@leeovery/claude-technical-workflows 2.1.42 → 2.2.1
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 +10 -9
- 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
|
@@ -1,162 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: begin-implementation
|
|
3
|
-
description: "Bridge skill for the feature pipeline. Runs pre-flight checks for implementation and invokes the technical-implementation skill. Called by continue-feature — not directly by users."
|
|
4
|
-
user-invocable: false
|
|
5
|
-
allowed-tools: Bash(.claude/skills/start-implementation/scripts/discovery.sh)
|
|
6
|
-
---
|
|
7
|
-
|
|
8
|
-
Invoke the **technical-implementation** skill for this conversation with pre-flight context.
|
|
9
|
-
|
|
10
|
-
> **⚠️ 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.
|
|
11
|
-
|
|
12
|
-
## Instructions
|
|
13
|
-
|
|
14
|
-
Follow these steps EXACTLY as written. Do not skip steps or combine them.
|
|
15
|
-
|
|
16
|
-
This skill is a **bridge** — it runs pre-flight checks for implementation and hands off to the processing skill. The topic has already been selected by the caller.
|
|
17
|
-
|
|
18
|
-
**CRITICAL**: This guidance is mandatory.
|
|
19
|
-
|
|
20
|
-
- After each user interaction, STOP and wait for their response before proceeding
|
|
21
|
-
- Never assume or anticipate user choices
|
|
22
|
-
- Complete each step fully before moving to the next
|
|
23
|
-
|
|
24
|
-
---
|
|
25
|
-
|
|
26
|
-
## Step 1: Run Discovery
|
|
27
|
-
|
|
28
|
-
!`.claude/skills/start-implementation/scripts/discovery.sh`
|
|
29
|
-
|
|
30
|
-
If the above shows a script invocation rather than YAML output, the dynamic content preprocessor did not run. Execute the script before continuing:
|
|
31
|
-
|
|
32
|
-
```bash
|
|
33
|
-
.claude/skills/start-implementation/scripts/discovery.sh
|
|
34
|
-
```
|
|
35
|
-
|
|
36
|
-
If YAML content is already displayed, it has been run on your behalf.
|
|
37
|
-
|
|
38
|
-
Parse the output to find the plan matching the provided topic. Extract:
|
|
39
|
-
|
|
40
|
-
- **Plan details**: status, format, plan_id, specification, specification_exists
|
|
41
|
-
- **External dependencies**: external_deps, has_unresolved_deps
|
|
42
|
-
- **Dependency resolution**: deps_satisfied, deps_blocking
|
|
43
|
-
- **Implementation tracking**: from `implementation.files` matching the topic
|
|
44
|
-
- **Environment**: setup_file_exists, requires_setup
|
|
45
|
-
|
|
46
|
-
If the plan is missing or not concluded, this is an error — report it and stop.
|
|
47
|
-
|
|
48
|
-
→ Proceed to **Step 2**.
|
|
49
|
-
|
|
50
|
-
---
|
|
51
|
-
|
|
52
|
-
## Step 2: Check External Dependencies
|
|
53
|
-
|
|
54
|
-
Check the plan's `external_deps` and `dependency_resolution` from the discovery output.
|
|
55
|
-
|
|
56
|
-
#### If all deps satisfied (or no deps)
|
|
57
|
-
|
|
58
|
-
> *Output the next fenced block as a code block:*
|
|
59
|
-
|
|
60
|
-
```
|
|
61
|
-
External dependencies satisfied.
|
|
62
|
-
```
|
|
63
|
-
|
|
64
|
-
→ Proceed to **Step 3**.
|
|
65
|
-
|
|
66
|
-
#### If any deps are blocking
|
|
67
|
-
|
|
68
|
-
> *Output the next fenced block as a code block:*
|
|
69
|
-
|
|
70
|
-
```
|
|
71
|
-
Missing Dependencies
|
|
72
|
-
|
|
73
|
-
Unresolved (not yet planned):
|
|
74
|
-
• {topic}: {description}
|
|
75
|
-
No plan exists. Create with /start-planning or mark as
|
|
76
|
-
satisfied externally.
|
|
77
|
-
|
|
78
|
-
Incomplete (planned but not implemented):
|
|
79
|
-
• {topic}: {plan}:{task-id} not yet completed
|
|
80
|
-
This task must be completed first.
