@jakkrichm/create-nexus-devflow 2.0.9 → 2.0.11
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/package.json +1 -1
- package/template/.agents/skills/00-discover/SKILL.md +12 -12
- package/template/.agents/skills/10-define/SKILL.md +15 -15
- package/template/.agents/skills/20-spec/SKILL.md +13 -13
- package/template/.agents/skills/30-plan/SKILL.md +12 -12
- package/template/.agents/skills/40-implement/SKILL.md +13 -13
- package/template/.agents/skills/50-verify/SKILL.md +24 -24
- package/template/.agents/skills/60-report/SKILL.md +10 -9
- package/template/.agents/skills/70-release/SKILL.md +33 -14
- package/template/.agents/skills/adopt/SKILL.md +4 -4
- package/template/.agents/skills/agent/SKILL.md +3 -3
- package/template/.agents/skills/autopilot/SKILL.md +19 -19
- package/template/.agents/skills/brainstorm/SKILL.md +9 -9
- package/template/.agents/skills/brief/SKILL.md +8 -8
- package/template/.agents/skills/changelog/SKILL.md +3 -3
- package/template/.agents/skills/ci/SKILL.md +1 -1
- package/template/.agents/skills/ci-cd-and-automation/SKILL.md +3 -3
- package/template/.agents/skills/codebase-design/SKILL.md +5 -5
- package/template/.agents/skills/commit/SKILL.md +3 -3
- package/template/.agents/skills/competitor-analysis/SKILL.md +2 -2
- package/template/.agents/skills/debug/SKILL.md +10 -10
- package/template/.agents/skills/deploy/SKILL.md +3 -3
- package/template/.agents/skills/devflow/SKILL.md +24 -24
- package/template/.agents/skills/diagnosing-bugs/SKILL.md +3 -3
- package/template/.agents/skills/doctor/SKILL.md +3 -3
- package/template/.agents/skills/followup/SKILL.md +9 -9
- package/template/.agents/skills/goal/SKILL.md +10 -10
- package/template/.agents/skills/help/SKILL.md +17 -17
- package/template/.agents/skills/human-review-decisions/SKILL.md +5 -5
- package/template/.agents/skills/insight/SKILL.md +7 -7
- package/template/.agents/skills/insight-capture/SKILL.md +3 -3
- package/template/.agents/skills/intelligent-routing/SKILL.md +22 -22
- package/template/.agents/skills/issue-triage/SKILL.md +4 -4
- package/template/.agents/skills/merge/SKILL.md +4 -4
- package/template/.agents/skills/onboard/SKILL.md +7 -7
- package/template/.agents/skills/parallel-agents/SKILL.md +1 -1
- package/template/.agents/skills/planning-and-task-breakdown/SKILL.md +1 -1
- package/template/.agents/skills/pr/SKILL.md +7 -7
- package/template/.agents/skills/pr-review/SKILL.md +6 -6
- package/template/.agents/skills/pr-review-analysis/SKILL.md +2 -2
- package/template/.agents/skills/prd/SKILL.md +10 -10
- package/template/.agents/skills/preview/SKILL.md +7 -7
- package/template/.agents/skills/preview-local-check/SKILL.md +5 -5
- package/template/.agents/skills/prototype/SKILL.md +1 -1
- package/template/.agents/skills/release-git-operations/SKILL.md +5 -5
- package/template/.agents/skills/research/SKILL.md +9 -9
- package/template/.agents/skills/review/SKILL.md +3 -3
- package/template/.agents/skills/review-followup-routing/SKILL.md +3 -3
- package/template/.agents/skills/roadmap-strategy/SKILL.md +3 -3
- package/template/.agents/skills/rollback/SKILL.md +5 -5
- package/template/.agents/skills/security-review/SKILL.md +3 -3
- package/template/.agents/skills/shipping-and-launch/SKILL.md +1 -1
- package/template/.agents/skills/simplify/SKILL.md +6 -6
- package/template/.agents/skills/spec-orchestration/SKILL.md +5 -5
- package/template/.agents/skills/specialist-agent-routing/SKILL.md +7 -7
- package/template/.agents/skills/test/SKILL.md +3 -3
- package/template/.agents/skills/test-execution-and-coverage/SKILL.md +4 -4
- package/template/.agents/skills/try/SKILL.md +3 -3
- package/template/.agents/skills/verification-orchestration/SKILL.md +4 -4
- package/template/.agents/skills/wiki/SKILL.md +6 -6
- package/template/.agents/skills/workflow-documentation-sync/SKILL.md +1 -1
- package/template/.claude/skills/00-discover/SKILL.md +12 -12
- package/template/.claude/skills/10-define/SKILL.md +15 -15
- package/template/.claude/skills/20-spec/SKILL.md +13 -13
- package/template/.claude/skills/30-plan/SKILL.md +12 -12
- package/template/.claude/skills/40-implement/SKILL.md +13 -13
- package/template/.claude/skills/50-verify/SKILL.md +24 -24
- package/template/.claude/skills/60-report/SKILL.md +10 -9
- package/template/.claude/skills/70-release/SKILL.md +33 -14
- package/template/.claude/skills/adopt/SKILL.md +4 -4
- package/template/.claude/skills/agent/SKILL.md +3 -3
- package/template/.claude/skills/autopilot/SKILL.md +19 -19
- package/template/.claude/skills/brainstorm/SKILL.md +9 -9
- package/template/.claude/skills/brief/SKILL.md +8 -8
- package/template/.claude/skills/changelog/SKILL.md +3 -3
- package/template/.claude/skills/ci/SKILL.md +1 -1
- package/template/.claude/skills/ci-cd-and-automation/SKILL.md +3 -3
- package/template/.claude/skills/codebase-design/SKILL.md +5 -5
