@leeovery/claude-technical-workflows 2.1.42 → 2.2.0
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/hooks/workflows/compact-recovery.sh +3 -23
- package/hooks/workflows/write-session-state.sh +2 -26
- package/package.json +1 -1
- package/skills/link-dependencies/SKILL.md +0 -1
- package/skills/migrate/SKILL.md +0 -1
- package/skills/migrate/scripts/migrations/013-discussion-work-type.sh +76 -0
- package/skills/migrate/scripts/migrations/014-specification-work-type.sh +76 -0
- package/skills/migrate/scripts/migrations/015-plan-work-type.sh +76 -0
- package/skills/start-bugfix/SKILL.md +80 -0
- package/skills/start-bugfix/references/gather-bug-context.md +75 -0
- package/skills/start-bugfix/references/invoke-investigation.md +46 -0
- package/skills/start-bugfix/references/topic-name-check.md +59 -0
- package/skills/start-discussion/SKILL.md +51 -46
- package/skills/start-discussion/references/gather-context.md +54 -10
- package/skills/start-discussion/references/handle-selection.md +14 -4
- package/skills/start-discussion/references/invoke-skill.md +71 -3
- package/skills/start-discussion/references/research-analysis.md +2 -0
- package/skills/start-discussion/references/route-scenario.md +39 -0
- package/skills/start-discussion/references/validate-topic.md +46 -0
- package/skills/start-discussion/scripts/discovery.sh +3 -0
- package/skills/start-feature/SKILL.md +28 -84
- package/skills/start-feature/references/invoke-discussion.md +8 -4
- package/skills/start-feature/references/invoke-research.md +29 -0
- package/skills/start-feature/references/invoke-skill.md +35 -0
- package/skills/start-feature/references/research-gating.md +65 -0
- package/skills/start-feature/references/topic-name-check.md +61 -0
- package/skills/start-implementation/SKILL.md +35 -289
- package/skills/start-implementation/references/check-dependencies.md +65 -0
- package/skills/start-implementation/references/display-plans.md +159 -0
- package/skills/start-implementation/references/environment-check.md +45 -0
- package/skills/start-implementation/references/invoke-skill.md +42 -0
- package/skills/start-implementation/references/route-scenario.md +32 -0
- package/skills/start-implementation/references/validate-plan.md +45 -0
- package/skills/start-implementation/scripts/discovery.sh +3 -0
- package/skills/start-investigation/SKILL.md +145 -0
- package/skills/start-investigation/references/gather-context-fresh.md +72 -0
- package/skills/start-investigation/references/gather-context.md +31 -0
- package/skills/start-investigation/references/invoke-skill.md +54 -0
- package/skills/start-investigation/references/route-scenario.md +69 -0
- package/skills/start-investigation/references/validate-investigation.md +46 -0
- package/skills/start-investigation/scripts/discovery.sh +92 -0
- package/skills/start-planning/SKILL.md +32 -72
- package/skills/start-planning/references/cross-cutting-context.md +5 -5
- package/skills/start-planning/references/invoke-skill.md +27 -4
- package/skills/start-planning/references/route-plan-state.md +30 -0
- package/skills/start-planning/references/route-scenario.md +38 -0
- package/skills/start-planning/references/validate-spec.md +47 -0
- package/skills/start-planning/scripts/discovery.sh +7 -0
- package/skills/start-research/SKILL.md +17 -6
- package/skills/start-research/references/invoke-skill.md +3 -0
- package/skills/start-review/SKILL.md +32 -60
- package/skills/start-review/references/determine-review-version.md +24 -0
- package/skills/start-review/references/display-plans.md +2 -2
- package/skills/start-review/references/route-scenario.md +74 -0
- package/skills/start-review/references/select-plans.md +8 -6
- package/skills/start-review/references/validate-artifacts.md +63 -0
- package/skills/start-review/scripts/discovery.sh +3 -0
- package/skills/start-specification/SKILL.md +44 -20
- package/skills/start-specification/references/check-existing-spec.md +57 -0
- package/skills/start-specification/references/check-prerequisites.md +15 -0
- package/skills/start-specification/references/handoffs/continue-concluded.md +3 -0
- package/skills/start-specification/references/handoffs/continue.md +3 -0
- package/skills/start-specification/references/handoffs/create-with-incorporation.md +3 -0
- package/skills/start-specification/references/handoffs/create.md +3 -0
- package/skills/start-specification/references/handoffs/unify-with-incorporation.md +3 -0
- package/skills/start-specification/references/handoffs/unify.md +3 -0
