@leeovery/claude-technical-workflows 2.1.41 → 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.
Files changed (119) hide show
  1. package/README.md +5 -20
  2. package/hooks/workflows/compact-recovery.sh +3 -23
  3. package/hooks/workflows/write-session-state.sh +2 -26
  4. package/package.json +1 -1
  5. package/skills/link-dependencies/SKILL.md +0 -1
  6. package/skills/migrate/SKILL.md +0 -1
  7. package/skills/migrate/scripts/migrations/013-discussion-work-type.sh +76 -0
  8. package/skills/migrate/scripts/migrations/014-specification-work-type.sh +76 -0
  9. package/skills/migrate/scripts/migrations/015-plan-work-type.sh +76 -0
  10. package/skills/start-bugfix/SKILL.md +80 -0
  11. package/skills/start-bugfix/references/gather-bug-context.md +75 -0
  12. package/skills/start-bugfix/references/invoke-investigation.md +46 -0
  13. package/skills/start-bugfix/references/topic-name-check.md +59 -0
  14. package/skills/start-discussion/SKILL.md +51 -46
  15. package/skills/start-discussion/references/gather-context.md +54 -10
  16. package/skills/start-discussion/references/handle-selection.md +14 -4
  17. package/skills/start-discussion/references/invoke-skill.md +71 -3
  18. package/skills/start-discussion/references/research-analysis.md +2 -0
  19. package/skills/start-discussion/references/route-scenario.md +39 -0
  20. package/skills/start-discussion/references/validate-topic.md +46 -0
  21. package/skills/start-discussion/scripts/discovery.sh +3 -0
  22. package/skills/start-feature/SKILL.md +28 -84
  23. package/skills/start-feature/references/invoke-discussion.md +8 -4
  24. package/skills/start-feature/references/invoke-research.md +29 -0
  25. package/skills/start-feature/references/invoke-skill.md +35 -0
  26. package/skills/start-feature/references/research-gating.md +65 -0
  27. package/skills/start-feature/references/topic-name-check.md +61 -0
  28. package/skills/start-implementation/SKILL.md +35 -289
  29. package/skills/start-implementation/references/check-dependencies.md +65 -0
  30. package/skills/start-implementation/references/display-plans.md +159 -0
  31. package/skills/start-implementation/references/environment-check.md +45 -0
  32. package/skills/start-implementation/references/invoke-skill.md +42 -0
  33. package/skills/start-implementation/references/route-scenario.md +32 -0
  34. package/skills/start-implementation/references/validate-plan.md +45 -0
  35. package/skills/start-implementation/scripts/discovery.sh +3 -0
  36. package/skills/start-investigation/SKILL.md +145 -0
  37. package/skills/start-investigation/references/gather-context-fresh.md +72 -0
  38. package/skills/start-investigation/references/gather-context.md +31 -0
  39. package/skills/start-investigation/references/invoke-skill.md +54 -0
  40. package/skills/start-investigation/references/route-scenario.md +69 -0
  41. package/skills/start-investigation/references/validate-investigation.md +46 -0
  42. package/skills/start-investigation/scripts/discovery.sh +92 -0
  43. package/skills/start-planning/SKILL.md +32 -72
  44. package/skills/start-planning/references/cross-cutting-context.md +5 -5
  45. package/skills/start-planning/references/invoke-skill.md +27 -4
  46. package/skills/start-planning/references/route-plan-state.md +30 -0
  47. package/skills/start-planning/references/route-scenario.md +38 -0
  48. package/skills/start-planning/references/validate-spec.md +47 -0
  49. package/skills/start-planning/scripts/discovery.sh +7 -0
  50. package/skills/start-research/SKILL.md +17 -6
  51. package/skills/start-research/references/invoke-skill.md +3 -0
  52. package/skills/start-review/SKILL.md +32 -60
  53. package/skills/start-review/references/determine-review-version.md +24 -0
  54. package/skills/start-review/references/display-plans.md +2 -2
  55. package/skills/start-review/references/route-scenario.md +74 -0
  56. package/skills/start-review/references/select-plans.md +8 -6
  57. package/skills/start-review/references/validate-artifacts.md +63 -0
  58. package/skills/start-review/scripts/discovery.sh +3 -0
  59. package/skills/start-specification/SKILL.md +44 -20
  60. package/skills/start-specification/references/check-existing-spec.md +57 -0
  61. package/skills/start-specification/references/check-prerequisites.md +15 -0