- package/template/.claude/skills/commit/SKILL.md +3 -3
- package/template/.claude/skills/competitor-analysis/SKILL.md +2 -2
- package/template/.claude/skills/debug/SKILL.md +10 -10
- package/template/.claude/skills/deploy/SKILL.md +3 -3
- package/template/.claude/skills/devflow/SKILL.md +24 -24
- package/template/.claude/skills/diagnosing-bugs/SKILL.md +3 -3
- package/template/.claude/skills/doctor/SKILL.md +3 -3
- package/template/.claude/skills/followup/SKILL.md +9 -9
- package/template/.claude/skills/goal/SKILL.md +10 -10
- package/template/.claude/skills/help/SKILL.md +17 -17
- package/template/.claude/skills/human-review-decisions/SKILL.md +5 -5
- package/template/.claude/skills/insight/SKILL.md +7 -7
- package/template/.claude/skills/insight-capture/SKILL.md +3 -3
- package/template/.claude/skills/intelligent-routing/SKILL.md +22 -22
- package/template/.claude/skills/issue-triage/SKILL.md +4 -4
- package/template/.claude/skills/merge/SKILL.md +4 -4
- package/template/.claude/skills/onboard/SKILL.md +7 -7
- package/template/.claude/skills/parallel-agents/SKILL.md +1 -1
- package/template/.claude/skills/planning-and-task-breakdown/SKILL.md +1 -1
- package/template/.claude/skills/pr/SKILL.md +7 -7
- package/template/.claude/skills/pr-review/SKILL.md +6 -6
- package/template/.claude/skills/pr-review-analysis/SKILL.md +2 -2
- package/template/.claude/skills/prd/SKILL.md +10 -10
- package/template/.claude/skills/preview/SKILL.md +7 -7
- package/template/.claude/skills/preview-local-check/SKILL.md +5 -5
- package/template/.claude/skills/prototype/SKILL.md +1 -1
- package/template/.claude/skills/release-git-operations/SKILL.md +5 -5
- package/template/.claude/skills/research/SKILL.md +9 -9
- package/template/.claude/skills/review/SKILL.md +3 -3
- package/template/.claude/skills/review-followup-routing/SKILL.md +3 -3
- package/template/.claude/skills/roadmap-strategy/SKILL.md +3 -3
- package/template/.claude/skills/rollback/SKILL.md +5 -5
- package/template/.claude/skills/security-review/SKILL.md +3 -3
- package/template/.claude/skills/shipping-and-launch/SKILL.md +1 -1
- package/template/.claude/skills/simplify/SKILL.md +6 -6
- package/template/.claude/skills/spec-orchestration/SKILL.md +5 -5
- package/template/.claude/skills/specialist-agent-routing/SKILL.md +7 -7
- package/template/.claude/skills/test/SKILL.md +3 -3
- package/template/.claude/skills/test-execution-and-coverage/SKILL.md +4 -4
- package/template/.claude/skills/try/SKILL.md +3 -3
- package/template/.claude/skills/verification-orchestration/SKILL.md +4 -4
- package/template/.claude/skills/wiki/SKILL.md +6 -6
- package/template/.claude/skills/workflow-documentation-sync/SKILL.md +1 -1
- package/template/AGENTS.md +43 -38
|
@@ -16,7 +16,7 @@ Primary behavior now lives in:
|
|
|
16
16
|
|
|
17
17
|
Treat this workflow file as a compatibility wrapper around that skill in `pr` mode.
|
|
18
18
|
|
|
19
|
-
In DevFlow 2.0, this is a release-adjacent workflow. It usually follows
|
|
19
|
+
In DevFlow 2.0, this is a release-adjacent workflow. It usually follows `60-report` and pairs naturally with `70-release` once the final summary is aligned.
|
|
20
20
|
|
|
21
21
|
---
|
|
22
22
|
|
|
@@ -31,7 +31,7 @@ You are an orchestrator. Your goal is to call the specialized Git PR Maker agent
|
|
|
31
31
|
- Ensure the branch is not `main` or `master`.
|
|
32
32
|
- Check for unpushed commits.
|
|
33
33
|
- Verify the working directory is clean enough for PR submission.
|
|
34
|
-
- Confirm the implementation has already passed the expected verification gate. If it has not, route back to
|
|
34
|
+
- Confirm the implementation has already passed the expected verification gate. If it has not, route back to `50-verify` first.
|
|
35
35
|
|
|
36
36
|
### Phase 2: Context And Template
|
|
37
37
|
|
|
@@ -75,19 +75,19 @@ Verify that the workflow returns:
|
|
|
75
75
|
|
|
76
76
|
- Classification: Companion command
|
|
77
77
|
- Mainline status: Release support command, not a numbered stage
|
|
78
|
-
- Typical entry points:
|
|
79
|
-
- Typical handoff targets: `PR-Review`, `PR-Followup`, `Merge`,
|
|
78
|
+
- Typical entry points: `70-release`, `Commit`
|
|
79
|
+
- Typical handoff targets: `PR-Review`, `PR-Followup`, `Merge`, `70-release`
|
|
80
80
|
|
|
81
81
|
## Sources
|
|
82
82
|
|
|
83
83
|
- `AGENTS.md`
|
|
84
84
|
- `.agents/skills/release-git-operations/SKILL.md`
|
|
85
85
|
- `.agents/skills/git-workflow-and-versioning/SKILL.md`
|
|
86
|
-
- Related commands: `Commit`, `PR-Review`, `PR-Followup`, `Merge`,
|
|
86
|
+
- Related commands: `Commit`, `PR-Review`, `PR-Followup`, `Merge`, `60-report`, `70-release`
|
|
87
87
|
|
|
88
88
|
## Next Workflow Recommendation
|
|
89
89
|
|
|
90
|
-
- **Primary**:
|
|
90
|
+
- **Primary**: `70-release`
|
|
91
91
|
- **Why**: after PR creation, release execution and handoff details should stay consistent with the approved report.