|
|
81
|
-
```
|
|
82
|
-
|
|
83
|
-
> *Output the next fenced block as markdown (not a code block):*
|
|
84
|
-
|
|
85
|
-
```
|
|
86
|
-
· · · · · · · · · · · ·
|
|
87
|
-
- **`i`/`implement`** — Implement the blocking dependencies first
|
|
88
|
-
- **`s`/`satisfied`** — Mark a dependency as satisfied externally
|
|
89
|
-
- **`c`/`continue`** — Continue anyway (at your own risk)
|
|
90
|
-
· · · · · · · · · · · ·
|
|
91
|
-
```
|
|
92
|
-
|
|
93
|
-
**STOP.** Wait for user response.
|
|
94
|
-
|
|
95
|
-
If the user chooses `implement`, end here — suggest running `/start-implementation` for the blocking topic. If `satisfied`, update the plan frontmatter (`state: satisfied_externally`) and continue. If `continue`, proceed.
|
|
96
|
-
|
|
97
|
-
→ Proceed to **Step 3**.
|
|
98
|
-
|
|
99
|
-
---
|
|
100
|
-
|
|
101
|
-
## Step 3: Check Environment Setup
|
|
102
|
-
|
|
103
|
-
Use the `environment` section from the discovery output:
|
|
104
|
-
|
|
105
|
-
**If `setup_file_exists: true` and `requires_setup: false`:**
|
|
106
|
-
|
|
107
|
-
> *Output the next fenced block as a code block:*
|
|
108
|
-
|
|
109
|
-
```
|
|
110
|
-
Environment: No special setup required.
|
|
111
|
-
```
|
|
112
|
-
|
|
113
|
-
→ Proceed to **Step 4**.
|
|
114
|
-
|
|
115
|
-
**If `setup_file_exists: true` and `requires_setup: true`:**
|
|
116
|
-
|
|
117
|
-
> *Output the next fenced block as a code block:*
|
|
118
|
-
|
|
119
|
-
```
|
|
120
|
-
Environment setup file found: .workflows/environment-setup.md
|
|
121
|
-
```
|
|
122
|
-
|
|
123
|
-
→ Proceed to **Step 4**.
|
|
124
|
-
|
|
125
|
-
**If `setup_file_exists: false` or `requires_setup: unknown`:**
|
|
126
|
-
|
|
127
|
-
> *Output the next fenced block as a code block:*
|
|
128
|
-
|
|
129
|
-
```
|
|
130
|
-
Are there any environment setup instructions I should follow before implementation?
|
|
131
|
-
(Or "none" if no special setup is needed)
|
|
132
|
-
```
|
|
133
|
-
|
|
134
|
-
**STOP.** Wait for user response.
|
|
135
|
-
|
|
136
|
-
- If the user provides instructions, save them to `.workflows/environment-setup.md`, commit
|
|
137
|
-
- If the user says no/none, create `.workflows/environment-setup.md` with "No special setup required." and commit
|
|
138
|
-
|
|
139
|
-
→ Proceed to **Step 4**.
|
|
140
|
-
|
|
141
|
-
---
|
|
142
|
-
|
|
143
|
-
## Step 4: Invoke the Skill
|
|
144
|
-
|
|
145
|
-
Determine the implementation tracking state:
|
|
146
|
-
- If a tracking file exists for this topic → use its status
|
|
147
|
-
- If no tracking file → status is "not-started"
|
|
148
|
-
|
|
149
|
-
Construct the handoff and invoke the [technical-implementation](../technical-implementation/SKILL.md) skill:
|
|
150
|
-
|
|
151
|
-
```
|
|
152
|
-
Implementation session for: {topic}
|
|
153
|
-
Plan: .workflows/planning/{topic}/plan.md
|
|
154
|
-
Format: {format}
|
|
155
|
-
Plan ID: {plan_id} (if applicable)
|
|
156
|
-
Specification: .workflows/specification/{topic}/specification.md (exists: {true|false})
|
|
157
|
-
Implementation tracking: {exists | new} (status: {status})
|
|
158
|
-
Dependencies: {All satisfied | notes}
|
|
159
|
-
Environment: {Setup required | No special setup required}
|
|
160
|
-
|
|
161
|
-
Invoke the technical-implementation skill.
|
|
162
|
-
```
|
|
@@ -1,92 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: begin-planning
|
|
3
|
-
description: "Bridge skill for the feature pipeline. Runs pre-flight checks for planning and invokes the technical-planning skill. Called by continue-feature — not directly by users."
|
|
4
|
-
user-invocable: false
|
|
5
|
-
allowed-tools: Bash(.claude/skills/start-planning/scripts/discovery.sh)
|
|
6
|
-
---
|
|
7
|
-
|
|
8
|
-
Invoke the **technical-planning** skill for this conversation with pre-flight context.