- package/skills/start-specification/references/invoke-skill-bridge.md +74 -0
- package/skills/start-specification/references/route-scenario.md +23 -0
- package/skills/start-specification/references/validate-source.md +91 -0
- package/skills/start-specification/scripts/discovery.sh +6 -0
- package/skills/status/SKILL.md +6 -3
- package/skills/status/scripts/discovery.sh +9 -0
- package/skills/technical-discussion/SKILL.md +15 -4
- package/skills/technical-discussion/references/template.md +9 -1
- package/skills/technical-implementation/SKILL.md +24 -1
- package/skills/technical-implementation/references/analysis-loop.md +4 -4
- package/skills/technical-implementation/references/task-loop.md +2 -2
- package/skills/technical-investigation/SKILL.md +239 -0
- package/skills/technical-investigation/references/analysis-patterns.md +181 -0
- package/skills/technical-investigation/references/symptom-gathering.md +164 -0
- package/skills/technical-investigation/references/template.md +164 -0
- package/skills/technical-planning/SKILL.md +24 -1
- package/skills/technical-planning/references/author-tasks.md +16 -16
- package/skills/technical-planning/references/define-tasks.md +2 -2
- package/skills/technical-planning/references/plan-construction.md +11 -30
- package/skills/technical-planning/references/plan-review.md +3 -3
- package/skills/technical-research/SKILL.md +38 -2
- package/skills/technical-review/SKILL.md +1 -2
- package/skills/technical-review/references/review-actions-loop.md +43 -1
- package/skills/technical-specification/SKILL.md +1 -2
- package/skills/technical-specification/references/spec-completion.md +34 -6
- package/skills/technical-specification/references/spec-construction.md +1 -1
- package/skills/technical-specification/references/spec-review.md +5 -5
- package/skills/view-plan/SKILL.md +0 -1
- package/skills/workflow/bridge/SKILL.md +82 -0
- package/skills/workflow/bridge/references/bugfix-continuation.md +59 -0
- package/skills/workflow/bridge/references/feature-continuation.md +60 -0
- package/skills/workflow/bridge/references/greenfield-continuation.md +224 -0
- package/skills/workflow/bridge/scripts/discovery.sh +512 -0
- package/skills/workflow/start/SKILL.md +97 -0
- package/skills/workflow/start/references/bugfix-routing.md +117 -0
- package/skills/workflow/start/references/feature-routing.md +117 -0
- package/skills/workflow/start/references/greenfield-routing.md +140 -0
- package/skills/workflow/start/references/work-type-selection.md +83 -0
- package/skills/workflow/start/scripts/discovery.sh +577 -0
- package/skills/begin-implementation/SKILL.md +0 -162
- package/skills/begin-planning/SKILL.md +0 -92
- package/skills/begin-review/SKILL.md +0 -90
- package/skills/continue-feature/SKILL.md +0 -186
- package/skills/continue-feature/references/detect-phase.md +0 -99
- package/skills/continue-feature/references/invoke-implementation.md +0 -43
- package/skills/continue-feature/references/invoke-planning.md +0 -43
- package/skills/continue-feature/references/invoke-review.md +0 -43
- package/skills/continue-feature/references/invoke-specification.md +0 -55
- package/skills/continue-feature/references/phase-bridge.md +0 -57
- package/skills/continue-feature/scripts/discovery.sh +0 -233
- package/skills/start-feature/references/phase-bridge.md +0 -37
|
@@ -4,26 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
7
|
-
This step constructs the complete plan — defining phases, designing task lists, and authoring every task.
|
|
8
|
-
|
|
9
|
-
┌─────────────────────────────────────────────────────┐
|
|
10
|
-
│ │
|
|
11
|
-
│ Phase Structure — define or review all phases │
|
|
12
|
-
│ │
|
|
13
|
-
│ ┌─────────────────────────────────────────────┐ │
|
|
14
|
-
│ │ For each phase: │ │
|
|
15
|
-
│ │ │ │
|
|
16
|
-
│ │ Step A → Define tasks for the phase │ │
|
|
17
|
-
│ │ │ │
|
|
18
|
-
│ │ ┌─────────────────────────────────┐ │ │
|
|
19
|
-
│ │ │ For each task in the phase: │ │ │
|
|
20
|
-
│ │ │ │ │ │
|
|
21
|
-
│ │ │ Step B → Author the task │ │ │
|
|
22
|
-
│ │ └─────────────────────────────────┘ │ │
|
|
23
|
-
│ │ │ │
|
|
24
|
-
│ └─────────────────────────────────────────────┘ │
|
|
25
|
-
│ │
|
|
26
|
-
└─────────────────────────────────────────────────────┘
|
|
7
|
+
This step constructs the complete plan — defining phases, designing task lists, and authoring every task.
|
|
27
8
|
|
|
28
9
|
---
|
|
29
10
|
|
|
@@ -65,9 +46,9 @@ every stage.