|
|
92
|
-
- **Alternative**: `PR-Review` for structured review before broader sharing, or
|
|
92
|
+
- **Alternative**: `PR-Review` for structured review before broader sharing, or `60-report` when the final communication summary still needs to be refreshed first.
|
|
93
93
|
|
|
@@ -9,7 +9,7 @@ description: "[Devflow] PR Review Addon - Review a pull request using GitHub rev
|
|
|
9
9
|
|
|
10
10
|
Use this workflow when you need a structured PR review without creating or changing the PR. It can review a local diff, a PR URL or number, or a task-linked branch.
|
|
11
11
|
|
|
12
|
-
In DevFlow 2.0, this remains a supporting review workflow. It should feed corrective work back into
|
|
12
|
+
In DevFlow 2.0, this remains a supporting review workflow. It should feed corrective work back into `40-implement` or clear the path toward `60-report` and then `70-release`.
|
|
13
13
|
|
|
14
14
|
Primary behavior now lives in the `pr-review-analysis` skill. Keep this workflow as the compatibility wrapper and user-facing review prompt surface.
|
|
15
15
|
|
|
@@ -123,21 +123,21 @@ devflow/runs/{ID}-*/pr_review.md
|
|
|
123
123
|
|
|
124
124
|
- Classification: Companion command
|
|
125
125
|
- Mainline status: Verification and release support command, not a numbered stage
|
|
126
|
-
- Typical entry points:
|
|
127
|
-
- Typical handoff targets: `PR-Followup`,
|
|
126
|
+
- Typical entry points: `50-verify`, `PR`, `Agent code-reviewer`
|
|
127
|
+
- Typical handoff targets: `PR-Followup`, `60-report`, `70-release`, `Wiki`
|
|
128
128
|
|
|
129
129
|
## Sources
|
|
130
130
|
|
|
131
131
|
- `AGENTS.md`
|
|
132
132
|
- `.agent/resources/schemas/pr_review.template.md`
|
|
133
|
-
- Related commands:
|
|
133
|
+
- Related commands: `50-verify`, `PR`, `PR-Followup`, `Agent`, `60-report`, `70-release`, `Wiki`
|
|
134
134
|
|
|
135
135
|
## Next Workflow Recommendation
|
|
136
136
|
|
|
137
|
-
- **Primary**:
|
|
137
|
+
- **Primary**: `40-implement {ID}` when review finds required fixes, or `60-report {ID}` when the review is clean and the run needs the final summary refreshed before release execution.
|
|
138
138
|
- **Why**: PR review either creates corrective implementation work or clears the path toward final summary alignment and release-facing packaging.
|
|
139
139
|
- **Alternatives**:
|
|
140
|
-
-
|
|
140
|
+
- `70-release` when the report is already aligned and only release execution remains
|
|
141
141
|
- `Wiki` when the review establishes a durable convention or risk pattern
|
|
142
142
|
- `PR-Followup {target}` when the PR already has comments that need classification and response
|
|
143
143
|
|
|
@@ -20,7 +20,7 @@ This skill should reuse and align with:
|
|
|
20
20
|
|
|
21
21
|
## When to Use
|
|
22
22
|
|
|
23
|
-
- after
|
|
23
|
+
- after `50-verify` when the change needs structured review before `60-report` and `70-release`
|
|
24
24
|
- when a local diff, branch, or pull request needs findings-first analysis
|
|
25
25
|
- when the user wants review without directly editing code
|
|
26
26
|
|
|
@@ -86,4 +86,4 @@ Return:
|
|
|
86
86
|
- open questions or assumptions
|
|
87
87
|
- residual risks or test gaps
|
|
88
88
|
- where the review report was saved
|
|
89
|
-
- the recommended next route such as
|
|
89
|
+
- the recommended next route such as `40-implement`, `70-release`, or `PR-Followup`
|
|
@@ -12,9 +12,9 @@ description: Strategic PRD Generator (Orchestration) - Transform a product or fe
|
|
|
12
12
|
|
|
13
13
|
Transform a product or feature idea into a problem-first, hypothesis-driven Product Requirements Document (PRD).
|
|
14
14
|
|
|
15
|
-
In DevFlow 2.0, this is a supporting workflow, not part of the numbered mainline state path. Use it when the idea is still too product-shaped for
|
|
15
|
+
In DevFlow 2.0, this is a supporting workflow, not part of the numbered mainline state path. Use it when the idea is still too product-shaped for `10-define` or `20-spec` to proceed cleanly.
|
|
16
16
|
Use `to-prd` when existing conversation, discovery, or codebase context is already sufficient and the job is synthesis rather than another interview.
|
|
17
|
-
When invoked from
|
|
17
|
+
When invoked from `00-discover`, link the PRD to the Discovery ID and return to `00-discover {discovery_id}` for the final `Proceed`, `Defer`, or `Reject` decision. PRD does not create Running IDs.
|
|
18
18
|
|
|
19
19
|
---
|
|
20
20
|
|
|
@@ -56,7 +56,7 @@ You are an orchestrator. Your goal is to call the specialized PRD Architect agen
|
|
|
56
56
|
- explicit assumptions
|
|
57
57
|
- open questions
|
|
58
58
|
- risks that should remain visible before delivery planning
|
|
59
|
-
- Do not let the PRD silently drift into implementation detail that belongs in
|
|
59
|
+
- Do not let the PRD silently drift into implementation detail that belongs in `20-spec` or `30-plan`.