  62. package/skills/start-specification/references/handoffs/continue-concluded.md +3 -0
  63. package/skills/start-specification/references/handoffs/continue.md +3 -0
  64. package/skills/start-specification/references/handoffs/create-with-incorporation.md +3 -0
  65. package/skills/start-specification/references/handoffs/create.md +3 -0
  66. package/skills/start-specification/references/handoffs/unify-with-incorporation.md +3 -0
  67. package/skills/start-specification/references/handoffs/unify.md +3 -0
  68. package/skills/start-specification/references/invoke-skill-bridge.md +74 -0
  69. package/skills/start-specification/references/route-scenario.md +23 -0
  70. package/skills/start-specification/references/validate-source.md +91 -0
  71. package/skills/start-specification/scripts/discovery.sh +6 -0
  72. package/skills/status/SKILL.md +6 -3
  73. package/skills/status/scripts/discovery.sh +9 -0
  74. package/skills/technical-discussion/SKILL.md +15 -4
  75. package/skills/technical-discussion/references/template.md +9 -1
  76. package/skills/technical-implementation/SKILL.md +24 -1
  77. package/skills/technical-implementation/references/analysis-loop.md +4 -4
  78. package/skills/technical-implementation/references/task-loop.md +2 -2
  79. package/skills/technical-investigation/SKILL.md +239 -0
  80. package/skills/technical-investigation/references/analysis-patterns.md +181 -0
  81. package/skills/technical-investigation/references/symptom-gathering.md +164 -0
  82. package/skills/technical-investigation/references/template.md +164 -0
  83. package/skills/technical-planning/SKILL.md +24 -1
  84. package/skills/technical-planning/references/author-tasks.md +16 -16
  85. package/skills/technical-planning/references/define-tasks.md +2 -2
  86. package/skills/technical-planning/references/output-formats/tick/authoring.md +3 -15
  87. package/skills/technical-planning/references/plan-construction.md +11 -30
  88. package/skills/technical-planning/references/plan-review.md +3 -3
  89. package/skills/technical-research/SKILL.md +38 -2
  90. package/skills/technical-review/SKILL.md +1 -2
  91. package/skills/technical-review/references/review-actions-loop.md +43 -1
  92. package/skills/technical-specification/SKILL.md +1 -2
  93. package/skills/technical-specification/references/spec-completion.md +34 -6
  94. package/skills/technical-specification/references/spec-construction.md +1 -1
  95. package/skills/technical-specification/references/spec-review.md +5 -5
  96. package/skills/view-plan/SKILL.md +0 -1
  97. package/skills/workflow/bridge/SKILL.md +82 -0
  98. package/skills/workflow/bridge/references/bugfix-continuation.md +59 -0
  99. package/skills/workflow/bridge/references/feature-continuation.md +60 -0
  100. package/skills/workflow/bridge/references/greenfield-continuation.md +224 -0
  101. package/skills/workflow/bridge/scripts/discovery.sh +512 -0
  102. package/skills/workflow/start/SKILL.md +97 -0
  103. package/skills/workflow/start/references/bugfix-routing.md +117 -0
  104. package/skills/workflow/start/references/feature-routing.md +117 -0
  105. package/skills/workflow/start/references/greenfield-routing.md +140 -0
  106. package/skills/workflow/start/references/work-type-selection.md +83 -0
  107. package/skills/workflow/start/scripts/discovery.sh +577 -0
  108. package/skills/begin-implementation/SKILL.md +0 -162
  109. package/skills/begin-planning/SKILL.md +0 -92
  110. package/skills/begin-review/SKILL.md +0 -90
  111. package/skills/continue-feature/SKILL.md +0 -186
  112. package/skills/continue-feature/references/detect-phase.md +0 -99
  113. package/skills/continue-feature/references/invoke-implementation.md +0 -43
  114. package/skills/continue-feature/references/invoke-planning.md +0 -43
  115. package/skills/continue-feature/references/invoke-review.md +0 -43
  116. package/skills/continue-feature/references/invoke-specification.md +0 -55
  117. package/skills/continue-feature/references/phase-bridge.md +0 -57
  118. package/skills/continue-feature/scripts/discovery.sh +0 -233
  119. 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. It operates as a nested structure:
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
- Go to **Step A** with this phase.
49
+ Proceed to **A. Define Tasks** with this phase.
69
50
 