|
|
|
65
46
|
|
|
66
47
|
This phase needs task design.
|
|
67
48
|
|
|
68
|
-
→
|
|
49
|
+
→ Proceed to **A. Define Tasks** with this phase.
|
|
69
50
|
|
|
70
|
-
After
|
|
51
|
+
After **A. Define Tasks** returns with an approved task table, proceed to **Author Tasks for the Phase** below.
|
|
71
52
|
|
|
72
53
|
#### If the phase has a task table
|
|
73
54
|
|
|
@@ -89,7 +70,7 @@ Check `task_list_gate_mode` in the Plan Index File frontmatter.
|
|
|
89
70
|
Phase {N}: {Phase Name} — task list confirmed. Proceeding to authoring.
|
|
90
71
|
```
|
|
91
72
|
|
|
92
|
-
→
|
|
73
|
+
→ Proceed to **Author Tasks for the Phase** below.
|
|
93
74
|
|
|
94
75
|
#### If `task_list_gate_mode: gated` (existing task table)
|
|
95
76
|
|
|
@@ -108,11 +89,11 @@ Phase {N}: {Phase Name} — task list confirmed. Proceeding to authoring.
|
|
|
108
89
|
|
|
109
90
|
#### If the user wants changes
|
|
110
91
|
|
|
111
|
-
→
|
|
92
|
+
→ Proceed to **A. Define Tasks** with this phase for revision.
|
|
112
93
|
|
|
113
94
|
#### If confirmed
|
|
114
95
|
|
|
115
|
-
→
|
|
96
|
+
→ Proceed to **Author Tasks for the Phase** below.
|
|
116
97
|
|
|
117
98
|
---
|
|
118
99
|
|
|
@@ -130,13 +111,13 @@ All tasks already written.
|
|
|
130
111
|
Phase {N}: {Phase Name} — all tasks already authored.
|
|
131
112
|
```
|
|
132
113
|
|
|
133
|
-
→
|
|
114
|
+
→ Proceed to the next phase.
|
|
134
115
|
|
|
135
116
|
#### If any tasks in the phase have status `pending`
|
|
136
117
|
|
|
137
|
-
→
|
|
118
|
+
→ Proceed to **B. Author Tasks** for the entire phase.
|
|
138
119
|
|
|
139
|
-
After
|
|
120
|
+
After **B. Author Tasks** returns, all tasks in the phase are authored.
|
|
140
121
|
|
|
141
122
|
If the user navigates mid-approval, the scratch file preserves approval state. On return, resume from the first non-approved task.
|
|
142
123
|
|
|
@@ -166,12 +147,12 @@ All phases are complete. The plan has **{N} phases** with **{M} tasks** total.
|
|
|
166
147
|
|
|
167
148
|
---
|
|
168
149
|
|
|
169
|
-
##
|
|
150
|
+
## A. Define Tasks
|
|
170
151
|
|
|
171
152
|
Load **[define-tasks.md](define-tasks.md)** and follow its instructions as written. This step designs and approves a task list for **one phase**.
|
|
172
153
|
|
|
173
154
|
---
|
|
174
155
|
|
|
175
|
-
##
|
|
156
|
+
## B. Author Tasks
|
|
176
157
|
|
|
177
158
|
Load **[author-tasks.md](author-tasks.md)** and follow its instructions as written. This step authors **all tasks for the phase** via a batch agent and returns.
|
|
@@ -50,7 +50,7 @@ Record the current cycle number — passed to both review agents for tracking fi
|
|
|
50
50
|
|
|
51
51
|
#### If no findings were surfaced in this cycle
|
|
52
52
|
|
|
53
|
-
→ Proceed
|
|
53
|
+
→ Proceed to **E. Completion**.
|
|
54
54
|
|
|
55
55
|
#### If findings were surfaced
|
|
56
56
|
|
|
@@ -101,7 +101,7 @@ with fresh context — 2-3 cycles typically surface anything cascading.
|
|
|
101
101
|
|
|
102
102
|
#### If proceed
|
|
103
103
|
|
|
104
|
-
→
|
|
104
|
+
→ Proceed to **E. Completion**.
|
|
105
105
|
|
|
106
106
|
---
|
|
107
107
|
|
|
@@ -119,4 +119,4 @@ with fresh context — 2-3 cycles typically surface anything cascading.
|
|
|
119
119
|
Plan review complete — {N} cycle(s), all tracking files finalised.
|
|
120
120
|
```
|
|
121
121
|
|
|
122
|
-
→ Return to **[
|
|
122
|
+
→ Return to **[the skill](../SKILL.md)** for **Step 8**.