|
|
60
60
|
|
|
61
61
|
### Phase 4: Output Generation
|
|
62
62
|
|
|
@@ -84,10 +84,10 @@ devflow/prds/{date}-{slug}.prd.md
|
|
|
84
84
|
|
|
85
85
|
Convert the PRD into explicit next steps for the Timeline flow:
|
|
86
86
|
|
|
87
|
-
-
|
|
88
|
-
-
|
|
89
|
-
-
|
|
90
|
-
-
|
|
87
|
+
- `00-discover {discovery_id}` when the PRD belongs to an active discovery
|
|
88
|
+
- `10-define` when product framing was created outside Discover and delivery has already been approved
|
|
89
|
+
- `20-spec` when the delivery contract is ready to be locked
|
|
90
|
+
- `30-plan {ID}` only after the spec is execution-ready
|
|
91
91
|
|
|
92
92
|
The user should still approve the transition into execution work. Do not treat PRD generation as automatic task creation.
|
|
93
93
|
|
|
@@ -110,18 +110,18 @@ Return:
|
|
|
110
110
|
- Classification: Companion command
|
|
111
111
|
- Mainline status: Not a numbered stage
|
|
112
112
|
- Typical entry points: product framing before implementation-ready scope exists
|
|
113
|
-
- Typical handoff targets:
|
|
113
|
+
- Typical handoff targets: `00-discover {discovery_id}`, `10-define`, `20-spec`, `Roadmap`, `Spec-Orchestrate`
|
|
114
114
|
|
|
115
115
|
## Sources
|
|
116
116
|
|
|
117
117
|
- `AGENTS.md`
|
|
118
118
|
- `.agent/resources/schemas/prd.template.md`
|
|
119
|
-
- Related commands: `Brainstorm`, `Research`,
|
|
119
|
+
- Related commands: `Brainstorm`, `Research`, `10-define`, `20-spec`, `Roadmap`, `Spec-Orchestrate`
|
|
120
120
|
- Support skills: `to-prd`, `grill-with-docs`, `domain-modeling`
|
|
121
121
|
|
|
122
122
|
## Next Workflow Recommendation
|
|
123
123
|
|
|
124
|
-
- **Primary**:
|
|
124
|
+
- **Primary**: `00-discover {discovery_id}` when invoked from discovery; otherwise `10-define`
|
|
125
125
|
- **Why**: PRD shapes product intent, while Discover owns the delivery decision and Define owns Running ID creation.
|
|
126
126
|
- **Alternative**: `Research` when technical feasibility or external dependencies are still unresolved.
|
|
127
127
|
|
|
@@ -42,8 +42,8 @@ Use it when:
|
|
|
42
42
|
|
|
43
43
|
Preferred DevFlow 2.0 pairing:
|
|
44
44
|
|
|
45
|
-
- from
|
|
46
|
-
- from
|
|
45
|
+
- from `40-implement`
|
|
46
|
+
- from `50-verify`
|
|
47
47
|
|
|
48
48
|
---
|
|
49
49
|
|
|
@@ -105,17 +105,17 @@ Example summary:
|
|
|
105
105
|
|
|
106
106
|
- Classification: Companion command
|
|
107
107
|
- Mainline status: Not a numbered stage
|
|
108
|
-
- Typical entry points:
|
|
109
|
-
- Typical handoff targets:
|
|
108
|
+
- Typical entry points: `40-implement`, `50-verify`, UI or runtime checking
|
|
109
|
+
- Typical handoff targets: `50-verify`, `Debug`, `40-implement`
|
|
110
110
|
|
|
111
111
|
## Sources
|
|
112
112
|
|
|
113
113
|
- `AGENTS.md`
|
|
114
114
|
- `.agents/skills/preview-local-check/SKILL.md`
|
|
115
|
-
- Related commands:
|
|
115
|
+
- Related commands: `40-implement`, `50-verify`, `Debug`
|
|
116
116
|
|
|
117
117
|
## Next Workflow Recommendation
|
|
118
118
|
|
|
119
|
-
- **Primary**:
|
|
120
|
-
- **Alternative**:
|
|
119
|
+
- **Primary**: `50-verify` when preview confirms the change is ready for formal checks
|
|
120
|
+
- **Alternative**: `40-implement` when preview exposed implementation work
|
|
121
121
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: preview-local-check
|
|
3
|
-
description: "[Devflow] Manage local preview, smoke-check, and temporary runtime verification before formal verification. Use when implementation needs a quick visual or runtime check, when a reviewer needs a local URL, or when a change should be inspected before
|
|
3
|
+
description: "[Devflow] Manage local preview, smoke-check, and temporary runtime verification before formal verification. Use when implementation needs a quick visual or runtime check, when a reviewer needs a local URL, or when a change should be inspected before 50-verify."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# Preview Local Check
|
|
@@ -18,8 +18,8 @@ Use it to:
|
|
|
18
18
|
|
|
19
19
|
## When to Use
|
|
20
20
|
|
|
21
|
-
- During
|
|
22
|
-
- During
|
|
21
|
+
- During `40-implement` when a quick runtime check is useful
|
|
22
|
+
- During `50-verify` when the change needs visual or interactive confirmation
|
|
23
23
|
- When a reviewer asks for a local preview URL
|
|
24
24
|
|
|
25
25
|
Do not use this skill as a replacement for test evidence, verification evidence, or release readiness.
|
|
@@ -50,8 +50,8 @@ Always report:
|
|
|
50
50
|
|
|
51
51
|
### 4. Route Back
|
|
52
52
|
|
|
53
|
-
- return to
|
|
54
|
-
- return to
|
|
53
|
+
- return to `50-verify` when preview confirms the change is ready for formal checks
|
|
54
|
+
- return to `40-implement` when preview reveals implementation issues
|
|
55
55
|
- use `Debug` when the preview failure needs RCA
|
|
56
56
|
|
|
57
57
|
## Output
|
|
@@ -8,7 +8,7 @@ disable-model-invocation: true
|
|
|
8
8
|
|
|
9
9
|
A prototype is throwaway code that answers one question.