|
|
9
|
-
|
|
10
|
-
> **⚠️ 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.
|
|
11
|
-
|
|
12
|
-
## Instructions
|
|
13
|
-
|
|
14
|
-
Follow these steps EXACTLY as written. Do not skip steps or combine them.
|
|
15
|
-
|
|
16
|
-
This skill is a **bridge** — it runs pre-flight checks for planning and hands off to the processing skill. The topic has already been selected by the caller.
|
|
17
|
-
|
|
18
|
-
**CRITICAL**: This guidance is mandatory.
|
|
19
|
-
|
|
20
|
-
- After each user interaction, STOP and wait for their response before proceeding
|
|
21
|
-
- Never assume or anticipate user choices
|
|
22
|
-
- Complete each step fully before moving to the next
|
|
23
|
-
|
|
24
|
-
---
|
|
25
|
-
|
|
26
|
-
## Step 1: Run Discovery
|
|
27
|
-
|
|
28
|
-
!`.claude/skills/start-planning/scripts/discovery.sh`
|
|
29
|
-
|
|
30
|
-
If the above shows a script invocation rather than YAML output, the dynamic content preprocessor did not run. Execute the script before continuing:
|
|
31
|
-
|
|
32
|
-
```bash
|
|
33
|
-
.claude/skills/start-planning/scripts/discovery.sh
|
|
34
|
-
```
|
|
35
|
-
|
|
36
|
-
If YAML content is already displayed, it has been run on your behalf.
|
|
37
|
-
|
|
38
|
-
Parse the output to extract:
|
|
39
|
-
|
|
40
|
-
- **Cross-cutting specifications** from `specifications.crosscutting` (name, status)
|
|
41
|
-
- **Common format** from `plans.common_format`
|
|
42
|
-
|
|
43
|
-
The topic was provided by the caller. Confirm the specification exists and is concluded:
|
|
44
|
-
|
|
45
|
-
- Check `specifications.feature` for the topic
|
|
46
|
-
- If the spec is missing or not concluded, this is an error — report it and stop
|
|
47
|
-
|
|
48
|
-
→ Proceed to **Step 2**.
|
|
49
|
-
|
|
50
|
-
---
|
|
51
|
-
|
|
52
|
-
## Step 2: Handle Cross-Cutting Context
|
|
53
|
-
|
|
54
|
-
Load **[cross-cutting-context.md](../start-planning/references/cross-cutting-context.md)** and follow its instructions as written.
|
|
55
|
-
|
|
56
|
-
→ Proceed to **Step 3**.
|
|
57
|
-
|
|
58
|
-
---
|
|
59
|
-
|
|
60
|
-
## Step 3: Gather Additional Context
|
|
61
|
-
|
|
62
|
-
> *Output the next fenced block as markdown (not a code block):*
|
|
63
|
-
|
|
64
|
-
```
|
|
65
|
-
· · · · · · · · · · · ·
|
|
66
|
-
Any additional context for planning?
|
|
67
|
-
|
|
68
|
-
- **`c`/`continue`** — Continue with the specification as-is
|
|
69
|
-
- Or provide additional context (priorities, constraints, new considerations)
|
|
70
|
-
· · · · · · · · · · · ·
|
|
71
|
-
```
|
|
72
|
-
|
|
73
|
-
**STOP.** Wait for user response.
|
|
74
|
-
|
|
75
|
-
→ Proceed to **Step 4**.
|
|
76
|
-
|
|
77
|
-
---
|
|
78
|
-
|
|
79
|
-
## Step 4: Invoke the Skill
|
|
80
|
-
|
|
81
|
-
Construct the handoff and invoke the [technical-planning](../technical-planning/SKILL.md) skill:
|
|
82
|
-
|
|
83
|
-
```
|
|
84
|
-
Planning session for: {topic}
|
|
85
|
-
Specification: .workflows/specification/{topic}/specification.md
|
|
86
|
-
Work type: feature
|
|
87
|
-
Additional context: {summary of user's answer from Step 3, or "none"}
|
|
88
|
-
Cross-cutting references: {list of applicable cross-cutting specs with brief summaries, or "none"}
|
|
89
|
-
Recommended output format: {common_format from discovery if non-empty, otherwise "none"}
|
|
90
|
-
|
|
91
|
-
Invoke the technical-planning skill.