|
|
@@ -1,6 +1,5 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: technical-research
|
|
3
|
-
description: "Explore ideas, validate concepts, and research broadly across technical, business, and market domains. Use when: (1) User has a new idea to explore, (2) Need to research a topic deeply, (3) Validating feasibility - technical, business, or market, (4) Learning and exploration without necessarily building anything, (5) User says 'research this' or 'explore this idea', (6) Brain dumping early thoughts before formal discussion. Creates research documents in .workflows/research/ that may feed into discussion or specification."
|
|
4
3
|
user-invocable: false
|
|
5
4
|
---
|
|
6
5
|
|
|
@@ -123,7 +122,44 @@ Document the convergence point in the research file using this marker:
|
|
|
123
122
|
> **Discussion-ready**: {Brief summary of what was explored and why it's ready for decision-making. Key tradeoffs or options identified.}
|
|
124
123
|
```
|
|
125
124
|
|
|
126
|
-
|
|
125
|
+
Commit the file.
|
|
126
|
+
|
|
127
|
+
Check the research artifact frontmatter for `work_type`.
|
|
128
|
+
|
|
129
|
+
**If work_type is set** (feature or greenfield):
|
|
130
|
+
|
|
131
|
+
> *Output the next fenced block as markdown (not a code block):*
|
|
132
|
+
|
|
133
|
+
```
|
|
134
|
+
· · · · · · · · · · · ·
|
|
135
|
+
This topic is marked discussion-ready. Would you like to:
|
|
136
|
+
|
|
137
|
+
- **`c`/`continue`** — Continue exploring
|
|
138
|
+
- **`d`/`discuss`** — Transition to discussion phase
|
|
139
|
+
· · · · · · · · · · · ·
|
|
140
|
+
```
|
|
141
|
+
|
|
142
|
+
**STOP.** Wait for user response.
|
|
143
|
+
|
|
144
|
+
#### If continue
|
|
145
|
+
|
|
146
|
+
Continue with whatever's next — another topic, a different angle, or wrapping up the session.
|
|
147
|
+
|
|
148
|
+
#### If discuss
|
|
149
|
+
|
|
150
|
+
Invoke the `/workflow:bridge` skill:
|
|
151
|
+
|
|
152
|
+
```
|
|
153
|
+
Pipeline bridge for: {topic}
|
|
154
|
+
Work type: {work_type from artifact frontmatter}
|
|
155
|
+
Completed phase: research
|
|
156
|
+
|
|
157
|
+
Invoke the workflow:bridge skill to enter plan mode with continuation instructions.
|
|
158
|
+
```
|
|
159
|
+
|
|
160
|
+
**If work_type is not set:**
|
|
161
|
+
|
|
162
|
+
Continue with whatever's next — another topic, a different angle, or wrapping up the session.
|
|
127
163
|
|
|
128
164
|
### If the user keeps digging
|
|
129
165
|
|
|
@@ -1,6 +1,5 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: technical-review
|
|
3
|
-
description: "Validate completed implementation against plan tasks and acceptance criteria. Use when: (1) Implementation is complete, (2) User wants validation before merging/shipping, (3) Quality gate check needed after implementation. Reviews ALL plan tasks for implementation correctness, test adequacy, and code quality. Produces structured feedback (approve, request changes, or comments) - does NOT fix code."
|
|
4
3
|
user-invocable: false
|
|
5
4
|
---
|
|
6
5
|
|
|
@@ -53,7 +52,7 @@ The specification is optional — the review can proceed with just the plan.
|
|
|
53
52
|
|
|
54
53
|
Analysis of existing review findings was requested. The review has already been completed.
|
|
55
54
|
|
|
56
|
-
→
|
|
55
|
+
→ Proceed to **Step 6**.
|
|
57
56
|
|
|
58
57
|
---
|
|
59
58
|
|
|
@@ -30,6 +30,30 @@ Check the verdict(s) from the review(s) being analyzed.
|
|
|
30
30
|
No actionable findings. All reviews passed with no required changes.
|
|
31
31
|
```
|
|
32
32
|
|
|
33
|
+
**Check for pipeline continuation** — Read the plan file (`.workflows/planning/{topic}/plan.md`) and check for `work_type`
|
|
34
|
+
|
|
35
|
+
**If work_type is set** (feature, bugfix, or greenfield):
|
|
36
|
+
|
|
37
|
+
This review is part of a pipeline. The pipeline is complete. Invoke the `/workflow:bridge` skill:
|
|
38
|
+
|
|
39
|
+
```
|
|
40
|
+
Pipeline bridge for: {topic}
|
|
41
|
+
Work type: {work_type from plan frontmatter}
|
|
42
|
+
Completed phase: review
|
|
43
|
+
|
|
44
|
+
Invoke the workflow:bridge skill to enter plan mode with completion confirmation.
