maestro-flow-one 0.2.30 → 0.2.32
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/maestro-flow/commands/learn/follow.md +1 -1
- package/maestro-flow/commands/learn/investigate.md +2 -2
- package/maestro-flow/commands/learn/second-opinion.md +1 -1
- package/maestro-flow/commands/lifecycle/analyze.md +53 -2
- package/maestro-flow/commands/lifecycle/blueprint.md +36 -1
- package/maestro-flow/commands/lifecycle/brainstorm.md +40 -1
- package/maestro-flow/commands/lifecycle/collab.md +1 -1
- package/maestro-flow/commands/lifecycle/companion.md +4 -4
- package/maestro-flow/commands/lifecycle/composer.md +1 -1
- package/maestro-flow/commands/lifecycle/execute.md +29 -6
- package/maestro-flow/commands/lifecycle/fork.md +24 -0
- package/maestro-flow/commands/lifecycle/grill.md +38 -1
- package/maestro-flow/commands/lifecycle/impeccable.md +13 -0
- package/maestro-flow/commands/lifecycle/init.md +11 -0
- package/maestro-flow/commands/lifecycle/merge.md +17 -1
- package/maestro-flow/commands/lifecycle/next.md +8 -9
- package/maestro-flow/commands/lifecycle/overlay.md +3 -3
- package/maestro-flow/commands/lifecycle/plan.md +21 -3
- package/maestro-flow/commands/lifecycle/quick.md +13 -1
- package/maestro-flow/commands/lifecycle/roadmap.md +28 -2
- package/maestro-flow/commands/lifecycle/swarm-workflow.md +2 -2
- package/maestro-flow/commands/lifecycle/tools-register.md +2 -2
- package/maestro-flow/commands/lifecycle/ui-codify.md +20 -0
- package/maestro-flow/commands/lifecycle/update.md +59 -116
- package/maestro-flow/commands/manage/codebase-rebuild.md +3 -3
- package/maestro-flow/commands/manage/harvest.md +1 -1
- package/maestro-flow/commands/manage/knowhow-capture.md +7 -4
- package/maestro-flow/commands/manage/knowhow.md +3 -1
- package/maestro-flow/commands/manage/wiki.md +17 -8
- package/maestro-flow/commands/milestone/audit.md +34 -2
- package/maestro-flow/commands/milestone/complete.md +19 -1
- package/maestro-flow/commands/milestone/release.md +18 -0
- package/maestro-flow/commands/quality/auto-test.md +3 -3
- package/maestro-flow/commands/quality/debug.md +4 -4
- package/maestro-flow/commands/quality/refactor.md +2 -2
- package/maestro-flow/commands/quality/retrospective.md +5 -5
- package/maestro-flow/commands/quality/review.md +4 -4
- package/maestro-flow/commands/quality/sync.md +1 -0
- package/maestro-flow/commands/quality/test.md +4 -4
- package/maestro-flow/commands/spec/add.md +6 -4
- package/maestro-flow/commands/spec/setup.md +1 -1
- package/package.json +1 -1
- package/maestro-flow/commands/learn/retro.md +0 -157
- package/maestro-flow/commands/lifecycle/learn.md +0 -140
- package/maestro-flow/commands/lifecycle/verify.md +0 -144
- package/maestro-flow/commands/manage/codebase-refresh.md +0 -60
- package/maestro-flow/commands/manage/learn.md +0 -65
- package/maestro-flow/commands/wiki/connect.md +0 -62
- package/maestro-flow/commands/wiki/digest.md +0 -68
|
@@ -1,144 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: maestro-verify
|
|
3
|
-
description: Use after execution to verify goals are actually achieved with evidence-based structural checks
|
|
4
|
-
argument-hint: "[phase] [--skip-tests] [--skip-antipattern] [--dir <path>]"
|
|
5
|
-
allowed-tools:
|
|
6
|
-
- Read
|
|
7
|
-
- Write
|
|
8
|
-
- Edit
|
|
9
|
-
- Bash
|
|
10
|
-
- Glob
|
|
11
|
-
- Grep
|
|
12
|
-
- Agent
|
|
13
|
-
- AskUserQuestion
|
|
14
|
-
---
|
|
15
|
-
<purpose>
|
|
16
|
-
Verify execution results through three complementary methods:
|
|
17
|
-
1. **Goal-Backward verification** — 3-layer check (Truths → Artifacts → Wiring) that validates goals are actually achieved
|
|
18
|
-
2. **Anti-pattern scan** — detect stubs, placeholders, TODO/FIXME, empty returns in modified files
|
|
19
|
-
3. **Nyquist test coverage validation** — requirement-to-test mapping with gap classification
|
|
20
|
-
|
|
21
|
-
Supports dual-level verification:
|
|
22
|
-
- **Single plan**: `verify --dir scratch/{YYYYMMDD}-plan-xxx` — verifies one plan, writes `verification.json` into plan dir
|
|
23
|
-
- **Milestone**: `verify` (no args) — aggregates all execute artifacts for current milestone into `scratch/{YYYYMMDD}-verify-M{N}-{slug}/milestone-verification.json`
|
|
24
|
-
|
|
25
|
-
Registers VRF artifact in state.json on completion.