70
- After Step A returns with an approved task table, continue to **Author Tasks for the Phase** below.
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
- Continue to **Author Tasks for the Phase** below.
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
- Go to **Step A** with this phase for revision.
92
+ Proceed to **A. Define Tasks** with this phase for revision.
112
93
 
113
94
  #### If confirmed
114
95
 
115
- Continue to **Author Tasks for the Phase** below.
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
- Continue to the next phase.
114
+ Proceed to the next phase.
134
115
 
135
116
  #### If any tasks in the phase have status `pending`
136
117
 
137
- Go to **Step B** for the entire phase.
118
+ Proceed to **B. Author Tasks** for the entire phase.
138
119
 
139
- After Step B returns, all tasks in the phase are authored.
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
- ## Step A: Define Tasks
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
- ## Step B: Author Tasks
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 directly to **E. Completion**.
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
- Continue to **E. Completion**.
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 **[technical-planning SKILL.md](../SKILL.md)** for **Step 8**.
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
- Then continue with whatever's next — another topic, a different angle, or wrapping up the session.
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
- Go directly to **Step 6**.
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 `/start-implementation`
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
- Skip Steps 1–2, proceed to **Step 3**.
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
- ## Step 1: Determine Specification Type
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
- ## Step 2: Verify Tracking Files Complete
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
- ## Step 3: Sign-Off
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 **Step 4**.
72
+ → Proceed to **D. Update Frontmatter and Conclude**.
73
73
 
74
74
  ---
75
75
 
76
- ## Step 4: Update Frontmatter and Conclude
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
- ## Step 5: Handle Source Specifications
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
+ ```
@@ -106,4 +106,4 @@ This is the end of this iteration.
106
106
 
107
107
  #### If all topics are covered
108
108
 
109
- → Return to **[technical-specification SKILL.md](../SKILL.md)** for **Step 5**.
109
+ → Return to **[the skill](../SKILL.md)** for **Step 5**.
@@ -56,11 +56,11 @@ were still found last cycle) or skip to completion.
56
56
 
57
57
  #### If `proceed`
58
58
 
59
- Continue to **B. Phase 1 — Input Review**.
59
+ Proceed to **B. Phase 1 — Input Review**.
60
60
 
61
61
  #### If `skip`
62
62
 
63
- Jump to **E. Completion**.
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
- Skip the re-loop prompt and proceed directly to **E. Completion** (nothing to re-analyse).
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
- Continue to **E. Completion**.
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 **[technical-specification SKILL.md](../SKILL.md)** for **Step 7**.
154
+ → Return to **[the skill](../SKILL.md)** for **Step 7**.
@@ -1,6 +1,5 @@
1
1
  ---
2
2
  name: view-plan
3
- description: "View a plan's tasks and progress, regardless of output format."
4
3
  disable-model-invocation: true
5
4
  hooks:
6
5
  PreToolUse:
@@ -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.