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
**If work_type is not set:**
|
|
48
|
+
|
|
49
|
+
> *Output the next fenced block as a code block:*
|
|
50
|
+
|
|
51
|
+
```
|
|
52
|
+
Review complete: {topic}
|
|
53
|
+
|
|
54
|
+
All checks passed. The implementation has been validated.
|
|
55
|
+
```
|
|
56
|
+
|
|
33
57
|
**STOP.** Do not proceed — terminal condition.
|
|
34
58
|
|
|
35
59
|
#### If any verdict is "Request Changes"
|
|
@@ -62,6 +86,24 @@ Proceed with synthesis?
|
|
|
62
86
|
|
|
63
87
|
#### If no
|
|
64
88
|
|
|
89
|
+
User has chosen to skip synthesis. This is a terminal condition, but check for pipeline continuation first.
|
|
90
|
+
|
|
91
|
+
**Check for pipeline continuation** — Read the plan file (`.workflows/planning/{topic}/plan.md`) and check for `work_type`
|
|
92
|
+
|
|
93
|
+
**If work_type is set** (feature, bugfix, or greenfield):
|
|
94
|
+
|
|
95
|
+
This review is part of a pipeline. Invoke the `/workflow:bridge` skill:
|
|
96
|
+
|
|
97
|
+
```
|
|
98
|
+
Pipeline bridge for: {topic}
|
|
99
|
+
Work type: {work_type from plan frontmatter}
|
|
100
|
+
Completed phase: review
|
|
101
|
+
|
|
102
|
+
Invoke the workflow:bridge skill to enter plan mode with continuation instructions.
|
|
103
|
+
```
|
|
104
|
+
|
|
105
|
+
**If work_type is not set:**
|
|
106
|
+
|
|
65
107
|
**STOP.** Do not proceed — terminal condition.
|
|
66
108
|
|
|
67
109
|
#### If verdict is "Comments Only"
|
|
@@ -279,7 +321,7 @@ Review findings have been synthesized into {N} implementation tasks.
|
|
|
279
321
|
|
|
280
322
|
## Instructions
|
|
281
323
|
|
|
282
|
-
1. Invoke
|
|
324
|
+
1. Invoke `start-implementation`
|
|
283
325
|
2. The skill will detect the new tasks and start executing them
|
|
284
326
|
|
|
285
327
|
## Context
|
|
@@ -1,6 +1,5 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: technical-specification
|
|
3
|
-
description: "Build validated specifications from source material through collaborative refinement. Use when: (1) User asks to create/build a specification from source material, (2) User wants to validate and refine content before planning, (3) Converting source material (discussions, research, requirements) into standalone specifications, (4) User says 'specify this' or 'create a spec', (5) Need to filter hallucinations and enrich gaps before formal planning. Creates specifications in .workflows/specification/{topic}/specification.md that can be used to build implementation plans."
|
|
4
3
|
user-invocable: false
|
|
5
4
|
---
|
|
6
5
|
|
|
@@ -124,7 +123,7 @@ Found existing specification for **{topic}**.
|
|
|
124
123
|
|
|
125
124
|
Reset `finding_gate_mode` to `gated` in the specification frontmatter (fresh invocation = fresh gates).
|
|
126
125
|
|
|
127
|
-
→
|
|
126
|
+
→ Proceed to **Step 3** (skipping Steps 1–2).
|
|
128
127
|
|
|
129
128
|
#### If `restart`
|
|
130
129
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
7
|
-
##
|
|
7
|
+
## A. Determine Specification Type
|
|
8
8
|
|
|
9
9
|
Before asking for sign-off, assess whether this is a **feature** or **cross-cutting** specification. See **[specification-format.md](specification-format.md)** for type definitions.
|
|
10
10
|
|
|
@@ -37,7 +37,7 @@ Does this assessment seem correct?
|
|
|
37
37
|
|
|
38
38
|
---
|
|
39
39
|
|
|
40
|
-
##
|
|
40
|
+
## B. Verify Tracking Files Complete
|
|
41
41
|
|
|
42
42
|
Before proceeding to sign-off, confirm that all review tracking files across all cycles have `status: complete`:
|
|
43
43
|
|
|
@@ -50,7 +50,7 @@ If any tracking file still shows `status: in-progress`, mark it complete now.
|
|
|
50
50
|
|
|
51
51
|
---
|
|
52
52
|
|
|
53
|
-
##
|
|
53
|
+
## C. Sign-Off
|
|
54
54
|
|
|
55
55
|
> *Output the next fenced block as markdown (not a code block):*
|
|
56
56
|
|
|
@@ -69,11 +69,11 @@ Discuss the user's context, apply any changes, then re-present the sign-off prom
|
|
|
69
69
|
|
|
70
70
|
#### If yes
|
|
71
71
|
|
|
72
|
-
→ Proceed to **
|
|
72
|
+
→ Proceed to **D. Update Frontmatter and Conclude**.