|
|
26
|
-
</purpose>
|
|
27
|
-
|
|
28
|
-
<required_reading>
|
|
29
|
-
@~/.maestro/workflows/verify.md
|
|
30
|
-
</required_reading>
|
|
31
|
-
|
|
32
|
-
<deferred_reading>
|
|
33
|
-
- [verification.json](~/.maestro/templates/verification.json) — read when generating output
|
|
34
|
-
- [validation.json](~/.maestro/templates/validation.json) — read when generating test output
|
|
35
|
-
</deferred_reading>
|
|
36
|
-
|
|
37
|
-
<context>
|
|
38
|
-
$ARGUMENTS — phase number or no args for milestone-wide, with optional flags.
|
|
39
|
-
|
|
40
|
-
### Flags
|
|
41
|
-
|
|
42
|
-
| Flag | Effect | Default |
|
|
43
|
-
|------|--------|---------|
|
|
44
|
-
| `--skip-tests` | Skip Nyquist test coverage validation (V2), only run Goal-Backward verification | false |
|
|
45
|
-
| `--skip-antipattern` | Skip anti-pattern scan step | false |
|
|
46
|
-
| `--dir <path>` | Verify a single plan directory instead of milestone-wide | — (milestone mode) |
|
|
47
|
-
|
|
48
|
-
**Scope routing:**
|
|
49
|
-
| Input | Scope | Resolution |
|
|
50
|
-
|-------|-------|------------|
|
|
51
|
-
| `--dir scratch/{dir}` | single plan | Verify one plan, write verification.json into plan dir |
|
|
52
|
-
| numeric arg | phase | Verify all execute artifacts for that phase |
|
|
53
|
-
| no args | milestone | Aggregate all execute artifacts for current milestone |
|
|
54
|
-
|
|
55
|
-
Output paths and VRF artifact registration schema are defined in workflow `verify.md`.
|
|
56
|
-
|
|
57
|
-
### Pre-load context (before verification)
|
|
58
|
-
|
|
59
|
-
1. **Codebase docs**: If `.workflow/codebase/` exists, read `ARCHITECTURE.md` for expected module wiring and `FEATURES.md` for component mapping. Use in Layer 3 (Connection) checks.
|
|
60
|
-
2. **Review specs**: Run `maestro spec load --category review` to load review standards. Use as quality baseline for anti-pattern scan and constraint checks.
|
|
61
|
-
3. **Wiki constraints**: Run `maestro wiki search "architecture constraint" --json 2>/dev/null`. If results found, include documented invariants as additional truth checks in Layer 1.
|
|
62
|
-
4. **Role Knowledge**:
|
|
63
|
-
- Browse: `maestro wiki list --category review`
|
|
64
|
-
- Load task-relevant entries: `maestro wiki load <id1> [id2...]`
|
|
65
|
-
5. All are optional — proceed without if unavailable.
|
|
66
|
-
</context>
|
|
67
|
-
|
|
68
|
-
<execution>
|
|
69
|
-
Follow '~/.maestro/workflows/verify.md' completely.
|
|
70
|
-
|
|
71
|
-
### Post-verify Knowledge Inquiry
|
|
72
|
-
|
|
73
|
-
| Condition | Ask | Route |
|
|
74
|
-
|-----------|-----|-------|
|
|
75
|
-
| Anti-pattern blockers found (TODO/FIXME/stubs) | "Update quality-rules.md?" | spec-add quality |
|
|
76
|
-
| Architecture constraint violations | "Update architecture-constraints.md?" | spec-add arch |
|
|
77
|
-
| Recurring test coverage gap (same module across tasks) | "Add to test-conventions.md?" | spec-add test |
|
|
78
|
-
|
|
79
|
-
On confirm → `Skill("spec-add", "<category> <content>")`.