|
|
10
10
|
|
|
11
|
-
Use this support skill behind `Research`, `Brainstorm`,
|
|
11
|
+
Use this support skill behind `Research`, `Brainstorm`, `00-discover`, `10-define`, `20-spec`, or `30-plan` when conversation alone cannot settle the uncertainty.
|
|
12
12
|
|
|
13
13
|
## Branches
|
|
14
14
|
|
|
@@ -27,8 +27,8 @@ This skill should reuse and align with:
|
|
|
27
27
|
|
|
28
28
|
## When to Use
|
|
29
29
|
|
|
30
|
-
- After
|
|
31
|
-
- During
|
|
30
|
+
- After `50-verify` when verified work is ready for packaging
|
|
31
|
+
- During `70-release` when the team needs commit, PR, merge, deployment, or changelog support after the report is already aligned
|
|
32
32
|
- When release communication must be built from markdown-first stage artifacts
|
|
33
33
|
|
|
34
34
|
## Supported Modes
|
|
@@ -83,9 +83,9 @@ Read the minimum required artifacts:
|
|
|
83
83
|
|
|
84
84
|
### 3. Route Back
|
|
85
85
|
|
|
86
|
-
- return to
|
|
87
|
-
- return to
|
|
88
|
-
- return to
|
|
86
|
+
- return to `70-release` when packaging is still in progress
|
|
87
|
+
- return to `60-report` when communication is the remaining task
|
|
88
|
+
- return to `40-implement`, `50-verify`, or `PR-Followup` if release blockers are discovered
|
|
89
89
|
|
|
90
90
|
## Output
|
|
91
91
|
|
|
@@ -30,12 +30,12 @@ Use `prototype` when the fastest reliable evidence is a runnable throwaway exper
|
|
|
30
30
|
|
|
31
31
|
Preferred DevFlow 2.0 pairing:
|
|
32
32
|
|
|
33
|
-
- from
|
|
34
|
-
- from
|
|
35
|
-
- from
|
|
36
|
-
- from
|
|
33
|
+
- from `00-discover`
|
|
34
|
+
- from `10-define`
|
|
35
|
+
- from `20-spec`
|
|
36
|
+
- from `50-verify` when validating a claim or implementation choice
|
|
37
37
|
|
|
38
|
-
When invoked with a Discovery ID, link the research report to that discovery and return to
|
|
38
|
+
When invoked with a Discovery ID, link the research report to that discovery and return to `00-discover {discovery_id}` so Discover can synthesize the evidence and make the decision. Research must not allocate a Running ID.
|
|
39
39
|
|
|
40
40
|
---
|
|
41
41
|
|
|
@@ -125,19 +125,19 @@ Research whether this API version is compatible
|
|
|
125
125
|
|
|
126
126
|
- Classification: Companion command
|
|
127
127
|
- Mainline status: Not a numbered stage
|
|
128
|
-
- Typical entry points:
|
|
128
|
+
- Typical entry points: `00-discover`, `10-define`, `20-spec`, `30-plan`
|
|
129
129
|
- Typical handoff targets: return to the stage that asked for the evidence
|
|
130
130
|
|
|
131
131
|
## Sources
|
|
132
132
|
|
|
133
133
|
- `AGENTS.md`
|
|
134
134
|
- `.agent/resources/schemas/research.template.md`
|
|
135
|
-
- Related commands:
|
|
135
|
+
- Related commands: `00-discover`, `10-define`, `20-spec`, `30-plan`, `Spec-Research`, `Agent`
|
|
136
136
|
- Support skills: `prototype`, `spec-research`, `competitor-analysis`, `insight-capture`
|
|
137
137
|
|
|
138
138
|
## Next Workflow Recommendation
|
|
139
139
|
|
|
140
|
-
- Default: return to the stage that asked for evidence; for discovery-owned research this is
|
|
141
|
-
- Common routes:
|
|
140
|
+
- Default: return to the stage that asked for evidence; for discovery-owned research this is `00-discover {discovery_id}`
|
|
141
|
+
- Common routes: `10-define`, `20-spec`, `30-plan`, or `50-verify`
|
|
142
142
|
- Alternate: `Brainstorm` if the research opens multiple strategic options
|
|
143
143
|
|
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: review
|
|
3
|
-
description: "[Devflow] Two-axis review for changed work. Use inside
|
|
3
|
+
description: "[Devflow] Two-axis review for changed work. Use inside 50-verify or 70-release when a branch, PR, or work-in-progress diff needs standards and spec review."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# Review
|
|
7
7
|
|
|
8
|
-
Use this support skill as one verification lane.
|
|
8
|
+
Use this support skill as one verification lane. `50-verify` owns validation evidence; this skill reviews a diff from two separate angles.
|
|
9
9
|
|
|
10
10
|
## Axes
|
|
11
11
|
|
|
@@ -22,7 +22,7 @@ Keep the axes separate so one does not hide the other.
|
|
|
22
22
|
- Confirm the diff is non-empty.
|
|
23
23
|
|
|
24
24
|
2. Identify the spec source.
|
|
25
|
-
- Prefer `devflow/runs/{ID}
|
|
25
|
+
- Prefer `devflow/runs/{ID}-*20-spec.md`, `30-plan.md`, issue brief, PRD, or explicit user path.
|
|
26
26
|
- If no spec exists, mark the Spec axis as skipped.