|
|
92
|
-
```
|
|
@@ -1,90 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: begin-review
|
|
3
|
-
description: "Bridge skill for the feature pipeline. Runs pre-flight checks for review and invokes the technical-review skill. Called by continue-feature — not directly by users."
|
|
4
|
-
user-invocable: false
|
|
5
|
-
allowed-tools: Bash(.claude/skills/start-review/scripts/discovery.sh)
|
|
6
|
-
---
|
|
7
|
-
|
|
8
|
-
Invoke the **technical-review** skill for this conversation with pre-flight context.
|
|
9
|
-
|
|
10
|
-
> **⚠️ 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.
|
|
11
|
-
|
|
12
|
-
## Instructions
|
|
13
|
-
|
|
14
|
-
Follow these steps EXACTLY as written. Do not skip steps or combine them.
|
|
15
|
-
|
|
16
|
-
This skill is a **bridge** — it runs pre-flight checks for review and hands off to the processing skill. The topic has already been selected by the caller.
|
|
17
|
-
|
|
18
|
-
**CRITICAL**: This guidance is mandatory.
|
|
19
|
-
|
|
20
|
-
- After each user interaction, STOP and wait for their response before proceeding
|
|
21
|
-
- Never assume or anticipate user choices
|
|
22
|
-
- Complete each step fully before moving to the next
|
|
23
|
-
|
|
24
|
-
---
|
|
25
|
-
|
|
26
|
-
## Step 1: Run Discovery
|
|
27
|
-
|
|
28
|
-
!`.claude/skills/start-review/scripts/discovery.sh`
|
|
29
|
-
|
|
30
|
-
If the above shows a script invocation rather than YAML output, the dynamic content preprocessor did not run. Execute the script before continuing:
|
|
31
|
-
|
|
32
|
-
```bash
|
|
33
|
-
.claude/skills/start-review/scripts/discovery.sh
|
|
34
|
-
```
|
|
35
|
-
|
|
36
|
-
If YAML content is already displayed, it has been run on your behalf.
|
|
37
|
-
|
|
38
|
-
Parse the output to find the plan matching the provided topic. Extract:
|
|
39
|
-
|
|
40
|
-
- **Plan details**: status, format, plan_id, specification, specification_exists
|
|
41
|
-
- **Implementation status**: implementation_status
|
|
42
|
-
- **Review state**: review_count, latest_review_version
|
|
43
|
-
|
|
44
|
-
If the plan is missing, this is an error — report it and stop.
|
|
45
|
-
|
|
46
|
-
If `implementation_status` is `"none"`, this is an error:
|
|
47
|
-
|
|
48
|
-
> *Output the next fenced block as a code block:*
|
|
49
|
-
|
|
50
|
-
```
|
|
51
|
-
Review Pre-Flight Failed
|
|
52
|
-
|
|
53
|
-
"{topic:(titlecase)}" has no implementation to review.
|
|
54
|
-
|
|
55
|
-
Implementation must be completed or in-progress before review.
|
|
56
|
-
```
|
|
57
|
-
|
|
58
|
-
**STOP.** Do not proceed — terminal condition.
|
|
59
|
-
|
|
60
|
-
→ Proceed to **Step 2**.
|
|
61
|
-
|
|
62
|
-
---
|
|
63
|
-
|
|
64
|
-
## Step 2: Determine Review Version
|
|
65
|
-
|
|
66
|
-
Check the topic's review state from discovery output:
|
|
67
|
-
|
|
68
|
-
- If `review_count` is 0 → review version is `r1`
|
|
69
|
-
- If `review_count` > 0 → review version is `r{latest_review_version + 1}`
|
|
70
|
-
|
|
71
|
-
→ Proceed to **Step 3**.
|
|
72
|
-
|
|
73
|
-
---
|
|
74
|
-
|
|
75
|
-
## Step 3: Invoke the Skill
|
|
76
|
-
|
|
77
|
-
Construct the handoff and invoke the [technical-review](../technical-review/SKILL.md) skill:
|
|
78
|
-
|
|
79
|
-
```
|
|
80
|
-
Review session
|
|
81
|
-
Plans to review:
|
|
82
|
-
- topic: {topic}
|
|
83
|
-
plan: .workflows/planning/{topic}/plan.md
|
|
84
|
-
format: {format}
|
|
85
|
-
plan_id: {plan_id} (if applicable)
|
|
86
|
-
specification: {specification} (exists: {true|false})
|
|
87
|
-
review_version: r{N}
|
|
88
|
-
|
|
89
|
-
Invoke the technical-review skill.