|
|
80
|
-
|
|
81
|
-
</execution>
|
|
82
|
-
|
|
83
|
-
<completion>
|
|
84
|
-
### Standalone report
|
|
85
|
-
|
|
86
|
-
```
|
|
87
|
-
=== VERIFY COMPLETE ===
|
|
88
|
-
STATUS: DONE|DONE_WITH_CONCERNS|NEEDS_RETRY
|
|
89
|
-
CONCERNS: {description if applicable}
|
|
90
|
-
NEXT: /quality-review
|
|
91
|
-
=== END VERIFY ===
|
|
92
|
-
```
|
|
93
|
-
|
|
94
|
-
Status mapping:
|
|
95
|
-
- **DONE** — All checks pass, no gaps → NEXT: /quality-review
|
|
96
|
-
- **DONE_WITH_CONCERNS** — Gaps found (must-have failures or anti-pattern blockers) → NEXT: /maestro-execute (after /maestro-plan --gaps)
|
|
97
|
-
- **NEEDS_RETRY** — Verification could not complete (missing artifacts, corrupt data)
|
|
98
|
-
|
|
99
|
-
### Ralph-invoked completion
|
|
100
|
-
|
|
101
|
-
End the step by calling the CLI (no text block output):
|
|
102
|
-
```
|
|
103
|
-
maestro ralph complete <idx> --status {STATUS} [--evidence {path}]
|
|
104
|
-
```
|
|
105
|
-
|
|
106
|
-
Status verdicts:
|
|
107
|
-
- **DONE** — Normal completion
|
|
108
|
-
- **DONE_WITH_CONCERNS** — Completed with caveats; pass `--concerns`
|
|
109
|
-
- **NEEDS_RETRY** — Tooling error / transient issue; ralph will retry
|
|
110
|
-
- **BLOCKED** — External hard blocker; pass `--reason`
|
|
111
|
-
|
|
112
|
-
### Next-step routing
|
|
113
|
-
|
|
114
|
-
| Condition | Suggestion |
|
|
115
|
-
|-----------|-----------|
|
|
116
|
-
| All checks pass, no gaps | `/quality-review` |
|
|
117
|
-
| Gaps found (must-have failures or anti-pattern blockers) | `/maestro-plan --gaps` |
|
|
118
|
-
| Low test coverage (Nyquist gaps) | `/quality-auto-test` |
|
|
119
|
-
|
|
120
|
-
**Gap-fix closure loop:**
|
|
121
|
-
Gaps found → maestro-plan --gaps → maestro-execute → maestro-verify (re-run)
|
|
122
|
-
</completion>
|
|
123
|
-
|
|
124
|
-
<error_codes>
|
|
125
|
-
| Code | Severity | Condition | Recovery |
|
|
126
|
-
|------|----------|-----------|----------|
|
|
127
|
-
| E001 | error | No executed plans found for verification | Run maestro-execute first |
|
|
128
|
-
| E002 | error | Plan directory not found | Check --dir path |
|
|
129
|
-
| E003 | error | No execution results found (missing summaries) | Run maestro-execute first |
|
|
130
|
-
| W001 | warning | Test coverage below configured threshold | Review coverage gaps |
|
|
131
|
-
| W002 | warning | Anti-pattern blockers found in modified files | Fix blockers before proceeding |
|
|
132
|
-
</error_codes>
|
|
133
|
-
|
|
134
|
-
<success_criteria>
|
|
135
|
-
- [ ] Must-haves established (from convergence.criteria in tasks)
|
|
136
|
-
- [ ] All truths verified with status and evidence (Layer 1)
|
|
137
|
-
- [ ] All artifacts checked at L1 (exists), L2 (substantive), L3 (wired) (Layer 2)
|
|
138
|
-
- [ ] All key links verified with evidence (Layer 3)
|
|
139
|
-
- [ ] Anti-patterns scanned and categorized (unless skipped)
|
|
140
|
-
- [ ] Nyquist test coverage assessed (unless skipped)
|
|
141
|
-
- [ ] Fix plans generated for identified gaps
|
|
142
|
-
- [ ] verification.json written to plan dir (single plan) or milestone verify dir
|
|
143
|
-
- [ ] VRF artifact registered in state.json
|
|
144
|
-
</success_criteria>
|
|
@@ -1,60 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: manage-codebase-refresh
|
|
3
|
-
description: Refresh codebase docs from recent changes
|
|
4
|
-
argument-hint: "[--since <date>] [--deep]"
|
|
5
|
-
allowed-tools:
|
|
6
|
-
- Read
|
|
7
|
-
- Write
|
|
8
|
-
- Edit
|
|
9
|
-
- Bash
|
|
10
|
-
- Glob
|
|
11
|
-
- Grep
|
|
12
|
-
- Agent
|
|
13
|
-
- AskUserQuestion
|
|
14
|
-
---
|
|
15
|
-
|
|
16
|
-
<purpose>
|
|
17
|
-
Incrementally refresh .workflow/codebase/ documentation based on changes since the last rebuild or refresh. Detects which files have changed (via git diff), identifies which codebase docs are affected, selectively re-runs mapper agents on those areas only, and updates timestamps. Much faster than a full rebuild for ongoing maintenance.
