test coverage and cycle analysis (inline)
**Follow-up Skills**:
- `/workflow:tdd-verify` - Verify TDD compliance (can also invoke via verify mode)
- `/workflow:plan-verify` - Verify plan quality and dependencies
- `/workflow:status` - Review TDD task breakdown
- Display session status inline - Review TDD task breakdown
- `Skill(skill="workflow-execute")` - Begin TDD implementation

View File

@@ -430,6 +430,6 @@ After completion, ask user if they want to expand into issues (test/enhance/refa
- None for Prompt Mode
**Follow-up Skills**:
- `/workflow:status` - Review workflow state
- `/workflow:review` - Post-implementation review
- Display session status inline - Review workflow state
- `/workflow:review-session-cycle` - Post-implementation review
- `/issue:new` - Create follow-up issues