|
|
90
|
-
```
|
|
@@ -1,186 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: continue-feature
|
|
3
|
-
description: "Continue a feature through the pipeline. Routes to the next phase (specification, planning, or implementation) based on artifact state. Can be invoked manually or from plan mode bridges."
|
|
4
|
-
allowed-tools: Bash(.claude/skills/continue-feature/scripts/discovery.sh), Bash(.claude/hooks/workflows/write-session-state.sh), Bash(.claude/skills/start-review/scripts/discovery.sh)
|
|
5
|
-
hooks:
|
|
6
|
-
PreToolUse:
|
|
7
|
-
- hooks:
|
|
8
|
-
- type: command
|
|
9
|
-
command: "$CLAUDE_PROJECT_DIR/.claude/hooks/workflows/system-check.sh"
|
|
10
|
-
once: true
|
|
11
|
-
---
|
|
12
|
-
|
|
13
|
-
Route a feature to its next pipeline phase.
|
|
14
|
-
|
|
15
|
-
> **⚠️ 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.
|
|
16
|
-
|
|
17
|
-
## Instructions
|
|
18
|
-
|
|
19
|
-
Follow these steps EXACTLY as written. Do not skip steps or combine them.
|
|
20
|
-
|
|
21
|
-
**CRITICAL**: This guidance is mandatory.
|
|
22
|
-
|
|
23
|
-
- After each user interaction, STOP and wait for their response before proceeding
|
|
24
|
-
- Never assume or anticipate user choices
|
|
25
|
-
- Complete each step fully before moving to the next
|
|
26
|
-
|
|
27
|
-
---
|
|
28
|
-
|
|
29
|
-
## Resuming After Context Refresh
|
|
30
|
-
|
|
31
|
-
Context refresh (compaction) summarizes the conversation, losing procedural detail. When you detect a context refresh has occurred — the conversation feels abruptly shorter, you lack memory of recent steps, or a summary precedes this message — follow this recovery protocol:
|
|
32
|
-
|
|
33
|
-
1. **Re-read this skill file completely.** Do not rely on your summary of it. The full process, steps, and rules must be reloaded.
|
|
34
|
-
2. **Identify the topic.** Check conversation history for the topic name. If unknown, ask the user.
|
|
35
|
-
3. **Determine current step from artifacts** (check top-down, first match wins):
|
|
36
|
-
- Review exists for topic → resume at **Step 7** (phase bridge — pipeline complete)
|
|
37
|
-
- Implementation tracking exists with `status: completed`, no review → resume at **Step 6** (invoke begin-review)
|
|
38
|
-
- Implementation tracking exists with `status: in-progress` → resume at **Step 5** (re-invoke begin-implementation)
|
|
39
|
-
- Plan exists with `status: concluded` → resume at **Step 5** (invoke begin-implementation)
|
|
40
|
-
- Plan exists with other status → resume at **Step 4** (re-invoke begin-planning)
|
|
41
|
-
- Specification exists with `status: concluded` → resume at **Step 4** (invoke begin-planning)
|
|
42
|
-
- Specification exists with other status → resume at **Step 3** (re-invoke technical-specification)
|
|
43
|
-
- Discussion exists with `status: concluded` → resume at **Step 3** (invoke technical-specification)
|
|
44
|
-
- Discussion exists with other status → terminal — suggest `/start-discussion`
|
|
45
|
-
4. **Announce your position** to the user before continuing: what step you believe you're at, what's been completed, and what comes next. Wait for confirmation.
|
|
46
|
-
|
|
47
|
-
Do not guess at progress or continue from memory. The files on disk and git history are authoritative — your recollection is not.
|
|
48
|
-
|
|
49
|
-
---
|
|
50
|
-
|
|
51
|
-
## Step 0: Run Migrations
|
|
52
|
-
|
|
53
|
-
**This step is mandatory. You must complete it before proceeding.**
|
|
54
|
-
|
|
55
|
-
Invoke the `/migrate` skill and assess its output.
|
|
56
|
-
|
|
57
|
-
**If files were updated**: STOP and wait for the user to review the changes (e.g., via `git diff`) and confirm before proceeding to Step 1. Do not continue automatically.
|
|
58
|
-
|
|
59
|
-
**If no updates needed**: Proceed to Step 1.
|
|
60
|
-
|
|
61
|
-
---
|
|
62
|
-
|
|
63
|
-
## Step 1: Determine Topic
|
|
64
|
-
|
|
65
|
-
Check whether a topic was provided by the caller (e.g., from a plan mode bridge: "invoke continue-feature for {topic}").