|
|
18
|
-
</purpose>
|
|
19
|
-
|
|
20
|
-
<required_reading>
|
|
21
|
-
@~/.maestro/workflows/codebase-refresh.md
|
|
22
|
-
</required_reading>
|
|
23
|
-
|
|
24
|
-
<context>
|
|
25
|
-
$ARGUMENTS -- optional flags.
|
|
26
|
-
|
|
27
|
-
**Flags:**
|
|
28
|
-
- `--since <date>` -- Override change detection window (ISO date or relative like "3d")
|
|
29
|
-
- `--deep` -- Force deeper re-scan even for files with minor changes
|
|
30
|
-
|
|
31
|
-
**State files:**
|
|
32
|
-
- `.workflow/` -- must be initialized
|
|
33
|
-
- `.workflow/codebase/` -- must contain existing docs (from prior rebuild)
|
|
34
|
-
- `.workflow/codebase/doc-index.json` -- documentation index with timestamps
|
|
35
|
-
- `.workflow/codebase/knowledge-graph.json` -- Knowledge Graph (optional, for KG impact analysis)
|
|
36
|
-
- `.workflow/state.json` -- contains `codebase_last_rebuilt` timestamp
|
|
37
|
-
</context>
|
|
38
|
-
|
|
39
|
-
<execution>
|
|
40
|
-
Follow '~/.maestro/workflows/codebase-refresh.md' completely.
|
|
41
|
-
</execution>
|
|
42
|
-
|
|
43
|
-
<error_codes>
|
|
44
|
-
| Code | Meaning |
|
|
45
|
-
|------|----------------------------------------------------------|
|
|
46
|
-
| E001 | .workflow/ not initialized |
|
|
47
|
-
| E002 | No codebase/ docs exist, use codebase-rebuild instead |
|
|
48
|
-
| W001 | No changes detected since last refresh |
|
|
49
|
-
</error_codes>
|
|
50
|
-
|
|
51
|
-
<success_criteria>
|
|
52
|
-
- [ ] Changed files detected via git diff since last refresh
|
|
53
|
-
- [ ] Affected documentation entries identified from doc-index.json
|
|
54
|
-
- [ ] KG impact analysis run (if knowledge-graph.json exists): `maestro kg diff-wiki --json`
|
|
55
|
-
- [ ] Affected wiki entries flagged with warnings (if any)
|
|
56
|
-
- [ ] Only affected docs refreshed (selective mapper re-run)
|
|
57
|
-
- [ ] doc-index.json timestamps updated per affected entry
|
|
58
|
-
- [ ] state.json updated with codebase_last_refreshed timestamp
|
|
59
|
-
- [ ] Next step routing: `/manage-status` or `/spec-load` to use updated docs
|
|
60
|
-
</success_criteria>
|
|
@@ -1,65 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: manage-learn
|
|
3
|
-
description: Capture and search learning insights and tips
|
|
4
|
-
argument-hint: "[<text> | tip <text> | list | search | show <id>] [--category <cat>] [--tag t1,t2] [--phase N]"
|
|
5
|
-
allowed-tools:
|
|
6
|
-
- Read
|
|
7
|
-
- Write
|
|
8
|
-
- Edit
|
|
9
|
-
- Bash
|
|
10
|
-
- Glob
|
|
11
|
-
- Grep
|
|
12
|
-
- AskUserQuestion
|
|
13
|
-
---
|
|
14
|
-
<purpose>
|
|
15
|
-
Unified atomic knowledge capture for the workflow learning library. Captures two types of knowledge:
|
|
16
|
-
- **Insights**: Timeless "eureka moment" entries (patterns, gotchas, techniques) — the default mode
|
|
17
|
-
- **Tips**: Quick contextual notes for cross-session recovery (formerly in `manage-knowhow-capture tip`)
|
|
18
|
-
|
|
19
|
-
Both types are stored in `.workflow/specs/learnings.md` as `<spec-entry>` blocks with auto-detected phase linkage and keyword-based category inference. Tips are distinguished by `source: "tip"` and implicitly tagged `tip`. Same store as retrospective output, so search and list see the entire knowledge corpus.