|
|
73
73
|
|
|
74
74
|
---
|
|
75
75
|
|
|
76
|
-
##
|
|
76
|
+
## D. Update Frontmatter and Conclude
|
|
77
77
|
|
|
78
78
|
Update the specification frontmatter:
|
|
79
79
|
|
|
@@ -101,7 +101,7 @@ Commit: `spec({topic}): conclude specification`
|
|
|
101
101
|
|
|
102
102
|
---
|
|
103
103
|
|
|
104
|
-
##
|
|
104
|
+
## E. Handle Source Specifications
|
|
105
105
|
|
|
106
106
|
If any of your sources were **existing specifications** (as opposed to discussions, research, or other reference material), these have now been consolidated into the new specification.
|
|
107
107
|
|
|
@@ -112,3 +112,31 @@ If any of your sources were **existing specifications** (as opposed to discussio
|
|
|
112
112
|
```
|
|
113
113
|
2. Inform the user which files were updated
|
|
114
114
|
3. Commit: `spec({topic}): mark source specifications as superseded`
|
|
115
|
+
|
|
116
|
+
---
|
|
117
|
+
|
|
118
|
+
## F. Pipeline Continuation
|
|
119
|
+
|
|
120
|
+
Check the specification frontmatter for `work_type`.
|
|
121
|
+
|
|
122
|
+
#### If work_type is set (feature, bugfix, or greenfield)
|
|
123
|
+
|
|
124
|
+
This specification is part of a pipeline. Invoke the `/workflow:bridge` skill:
|
|
125
|
+
|
|
126
|
+
```
|
|
127
|
+
Pipeline bridge for: {topic}
|
|
128
|
+
Work type: {work_type from artifact frontmatter}
|
|
129
|
+
Completed phase: specification
|
|
130
|
+
|
|
131
|
+
Invoke the workflow:bridge skill to enter plan mode with continuation instructions.
|
|
132
|
+
```
|
|
133
|
+
|
|
134
|
+
#### If work_type is not set
|
|
135
|
+
|
|
136
|
+
> *Output the next fenced block as a code block:*
|
|
137
|
+
|
|
138
|
+
```
|
|
139
|
+
Specification concluded: {topic}
|
|
140
|
+
|
|
141
|
+
The specification is ready for planning. Run /start-planning to begin.
|
|
142
|
+
```
|
|
@@ -56,11 +56,11 @@ were still found last cycle) or skip to completion.
|
|
|
56
56
|
|
|
57
57
|
#### If `proceed`
|
|
58
58
|
|
|
59
|
-
→
|
|
59
|
+
→ Proceed to **B. Phase 1 — Input Review**.
|
|
60
60
|
|
|
61
61
|
#### If `skip`
|
|
62
62
|
|
|
63
|
-
→
|
|
63
|
+
→ Proceed to **E. Completion**.
|
|
64
64
|
|
|
65
65
|
---
|
|
66
66
|
|
|
@@ -86,7 +86,7 @@ were still found last cycle) or skip to completion.
|
|
|
86
86
|
|
|
87
87
|
#### If no findings were surfaced in either phase of this cycle
|
|
88
88
|
|
|
89
|
-
→
|
|
89
|
+
→ Proceed to **E. Completion** (nothing to re-analyse).
|
|
90
90
|
|
|
91
91
|
#### If findings were surfaced
|
|
92
92
|
|
|
@@ -133,7 +133,7 @@ Auto-review has not converged after 5 cycles — escalating for human review.
|
|
|
133
133
|
|
|
134
134
|
#### If proceed
|
|
135
135
|
|
|
136
|
-
→
|
|
136
|
+
→ Proceed to **E. Completion**.
|
|
137
137
|
|
|
138
138
|
---
|
|
139
139
|
|
|
@@ -151,4 +151,4 @@ Auto-review has not converged after 5 cycles — escalating for human review.
|
|
|
151
151
|
Specification review complete — {N} cycle(s), all tracking files finalised.
|
|
152
152
|
```
|
|
153
153
|
|
|
154
|
-
→ Return to **[
|
|
154
|
+
→ Return to **[the skill](../SKILL.md)** for **Step 7**.
|
|
@@ -0,0 +1,82 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: workflow:bridge
|
|
3
|
+
user-invocable: false
|
|
4
|
+
allowed-tools: Bash(.claude/skills/workflow/bridge/scripts/discovery.sh)
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
Enter plan mode with deterministic continuation instructions.