|
|
66
|
-
|
|
67
|
-
#### If topic was provided
|
|
68
|
-
|
|
69
|
-
Use the provided topic directly.
|
|
70
|
-
|
|
71
|
-
→ Proceed to **Step 2**.
|
|
72
|
-
|
|
73
|
-
#### If no topic provided (bare invocation)
|
|
74
|
-
|
|
75
|
-
Run the discovery script to gather current state:
|
|
76
|
-
|
|
77
|
-
```bash
|
|
78
|
-
.claude/skills/continue-feature/scripts/discovery.sh
|
|
79
|
-
```
|
|
80
|
-
|
|
81
|
-
Parse the output to understand:
|
|
82
|
-
|
|
83
|
-
**From `topics` array:** Each topic's name, discussion/specification/plan/implementation state, next_phase, and actionable flag.
|
|
84
|
-
|
|
85
|
-
**From `state` section:** topic_count, actionable_count, scenario.
|
|
86
|
-
|
|
87
|
-
**IMPORTANT**: Use ONLY this script for discovery. Do NOT run additional bash commands (ls, head, cat, etc.) to gather state.
|
|
88
|
-
|
|
89
|
-
#### If scenario is "no_topics"
|
|
90
|
-
|
|
91
|
-
> *Output the next fenced block as a code block:*
|
|
92
|
-
|
|
93
|
-
```
|
|
94
|
-
Continue Feature
|
|
95
|
-
|
|
96
|
-
No workflow topics found.
|
|
97
|
-
|
|
98
|
-
Start a new feature with /start-feature.
|
|
99
|
-
```
|
|
100
|
-
|
|
101
|
-
**STOP.** Do not proceed — terminal condition.
|
|
102
|
-
|
|
103
|
-
#### If topics exist
|
|
104
|
-
|
|
105
|
-
Present the discovered state as context, then ask the user to select:
|
|
106
|
-
|
|
107
|
-
> *Output the next fenced block as a code block:*
|
|
108
|
-
|
|
109
|
-
```
|
|
110
|
-
Continue Feature
|
|
111
|
-
|
|
112
|
-
This skill continues a feature through the pipeline phases:
|
|
113
|
-
Discussion → Specification → Planning → Implementation → Review
|
|
114
|
-
|
|
115
|
-
It's designed for features started with /start-feature, but works
|
|
116
|
-
with any topic that has workflow artifacts.
|
|
117
|
-
|
|
118
|
-
Topics found:
|
|
119
|
-
|
|
120
|
-
1. {topic:(titlecase)}
|
|
121
|
-
└─ Next: {next_phase}
|
|
122
|
-
|
|
123
|
-
2. ...
|
|
124
|
-
```
|
|
125
|
-
|
|
126
|
-
> *Output the next fenced block as markdown (not a code block):*
|
|
127
|
-
|
|
128
|
-
```
|
|
129
|
-
· · · · · · · · · · · ·
|
|
130
|
-
Which topic would you like to continue?
|
|
131
|
-
|
|
132
|
-
Select by number, or enter a topic name directly:
|
|
133
|
-
· · · · · · · · · · · ·
|
|
134
|
-
```
|
|
135
|
-
|
|
136
|
-
**STOP.** Wait for user response.
|
|
137
|
-
|
|
138
|
-
→ Proceed to **Step 2**.
|
|
139
|
-
|
|
140
|
-
---
|
|
141
|
-
|
|
142
|
-
## Step 2: Detect Phase and Route
|
|
143
|
-
|
|
144
|
-
Load **[detect-phase.md](references/detect-phase.md)** and follow its instructions.
|
|
145
|
-
|
|
146
|
-
→ The reference file will route you to **Step 3**, **Step 4**, **Step 5**, **Step 6**, or a terminal condition. Follow its routing.
|
|
147
|
-
|
|
148
|
-
---
|
|
149
|
-
|
|
150
|
-
## Step 3: Specification Phase
|
|
151
|
-
|
|
152
|
-
Load **[invoke-specification.md](references/invoke-specification.md)** and follow its instructions.
|
|
153
|
-
|
|
154
|
-
**CRITICAL**: When the specification concludes (status becomes "concluded"), you MUST proceed to **Step 7** below. Do not end the session — the feature pipeline continues to the phase bridge.
|
|
155
|
-
|
|
156
|
-
---
|
|
157
|
-
|
|
158
|
-
## Step 4: Planning Phase
|
|
159
|
-
|
|
160
|
-
Load **[invoke-planning.md](references/invoke-planning.md)** and follow its instructions.