|
|
20
|
-
</purpose>
|
|
21
|
-
|
|
22
|
-
<required_reading>
|
|
23
|
-
@~/.maestro/workflows/learn.md
|
|
24
|
-
</required_reading>
|
|
25
|
-
|
|
26
|
-
<context>
|
|
27
|
-
Arguments: $ARGUMENTS
|
|
28
|
-
|
|
29
|
-
**Modes (auto-detected from first token):**
|
|
30
|
-
- `"<insight text>"` (or any non-keyword text) → insight capture mode
|
|
31
|
-
- `tip <text>` → tip capture mode (quick contextual note, auto-tagged `tip`)
|
|
32
|
-
- `list` → list recent entries (default 20)
|
|
33
|
-
- `search <query>` → `maestro spec load --category learning` or text search across `.workflow/specs/learnings.md`
|
|
34
|
-
- `show <INS-id>` → full detail with phase context
|
|
35
|
-
- empty → AskUserQuestion to prompt for text
|
|
36
|
-
|
|
37
|
-
Flags, storage paths, and shared store rationale defined in workflow learn.md.
|
|
38
|
-
</context>
|
|
39
|
-
|
|
40
|
-
<execution>
|
|
41
|
-
Follow `~/.maestro/workflows/learn.md` Stages 1–5 in order.
|
|
42
|
-
</execution>
|
|
43
|
-
|
|
44
|
-
<error_codes>
|
|
45
|
-
| Code | Severity | Description | Stage |
|
|
46
|
-
|------|----------|-------------|-------|
|
|
47
|
-
| E001 | error | `.workflow/` not initialized — run `/maestro-init` first | parse_input |
|
|
48
|
-
| E002 | error | Unknown `--category` value (allowed: pattern, antipattern, decision, tool, gotcha, technique, tip) | parse_input |
|
|
49
|
-
| E003 | error | `show` mode requires an INS-id argument | show |
|
|
50
|
-
| E004 | error | Insight id not found in `.workflow/specs/learnings.md` | show |
|
|
51
|
-
| W001 | warning | Auto-phase detection found a current_phase but no matching artifact in registry; phase set to null | capture |
|
|
52
|
-
</error_codes>
|
|
53
|
-
|
|
54
|
-
<success_criteria>
|
|
55
|
-
- [ ] Mode correctly routed (capture / list / search / show)
|
|
56
|
-
- [ ] Capture: `<spec-entry>` block appended to `.workflow/specs/learnings.md` with all required fields
|
|
57
|
-
- [ ] Capture: phase auto-link resolves correctly via artifact registry when `state.json` has `current_phase`
|
|
58
|
-
- [ ] Capture: category inference produces a sensible default when `--category` absent
|
|
59
|
-
- [ ] List: filters apply, output sorted newest-first, default limit 20
|
|
60
|
-
- [ ] Search: results ranked by title (3) > tags (2) > summary (1) match
|
|
61
|
-
- [ ] Show: full insight displayed with phase context and routed-artifact link if any
|
|
62
|
-
- [ ] No file modifications outside `.workflow/specs/learnings.md` and `.workflow/knowhow/`
|
|
63
|
-
- [ ] Confirmation banner displayed with INS-id and next-step hints
|
|
64
|
-
- [ ] Next step: `/manage-learn list` to browse, or `/manage-learn search <query>` to find related insights
|
|
65
|
-
</success_criteria>
|
|
@@ -1,62 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: wiki-connect
|
|
3
|
-
description: Find and link hidden connections in wiki graph
|
|
4
|
-
argument-hint: "[--scope <type>] [--min-similarity N] [--fix] [--max N]"
|
|
5
|
-
allowed-tools:
|
|
6
|
-
- Read
|
|
7
|
-
- Write
|
|
8
|
-
- Bash
|
|
9
|
-
- Glob
|
|
10
|
-
- Grep
|
|
11
|
-
- Agent
|
|
12
|
-
- AskUserQuestion
|
|
13
|
-
---
|
|
14
|
-
<required_reading>
|
|
15
|
-
@~/.maestro/workflows/wiki-connect.md
|
|
16
|
-
</required_reading>
|
|
17
|
-
|
|
18
|
-
<purpose>
|
|
19
|
-
Knowledge graph link discovery and health improvement. Analyzes the wiki index to find orphaned entries, missing connections, and transitive link gaps, then suggests or auto-applies new `related` links to improve graph connectivity.