|
|
27
27
|
|
|
28
28
|
3. Identify standards sources.
|
|
@@ -83,9 +83,9 @@ For task follow-up, append the approved follow-up work directly into the relevan
|
|
|
83
83
|
|
|
84
84
|
### 5. Route Back
|
|
85
85
|
|
|
86
|
-
-
|
|
87
|
-
-
|
|
88
|
-
-
|
|
86
|
+
- `40-implement` for immediate corrective work
|
|
87
|
+
- `50-verify` when only verification needs another pass
|
|
88
|
+
- `10-define` or `20-spec` when the follow-up becomes genuinely new scope
|
|
89
89
|
|
|
90
90
|
## Output
|
|
91
91
|
|
|
@@ -23,7 +23,7 @@ This skill should reuse and align with:
|
|
|
23
23
|
|
|
24
24
|
- when product direction, priority, or sequencing needs a dedicated roadmap pass
|
|
25
25
|
- when competitor, PRD, research, or delivery insight should be consolidated into strategy
|
|
26
|
-
- when roadmap work should stay outside the numbered mainline but still hand off cleanly into `PRD`,
|
|
26
|
+
- when roadmap work should stay outside the numbered mainline but still hand off cleanly into `PRD`, `10-define`, or `20-spec`
|
|
27
27
|
|
|
28
28
|
## Canonical Artifacts
|
|
29
29
|
|
|
@@ -79,8 +79,8 @@ Replace placeholder content fully and keep headings and tables intact so validat
|
|
|
79
79
|
### 5. Route Back
|
|
80
80
|
|
|
81
81
|
- `PRD` when product framing needs to deepen
|
|
82
|
-
-
|
|
83
|
-
-
|
|
82
|
+
- `10-define` when roadmap decisions should become bounded work
|
|
83
|
+
- `20-spec` when one item is ready for delivery contract work
|
|
84
84
|
- `Brainstorm` when strategy is still too fuzzy to lock
|
|
85
85
|
|
|
86
86
|
## Output
|
|
@@ -8,7 +8,7 @@ description: "[Devflow] Plan safe feature or run reversal with dependency and co
|
|
|
8
8
|
Where this sits in the workflow:
|
|
9
9
|
|
|
10
10
|
```text
|
|
11
|
-
completed run + git history -> [rollback] ->
|
|
11
|
+
completed run + git history -> [rollback] -> 40-implement (or fix run) -> 50-verify -> 70-release
|
|
12
12
|
(run archive + commits) (risk review (reverse product diff) (prove) (log & finalize)
|
|
13
13
|
+ plan)
|
|
14
14
|
```
|
|
@@ -20,9 +20,9 @@ This skill **plans a rollback**. It does not silently alter product code, reset
|
|
|
20
20
|
A completed run by Running ID, name, or run path, plus an optional reason. Examples:
|
|
21
21
|
|
|
22
22
|
```text
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
23
|
+
rollback RUN-002-add-onboard-adopt-doctor-skills
|
|
24
|
+
rollback "auth login" because OAuth provider changed
|
|
25
|
+
rollback devflow/runs/RUN-001-align-devflow-blueprint
|
|
26
26
|
```
|
|
27
27
|
|
|
28
28
|
With no target, list recent completed runs from `devflow/runs/` and `devflow/context/current-stage.md` and ask the user to choose. Never silently guess the target. If the reason is missing, ask for one before finalizing the rollback plan.
|
|
@@ -98,7 +98,7 @@ Draft the rollback plan containing:
|
|
|
98
98
|
Present the rollback plan to the user:
|
|
99
99
|
|
|
100
100
|
- Summarize affected files and dependency risks.
|
|
101
|
-
- If approved, route to
|
|
101
|
+
- If approved, route to `40-implement` (or allocate a dedicated Fixrollback Run) to safely execute the reversal steps behind review gates.
|
|
102
102
|
|
|
103
103
|
## Rules
|
|
104
104
|
|
|
@@ -107,8 +107,8 @@ related_files: []
|
|
|
107
107
|
|
|
108
108
|
## 8. Next Allowed Command
|
|
109
109
|
|
|
110
|
-
-
|
|
111
|
-
-
|
|
110
|
+
- `40-implement {running_id}` (if fail, for code remediation)
|
|
111
|
+
- `50-verify {running_id}` (if pass, to verify execution correctness)
|
|
112
112
|
|
|
113
113
|
## 9. Nexus Event
|
|
114
114
|
|
|
@@ -157,7 +157,7 @@ Evaluate high-severity risks including:
|
|
|
157
157
|
|
|
158
158
|
- **Classification**: Companion command
|
|
159
159
|
- **Mainline Status**: Not part of the linear Timeline. Can be run at any stage.
|
|
160
|
-
- **Typical Entry Points**: Any stage, especially before
|
|
160
|
+
- **Typical Entry Points**: Any stage, especially before `50-verify` or `70-release` to verify security health.
|
|
161
161
|
|
|
162
162
|
## Sources
|
|
163
163
|
|
|
@@ -17,7 +17,7 @@ Ship with confidence. The goal is not just to deploy — it's to deploy safely,
|
|
|
17
17
|
- Opening a beta or early access program
|
|
18
18
|
- Any deployment that carries risk (all of them)
|
|
19
19
|
|
|
20
|
-
In DevFlow 2.0, this skill most often supports
|
|
20
|
+
In DevFlow 2.0, this skill most often supports `70-release` and assumes `60-report` is already aligned as the communication baseline.
|
|
21
21
|
|
|
22
22
|
## The Pre-Launch Checklist
|
|
23
23
|
|
|
@@ -21,7 +21,7 @@ Treat this workflow file as a wrapper around that skill.