|
|
161
|
-
|
|
162
|
-
**CRITICAL**: When the plan concludes (status becomes "concluded"), you MUST proceed to **Step 7** below. Do not end the session — the feature pipeline continues to the phase bridge.
|
|
163
|
-
|
|
164
|
-
---
|
|
165
|
-
|
|
166
|
-
## Step 5: Implementation Phase
|
|
167
|
-
|
|
168
|
-
Load **[invoke-implementation.md](references/invoke-implementation.md)** and follow its instructions.
|
|
169
|
-
|
|
170
|
-
**CRITICAL**: When implementation completes (tracking status becomes "completed"), you MUST proceed to **Step 7** below. Do not end the session — the feature pipeline continues to the phase bridge.
|
|
171
|
-
|
|
172
|
-
---
|
|
173
|
-
|
|
174
|
-
## Step 6: Review Phase
|
|
175
|
-
|
|
176
|
-
Load **[invoke-review.md](references/invoke-review.md)** and follow its instructions.
|
|
177
|
-
|
|
178
|
-
**CRITICAL**: When review concludes, you MUST proceed to **Step 7** below. Do not end the session — the feature pipeline continues to the phase bridge.
|
|
179
|
-
|
|
180
|
-
---
|
|
181
|
-
|
|
182
|
-
## Step 7: Phase Bridge
|
|
183
|
-
|
|
184
|
-
Load **[phase-bridge.md](references/phase-bridge.md)** and follow its instructions.
|
|
185
|
-
|
|
186
|
-
The bridge will enter plan mode with instructions to invoke continue-feature for the topic in the next session, or show a terminal message if the pipeline is complete.
|
|
@@ -1,99 +0,0 @@
|
|
|
1
|
-
# Detect Phase
|
|
2
|
-
|
|
3
|
-
*Reference for **[continue-feature](../SKILL.md)***
|
|
4
|
-
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
Determine the next phase for the selected topic using its artifact state.
|
|
8
|
-
|
|
9
|
-
## Phase Detection
|
|
10
|
-
|
|
11
|
-
Either use the `next_phase` from discovery output (if discovery was run), or compute it by checking artifacts directly:
|
|
12
|
-
|
|
13
|
-
### If discovery was not run (topic provided by caller)
|
|
14
|
-
|
|
15
|
-
Check artifacts in this order (first match wins):
|
|
16
|
-
|
|
17
|
-
1. Check `.workflows/review/{topic}/r*/review.md`
|
|
18
|
-
- If any review exists → next_phase is **"done"**
|
|
19
|
-
|
|
20
|
-
2. Read `.workflows/implementation/{topic}/tracking.md`
|
|
21
|
-
- If exists with `status: completed` → next_phase is **"review"**
|
|
22
|
-
- If exists with `status: in-progress` → next_phase is **"implementation"**
|
|
23
|
-
|
|
24
|
-
3. Read `.workflows/planning/{topic}/plan.md`
|
|
25
|
-
- If exists with `status: concluded` → next_phase is **"implementation"**
|
|
26
|
-
- If exists with other status → next_phase is **"planning"**
|
|
27
|
-
|
|
28
|
-
4. Read `.workflows/specification/{topic}/specification.md`
|
|
29
|
-
- If exists with `status: concluded` → next_phase is **"planning"**
|
|
30
|
-
- If exists with other status → next_phase is **"specification"**
|
|
31
|
-
|
|
32
|
-
5. Check `.workflows/discussion/{topic}.md`
|
|
33
|
-
- If exists with `status: concluded` → next_phase is **"specification"**
|
|
34
|
-
- If exists with other status → next_phase is **"discussion"**
|
|
35
|
-
|
|
36
|
-
6. If none found → next_phase is **"unknown"**
|
|
37
|
-
|
|
38
|
-
## Routing
|
|
39
|
-
|
|
40
|
-
#### If next_phase is "specification"
|
|
41
|
-
|
|
42
|
-
→ Proceed to **Step 3**.
|
|
43
|
-
|
|
44
|
-
#### If next_phase is "planning"
|
|
45
|
-
|
|
46
|
-
→ Proceed to **Step 4**.
|
|
47
|
-
|
|
48
|
-
#### If next_phase is "implementation"
|
|
49
|
-
|
|
50
|
-
→ Proceed to **Step 5**.
|
|
51
|
-
|
|
52
|
-
#### If next_phase is "review"
|
|
53
|
-
|
|
54
|
-
→ Proceed to **Step 6**.