|
|
20
|
-
|
|
21
|
-
Leverages maestro's unique wiki graph infrastructure (BM25 search, backlinks, health scoring) — no equivalent in gstack. Directly improves the quality of all downstream wiki consumers (search, digest, follow-along).
|
|
22
|
-
</purpose>
|
|
23
|
-
|
|
24
|
-
<context>
|
|
25
|
-
Arguments: $ARGUMENTS
|
|
26
|
-
|
|
27
|
-
Flags, storage paths, and CLI commands defined in workflow wiki-connect.md.
|
|
28
|
-
</context>
|
|
29
|
-
|
|
30
|
-
<execution>
|
|
31
|
-
Follow '~/.maestro/workflows/wiki-connect.md' completely (Stages 1-6).
|
|
32
|
-
|
|
33
|
-
**Next-step routing:**
|
|
34
|
-
- Generate knowledge digest → `/wiki-digest <topic>`
|
|
35
|
-
- Follow-along on orphan → `/learn-follow <wiki-id>`
|
|
36
|
-
- View full graph → `maestro wiki graph`
|
|
37
|
-
</execution>
|
|
38
|
-
|
|
39
|
-
<error_codes>
|
|
40
|
-
| Code | Severity | Condition | Recovery |
|
|
41
|
-
|------|----------|-----------|----------|
|
|
42
|
-
| E001 | error | No wiki entries found (empty index) | Initialize wiki content first, or run `/maestro-init` |
|
|
43
|
-
| E002 | error | `maestro wiki` CLI not available | Check maestro installation |
|
|
44
|
-
| W001 | warning | No connection candidates found above threshold | Lower --min-similarity or check if graph is already well-connected |
|
|
45
|
-
| W002 | warning | Some wiki update calls failed during --fix | Partial application; retry failed entries manually |
|
|
46
|
-
| W003 | warning | Health score unchanged after fix | Connections may not have improved the specific health metrics |
|
|
47
|
-
</error_codes>
|
|
48
|
-
|
|
49
|
-
<success_criteria>
|
|
50
|
-
- [ ] Wiki index loaded with entry count and type distribution
|
|
51
|
-
- [ ] Baseline health score recorded
|
|
52
|
-
- [ ] Orphans identified and rescue candidates generated
|
|
53
|
-
- [ ] Connection candidates scored and ranked
|
|
54
|
-
- [ ] Results filtered by --min-similarity and limited by --max
|
|
55
|
-
- [ ] Suggestions displayed with scores and reasons
|
|
56
|
-
- [ ] If --fix: entries updated with new `related` links
|
|
57
|
-
- [ ] If --fix: new health score computed and delta reported
|
|
58
|
-
- [ ] Report written to `wiki-connections-{date}.md`
|
|
59
|
-
- [ ] Graph insights appended to `specs/learnings.md` as `<spec-entry>` blocks
|
|
60
|
-
- [ ] No unintended entry modifications (only `related` field changed)
|
|
61
|
-
- [ ] Summary displayed with next-step routing
|
|
62
|
-
</success_criteria>
|
|
@@ -1,68 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: wiki-digest
|
|
3
|
-
description: Generate wiki digest with theme clustering and gap analysis
|
|
4
|
-
argument-hint: "[<topic>|--recent N] [--type <type>] [--format brief|full]"
|
|
5
|
-
allowed-tools:
|
|
6
|
-
- Read
|
|
7
|
-
- Write
|
|
8
|
-
- Bash
|
|
9
|
-
- Glob
|
|
10
|
-
- Grep
|
|
11
|
-
- Agent
|
|
12
|
-
- AskUserQuestion
|
|
13
|
-
---
|
|
14
|
-
<purpose>
|
|
15
|
-
Knowledge synthesis command that generates actionable digests from the wiki knowledge graph. Clusters entries by semantic theme, identifies knowledge gaps, and produces a coverage heatmap. Unique to maestro — leverages the wiki graph (BM25 search, backlinks, health) to surface trends and missing knowledge.