|
|
|
21
21
|
|
|
22
22
|
Use this workflow when the code works but has grown harder to read, harder to change, or more general than necessary.
|
|
23
23
|
|
|
24
|
-
In DevFlow 2.0, `Simplify` is a supporting implementation workflow. It usually pairs with
|
|
24
|
+
In DevFlow 2.0, `Simplify` is a supporting implementation workflow. It usually pairs with `40-implement` and should end in `50-verify`.
|
|
25
25
|
|
|
26
26
|
## Process
|
|
27
27
|
|
|
@@ -61,19 +61,19 @@ Return:
|
|
|
61
61
|
|
|
62
62
|
- Classification: Companion command
|
|
63
63
|
- Mainline status: Not a numbered stage
|
|
64
|
-
- Typical entry points:
|
|
65
|
-
- Typical handoff targets:
|
|
64
|
+
- Typical entry points: `40-implement`, `50-verify`, `PR-Review`, `Agent`
|
|
65
|
+
- Typical handoff targets: `40-implement`, `50-verify`, `PR-Review`
|
|
66
66
|
|
|
67
67
|
## Sources
|
|
68
68
|
|
|
69
69
|
- `AGENTS.md`
|
|
70
70
|
- `.agents/skills/code-simplification/SKILL.md`
|
|
71
71
|
- `.agent/resources/schemas/refactoring.template.md`
|
|
72
|
-
- Related commands:
|
|
72
|
+
- Related commands: `40-implement`, `50-verify`, `PR-Review`, `Agent`
|
|
73
73
|
|
|
74
74
|
## Next Workflow Recommendation
|
|
75
75
|
|
|
76
|
-
- **Primary**:
|
|
76
|
+
- **Primary**: `50-verify`
|
|
77
77
|
- **Why**: simplification should finish with explicit proof that behavior did not regress
|
|
78
|
-
- **Alternative**:
|
|
78
|
+
- **Alternative**: `40-implement` when simplification exposed a deeper implementation change rather than a pure refactor
|
|
79
79
|
|
|
@@ -48,8 +48,8 @@ Route proportionally:
|
|
|
48
48
|
- `Research` or `Spec-Research` for external or technical proof
|
|
49
49
|
- `Competitor` for market context
|
|
50
50
|
- `PRD` for product framing
|
|
51
|
-
-
|
|
52
|
-
-
|
|
51
|
+
- `10-define` for scope and decision locking
|
|
52
|
+
- `20-spec` for delivery contract writing
|
|
53
53
|
|
|
54
54
|
Do not stack every support surface by default.
|
|
55
55
|
|
|
@@ -76,9 +76,9 @@ Use `.agent/resources/schemas/spec_orchestration.template.md` and replace placeh
|
|
|
76
76
|
|
|
77
77
|
### 5. Route Back To Mainline
|
|
78
78
|
|
|
79
|
-
-
|
|
80
|
-
-
|
|
81
|
-
-
|
|
79
|
+
- `10-define` when the idea still needs scope decisions
|
|
80
|
+
- `20-spec` when enough evidence exists to write the delivery contract
|
|
81
|
+
- `30-plan` only when the spec is already solid
|
|
82
82
|
|
|
83
83
|
## Output
|
|
84
84
|
|
|
@@ -76,13 +76,13 @@ Use `.agent/resources/schemas/agent_report.template.md` unless the invoking work
|
|
|
76
76
|
|
|
77
77
|
Return to the owning step:
|
|
78
78
|
|
|
79
|
-
-
|
|
80
|
-
-
|
|
81
|
-
-
|
|
82
|
-
-
|
|
83
|
-
-
|
|
84
|
-
-
|
|
85
|
-
-
|
|
79
|
+
- `10-define`
|
|
80
|
+
- `20-spec`
|
|
81
|
+
- `30-plan`
|
|
82
|
+
- `40-implement`
|
|
83
|
+
- `50-verify`
|
|
84
|
+
- `70-release`
|
|
85
|
+
- `60-report`
|
|
86
86
|
- `PR-Review`
|
|
87
87
|
- `Research`
|
|
88
88
|
|
|
@@ -69,14 +69,14 @@ Display an organized output listing Passed/Failed files, and explicitly show the
|
|
|
69
69
|
|
|
70
70
|
- Classification: Companion command
|
|
71
71
|
- Mainline status: Verification support command, not a numbered stage
|
|
72
|
-
- Typical entry points:
|
|
73
|
-
- Typical handoff targets:
|
|
72
|
+
- Typical entry points: `40-implement`, `50-verify`, `Debug`
|
|
73
|
+
- Typical handoff targets: `50-verify`, `Debug`, `QA-Orchestrate`
|
|
74
74
|
|
|
75
75
|
## Sources
|
|
76
76
|
|
|
77
77
|
- `AGENTS.md`
|
|
78
78
|
- `.agents/skills/test-execution-and-coverage/SKILL.md`
|
|
79
79
|
- `.agent/resources/schemas/test_report.template.md`
|
|
80
|
-
- Related commands:
|
|
80
|
+
- Related commands: `40-implement`, `50-verify`, `Debug`, `QA-Orchestrate`
|
|
81
81
|
|
|
82
82
|
|
|
@@ -11,8 +11,8 @@ This skill complements TDD by handling test generation, execution, and persisten
|
|
|
11
11
|
|
|
12
12
|
## When to Use
|
|
13
13
|
|
|
14
|
-
- During
|
|
15
|
-
- During
|
|
14
|
+
- During `40-implement` when tests need to be added
|
|
15
|
+
- During `50-verify` when the test suite must be run and summarized
|
|
16
16
|
- During `Debug` when a bug needs a reproduction test
|
|
17
17
|
|
|
18
18
|
## Process
|
|
@@ -41,8 +41,8 @@ Use `.agent/resources/schemas/test_report.template.md` when saving a reusable re
|
|
|
41
41
|
|
|
42
42
|
### 4. Route Back
|
|
43
43
|
|
|
44
|
-
-
|
|
45
|
-
-
|
|
44
|
+
- `50-verify` when tests support formal verification
|
|
45
|
+
- `40-implement` when missing or failing tests require code changes
|
|
46
46
|
- `Debug` when failures need RCA
|
|
47
47
|
|
|
48
48
|
## Output
|
|
@@ -8,12 +8,12 @@ description: "[Devflow] Generate human manual QA review walkthrough guide (where
|
|
|
8
8
|
Where this sits in the workflow:
|
|
9
9
|
|
|
10
10
|
```text
|
|
11
|
-
|
|
11
|
+
40-implement or 50-verify or 60-report -> [try] -> human review & verification
|
|
12
12
|
(work implemented / verified) (manual (where to go,
|
|
13
13
|
steps) what to click)
|
|
14
14
|
```
|
|
15
15
|
|
|
16
|
-
|
|
16
|
+
`50-verify` proves behavior from automated QA and test runs. `try` gives the user and testers an actionable, step-by-step manual walkthrough: start this command, open this route, click these controls, expect this result, and watch for these failure signs.