|
|
55
|
-
|
|
56
|
-
#### If next_phase is "done"
|
|
57
|
-
|
|
58
|
-
> *Output the next fenced block as a code block:*
|
|
59
|
-
|
|
60
|
-
```
|
|
61
|
-
Pipeline Complete
|
|
62
|
-
|
|
63
|
-
"{topic:(titlecase)}" has completed all pipeline phases
|
|
64
|
-
(implementation and review).
|
|
65
|
-
|
|
66
|
-
Use /start-review to re-review or synthesize findings.
|
|
67
|
-
```
|
|
68
|
-
|
|
69
|
-
**STOP.** Do not proceed — terminal condition.
|
|
70
|
-
|
|
71
|
-
#### If next_phase is "discussion"
|
|
72
|
-
|
|
73
|
-
> *Output the next fenced block as a code block:*
|
|
74
|
-
|
|
75
|
-
```
|
|
76
|
-
Discussion In Progress
|
|
77
|
-
|
|
78
|
-
"{topic:(titlecase)}" has a discussion that is not yet concluded.
|
|
79
|
-
|
|
80
|
-
Resume the discussion with /start-discussion, or use /start-feature
|
|
81
|
-
to start a new feature from scratch.
|
|
82
|
-
```
|
|
83
|
-
|
|
84
|
-
**STOP.** Do not proceed — terminal condition.
|
|
85
|
-
|
|
86
|
-
#### If next_phase is "unknown"
|
|
87
|
-
|
|
88
|
-
> *Output the next fenced block as a code block:*
|
|
89
|
-
|
|
90
|
-
```
|
|
91
|
-
No Artifacts Found
|
|
92
|
-
|
|
93
|
-
No workflow artifacts found for "{topic}".
|
|
94
|
-
|
|
95
|
-
Start a new feature with /start-feature or begin a discussion
|
|
96
|
-
with /start-discussion.
|
|
97
|
-
```
|
|
98
|
-
|
|
99
|
-
**STOP.** Do not proceed — terminal condition.
|
|
@@ -1,43 +0,0 @@
|
|
|
1
|
-
# Invoke Implementation
|
|
2
|
-
|
|
3
|
-
*Reference for **[continue-feature](../SKILL.md)***
|
|
4
|
-
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
Invoke the begin-implementation bridge skill for this topic.
|
|
8
|
-
|
|
9
|
-
## Save Session State
|
|
10
|
-
|
|
11
|
-
Before invoking the processing skill, save a session bookmark.
|
|
12
|
-
|
|
13
|
-
> *Output the next fenced block as a code block:*
|
|
14
|
-
|
|
15
|
-
```
|
|
16
|
-
Saving session state so Claude can pick up where it left off and continue the feature pipeline if the conversation is compacted.
|
|
17
|
-
```
|
|
18
|
-
|
|
19
|
-
```bash
|
|
20
|
-
.claude/hooks/workflows/write-session-state.sh \
|
|
21
|
-
"{topic}" \
|
|
22
|
-
"skills/technical-implementation/SKILL.md" \
|
|
23
|
-
".workflows/implementation/{topic}/tracking.md" \
|
|
24
|
-
--pipeline "This session is part of the feature pipeline. After implementation completes, return to the continue-feature skill and execute Step 7 (Phase Bridge). Load: skills/continue-feature/references/phase-bridge.md"
|
|
25
|
-
```
|
|
26
|
-
|
|
27
|
-
## Handoff
|
|
28
|
-
|
|
29
|
-
Invoke the [begin-implementation](../../begin-implementation/SKILL.md) skill:
|
|
30
|
-
|
|
31
|
-
```
|
|
32
|
-
Implementation pre-flight for: {topic}
|
|
33
|
-
Plan: .workflows/planning/{topic}/plan.md
|
|
34
|
-
|
|
35
|
-
PIPELINE CONTINUATION — When implementation completes (tracking status: completed),
|
|
36
|
-
you MUST return to the continue-feature skill and execute Step 7 (Phase Bridge).
|
|
37
|
-
Load: skills/continue-feature/references/phase-bridge.md
|
|
38
|
-
Do not end the session after implementation — the feature pipeline continues.
|
|
39
|
-
|
|
40
|
-
Invoke the begin-implementation skill.
|
|
41
|
-
```
|
|
42
|
-
|
|
43
|
-
The bridge skill handles dependency checking, environment setup, and the handoff to technical-implementation.
|