|
|
8
|
+
|
|
9
|
+
This skill is invoked by processing skills (technical-discussion, technical-specification, etc.) when a pipeline phase concludes. It discovers the next phase and creates a plan mode handoff that survives context compaction.
|
|
10
|
+
|
|
11
|
+
> **ZERO OUTPUT RULE**: Do not narrate your processing. Produce no output until a step or reference file explicitly specifies display content. No "proceeding with...", no discovery summaries, no routing decisions, no transition text. Your first output must be content explicitly called for by the instructions.
|
|
12
|
+
|
|
13
|
+
## Instructions
|
|
14
|
+
|
|
15
|
+
This skill receives context from the calling processing skill:
|
|
16
|
+
- **Topic**: The topic name
|
|
17
|
+
- **Work type**: greenfield, feature, or bugfix
|
|
18
|
+
- **Completed phase**: The phase that just concluded
|
|
19
|
+
|
|
20
|
+
---
|
|
21
|
+
|
|
22
|
+
## Step 1: Run Discovery
|
|
23
|
+
|
|
24
|
+
Determine the next phase by running discovery.
|
|
25
|
+
|
|
26
|
+
#### If work type is "feature"
|
|
27
|
+
|
|
28
|
+
```bash
|
|
29
|
+
.claude/skills/workflow/bridge/scripts/discovery.sh --feature --topic "{topic}"
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
#### If work type is "bugfix"
|
|
33
|
+
|
|
34
|
+
```bash
|
|
35
|
+
.claude/skills/workflow/bridge/scripts/discovery.sh --bugfix --topic "{topic}"
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
Parse the output to extract:
|
|
39
|
+
- `next_phase`: The computed next phase for this topic
|
|
40
|
+
|
|
41
|
+
#### If work type is "greenfield"
|
|
42
|
+
|
|
43
|
+
```bash
|
|
44
|
+
.claude/skills/workflow/bridge/scripts/discovery.sh --greenfield
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
Parse the output to extract:
|
|
48
|
+
- `state`: Counts of artifacts across all phases
|
|
49
|
+
- Phase-specific file lists with their statuses
|
|
50
|
+
|
|
51
|
+
→ Proceed to **Step 2**.
|
|
52
|
+
|
|
53
|
+
---
|
|
54
|
+
|
|
55
|
+
## Step 2: Route to Continuation Reference
|
|
56
|
+
|
|
57
|
+
Based on work type, load the appropriate continuation reference:
|
|
58
|
+
|
|
59
|
+
#### If work type is "feature"
|
|
60
|
+
|
|
61
|
+
Load **[feature-continuation.md](references/feature-continuation.md)** and follow its instructions as written.
|
|
62
|
+
|
|
63
|
+
#### If work type is "bugfix"
|
|
64
|
+
|
|
65
|
+
Load **[bugfix-continuation.md](references/bugfix-continuation.md)** and follow its instructions as written.
|
|
66
|
+
|
|
67
|
+
#### If work type is "greenfield"
|
|
68
|
+
|
|
69
|
+
Load **[greenfield-continuation.md](references/greenfield-continuation.md)** and follow its instructions as written.
|
|
70
|
+
|
|
71
|
+
---
|
|
72
|
+
|
|
73
|
+
## Notes
|
|
74
|
+
|
|
75
|
+
**Feature/bugfix** continuation references:
|
|
76
|
+
1. Use discovery output to compute a single `next_phase`
|
|
77
|
+
2. Enter plan mode with instructions to invoke `start-{next_phase}` with topic + work_type
|
|
78
|
+
3. Exit plan mode for user approval
|
|
79
|
+
|
|
80
|
+
The user will then clear context, and the fresh session will invoke the appropriate start-* skill with the topic and work_type provided, causing it to skip discovery and proceed directly to validation/processing.
|
|
81
|
+
|
|
82
|
+
**Greenfield** continuation is interactive — greenfield is phase-centric with multiple actionable items, so there is no single next phase. The reference displays state, presents a menu of choices, waits for user selection, then enters plan mode with that specific choice. The plan mode content is deterministic (same as feature/bugfix) once the user has chosen.
|
|
@@ -0,0 +1,59 @@
|
|
|
1
|
+
# Bugfix Continuation
|
|
2
|
+
|
|
3
|
+
*Reference for **[workflow:bridge](../SKILL.md)***
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
Route a bugfix to its next pipeline phase and enter plan mode with continuation instructions.