|
|
17
17
|
|
|
18
18
|
It is always **read-only 100%**. It does not edit files, install dependencies, commit, merge, push, or run destructive commands.
|
|
19
19
|
|
|
@@ -23,7 +23,7 @@ Optional scope:
|
|
|
23
23
|
|
|
24
24
|
- **no argument**: use the active run in `devflow/context/current-stage.md` (or the latest completed run under `devflow/runs/`)
|
|
25
25
|
- `latest`: use the most recent completed run in `devflow/runs/`
|
|
26
|
-
- a run ID or path: e.g.
|
|
26
|
+
- a run ID or path: e.g. `try RUN-002-add-onboard-adopt-doctor-skills`
|
|
27
27
|
- a specific route, endpoint, or CLI command: focus the walkthrough on that surface
|
|
28
28
|
|
|
29
29
|
If there is no active run and no run history, ask what change or feature the user wants to test manually.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: verification-orchestration
|
|
3
|
-
description: "[Devflow] Coordinate multi-lane QA, specialist review, test planning, and verification follow-up. Use when
|
|
3
|
+
description: "[Devflow] Coordinate multi-lane QA, specialist review, test planning, and verification follow-up. Use when 50-verify needs more structure than a single pass and the team needs a QA matrix or specialist routing."
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# Verification Orchestration
|
|
@@ -11,7 +11,7 @@ This skill structures complex verification work across multiple QA lanes without
|
|
|
11
11
|
|
|
12
12
|
## When to Use
|
|
13
13
|
|
|
14
|
-
-
|
|
14
|
+
- `50-verify` is too broad for a single simple pass
|
|
15
15
|
- the change needs correctness, regression, security, performance, and UX checks together
|
|
16
16
|
- the team needs specialist routing for QA
|
|
17
17
|
|
|
@@ -54,8 +54,8 @@ Use `.agent/resources/schemas/qa_orchestration.template.md` when saving a reusab
|
|
|
54
54
|
|
|
55
55
|
### 5. Route Back
|
|
56
56
|
|
|
57
|
-
-
|
|
58
|
-
-
|
|
57
|
+
- `50-verify` when the QA matrix strengthens verification evidence
|
|
58
|
+
- `40-implement` when actionable fixes are required
|
|
59
59
|
- `Followup` when findings become new scope
|
|
60
60
|
|
|
61
61
|
## Output
|
|
@@ -31,9 +31,9 @@ Use `Wiki` when:
|
|
|
31
31
|
|
|
32
32
|
Preferred DevFlow 2.0 pairing:
|
|
33
33
|
|
|
34
|
-
- after
|
|
35
|
-
- after
|
|
36
|
-
- after
|
|
34
|
+
- after `50-verify`
|
|
35
|
+
- after `70-release`
|
|
36
|
+
- after `60-report`
|
|
37
37
|
- after meaningful `Debug` or review output
|
|
38
38
|
|
|
39
39
|
## Process
|
|
@@ -131,7 +131,7 @@ Return:
|
|
|
131
131
|
|
|
132
132
|
- Classification: Companion command
|
|
133
133
|
- Mainline status: Knowledge system command, not a numbered stage
|
|
134
|
-
- Typical entry points: after
|
|
134
|
+
- Typical entry points: after `50-verify`, `60-report`, `70-release`, `Debug`, `Insight`, `PR-Review`
|
|
135
135
|
- Typical handoff targets: return to the originating stage or finish as documentation-only work
|
|
136
136
|
|
|
137
137
|
## Sources
|
|
@@ -139,11 +139,11 @@ Return:
|
|
|
139
139
|
- `AGENTS.md`
|
|
140
140
|
- `.agent/resources/schemas/wiki_page.template.md`
|
|
141
141
|
- `.agent/resources/schemas/wiki_project_index.template.md`
|
|
142
|
-
- Related commands:
|
|
142
|
+
- Related commands: `50-verify`, `60-report`, `70-release`, `Debug`, `Insight`, `PR-Review`, `Help`
|
|
143
143
|
|
|
144
144
|
## Next Workflow Recommendation
|
|
145
145
|
|
|
146
146
|
- **Primary**: return to the stage or artifact flow that produced the reusable knowledge
|
|
147
147
|
- **Why**: `Wiki` compiles lessons after the source work is already validated
|
|
148
|
-
- **Common routes**:
|
|
148
|
+
- **Common routes**: `60-report`, `70-release`, or `50-verify`
|
|
149
149
|
|