|
|
16
|
-
|
|
17
|
-
Unlike `maestro wiki list` which shows raw entries, this command synthesizes and interprets the knowledge base, producing a curated summary with gap analysis and recommended next actions.
|
|
18
|
-
</purpose>
|
|
19
|
-
|
|
20
|
-
<required_reading>
|
|
21
|
-
@~/.maestro/workflows/wiki-digest.md
|
|
22
|
-
</required_reading>
|
|
23
|
-
|
|
24
|
-
<deferred_reading>
|
|
25
|
-
- @~/.maestro/workflows/issue.md (issues.jsonl canonical schema for `--create-issues` routing)
|
|
26
|
-
</deferred_reading>
|
|
27
|
-
|
|
28
|
-
<context>
|
|
29
|
-
Arguments: $ARGUMENTS
|
|
30
|
-
|
|
31
|
-
Flags, scope resolution, storage paths, and CLI commands defined in workflow wiki-digest.md.
|
|
32
|
-
</context>
|
|
33
|
-
|
|
34
|
-
<execution>
|
|
35
|
-
Follow '~/.maestro/workflows/wiki-digest.md' completely (Stages 1-8).
|
|
36
|
-
|
|
37
|
-
**Next-step routing:**
|
|
38
|
-
- Deep dive on a theme → `/learn-follow <wiki-id>`
|
|
39
|
-
- Fix graph gaps → `/wiki-connect --fix`
|
|
40
|
-
- Decompose code for missing patterns → `/learn-decompose <path>`
|
|
41
|
-
- Create missing entries → `maestro wiki create --type <type> --slug <slug>`
|
|
42
|
-
- Triage gap issues → `/manage-issue list --source wiki-digest`
|
|
43
|
-
</execution>
|
|
44
|
-
|
|
45
|
-
<error_codes>
|
|
46
|
-
| Code | Severity | Condition | Recovery |
|
|
47
|
-
|------|----------|-----------|----------|
|
|
48
|
-
| E001 | error | No wiki entries found (empty index) | Initialize wiki content first |
|
|
49
|
-
| E002 | error | Topic search returned 0 results | Broaden topic or check wiki content |
|
|
50
|
-
| W001 | warning | Too few entries (<5) for meaningful theme clustering | Digest produced but themes may be trivial |
|
|
51
|
-
| W002 | warning | specs/learnings.md not found — skipping cross-reference | Proceed without knowhow context |
|
|
52
|
-
| W003 | warning | Some entry bodies failed to load — partial summaries | Note incomplete entries in digest |
|
|
53
|
-
</error_codes>
|
|
54
|
-
|
|
55
|
-
<success_criteria>
|
|
56
|
-
- [ ] Scope parsed and entries loaded
|
|
57
|
-
- [ ] Baseline health score recorded
|
|
58
|
-
- [ ] Entries clustered into 3-5 semantic themes
|
|
59
|
-
- [ ] Per-theme analysis: summary, key entries, gaps, health
|
|
60
|
-
- [ ] Cross-reference with specs/learnings.md completed
|
|
61
|
-
- [ ] Coverage heatmap generated (type × theme matrix)
|
|
62
|
-
- [ ] Knowledge gaps identified with suggested actions
|
|
63
|
-
- [ ] If `--create-issues`: gap issues created in `issues.jsonl` (deduped)
|
|
64
|
-
- [ ] Digest written to `KNW-digest-{slug}-{date}.md`
|
|
65
|
-
- [ ] Meta-insights appended to `specs/learnings.md` as `<spec-entry>` blocks
|
|
66
|
-
- [ ] No files modified outside `.workflow/knowhow/` and `.workflow/issues/` (issues only when `--create-issues`)
|
|
67
|
-
- [ ] Summary displayed with key findings and next-step routing
|
|
68
|
-
</success_criteria>
|