|
|
8
|
+
|
|
9
|
+
Bugfix pipeline: Investigation → Specification → Planning → Implementation → Review
|
|
10
|
+
|
|
11
|
+
## Phase Routing
|
|
12
|
+
|
|
13
|
+
Use `next_phase` from discovery output to determine the target skill:
|
|
14
|
+
|
|
15
|
+
| next_phase | Target Skill | Plan Mode Instructions |
|
|
16
|
+
|------------|--------------|------------------------|
|
|
17
|
+
| investigation | start-investigation | Resume investigation for topic |
|
|
18
|
+
| specification | start-specification | Start/resume specification for topic |
|
|
19
|
+
| planning | start-planning | Start/resume planning for topic |
|
|
20
|
+
| implementation | start-implementation | Start/resume implementation for topic |
|
|
21
|
+
| review | start-review | Start review for topic |
|
|
22
|
+
| done | (terminal) | Pipeline complete |
|
|
23
|
+
|
|
24
|
+
## Generate Plan Mode Content
|
|
25
|
+
|
|
26
|
+
#### If next_phase is "done"
|
|
27
|
+
|
|
28
|
+
> *Output the next fenced block as a code block:*
|
|
29
|
+
|
|
30
|
+
```
|
|
31
|
+
Bugfix Complete
|
|
32
|
+
|
|
33
|
+
"{topic:(titlecase)}" has completed all pipeline phases.
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
**STOP.** Do not proceed — terminal condition.
|
|
37
|
+
|
|
38
|
+
#### Otherwise
|
|
39
|
+
|
|
40
|
+
Enter plan mode with the following content:
|
|
41
|
+
|
|
42
|
+
```
|
|
43
|
+
# Continue Bugfix: {topic}
|
|
44
|
+
|
|
45
|
+
The previous phase has concluded. Continue the pipeline.
|
|
46
|
+
|
|
47
|
+
## Next Step
|
|
48
|
+
|
|
49
|
+
Invoke `/start-{next_phase} bugfix {topic}`
|
|
50
|
+
|
|
51
|
+
Arguments: work_type = bugfix, topic = {topic}
|
|
52
|
+
The skill will skip discovery and proceed directly to validation.
|
|
53
|
+
|
|
54
|
+
## How to proceed
|
|
55
|
+
|
|
56
|
+
Clear context and continue.
|
|
57
|
+
```
|
|
58
|
+
|
|
59
|
+
Exit plan mode. The user will approve and clear context.
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
# Feature Continuation
|
|
2
|
+
|
|
3
|
+
*Reference for **[workflow:bridge](../SKILL.md)***
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
Route a feature to its next pipeline phase and enter plan mode with continuation instructions.
|
|
8
|
+
|
|
9
|
+
Feature pipeline: (Research) → Discussion → Specification → Planning → Implementation → Review
|
|
10
|
+
|
|
11
|
+
## Phase Routing
|
|
12
|
+
|
|
13
|
+
Use `next_phase` from discovery output to determine the target skill:
|
|
14
|
+
|
|
15
|
+
| next_phase | Target Skill | Plan Mode Instructions |
|
|
16
|
+
|------------|--------------|------------------------|
|
|
17
|
+
| research | start-research | Resume research for topic |
|
|
18
|
+
| discussion | start-discussion | Start/resume discussion for topic |
|
|
19
|
+
| specification | start-specification | Start/resume specification for topic |
|
|
20
|
+
| planning | start-planning | Start/resume planning for topic |
|
|
21
|
+
| implementation | start-implementation | Start/resume implementation for topic |
|
|
22
|
+
| review | start-review | Start review for topic |
|
|
23
|
+
| done | (terminal) | Pipeline complete |
|
|
24
|
+
|
|
25
|
+
## Generate Plan Mode Content
|
|
26
|
+
|
|
27
|
+
#### If next_phase is "done"
|
|
28
|
+
|
|
29
|
+
> *Output the next fenced block as a code block:*
|
|
30
|
+
|
|
31
|
+
```
|
|
32
|
+
Feature Complete
|
|
33
|
+
|
|
34
|
+
"{topic:(titlecase)}" has completed all pipeline phases.
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
**STOP.** Do not proceed — terminal condition.
|
|
38
|
+
|
|
39
|
+
#### Otherwise
|
|
40
|
+
|
|
41
|
+
Enter plan mode with the following content:
|
|
42
|
+
|
|
43
|
+
```
|
|
44
|
+
# Continue Feature: {topic}
|
|
45
|
+
|
|
46
|
+
The previous phase has concluded. Continue the pipeline.
|
|
47
|
+
|
|
48
|
+
## Next Step
|
|
49
|
+
|
|
50
|
+
Invoke `/start-{next_phase} feature {topic}`
|
|
51
|
+
|
|
52
|
+
Arguments: work_type = feature, topic = {topic}
|
|
53
|
+
The skill will skip discovery and proceed directly to validation.
|
|
54
|
+
|
|
55
|
+
## How to proceed
|
|
56
|
+
|
|
57
|
+
Clear context and continue.
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
Exit plan mode. The user will approve and clear context.
|