@codewizard-dt/bootstrap 5.3.0 → 6.0.1

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.
Files changed (95) hide show
  1. package/LICENSE.md +105 -0
  2. package/README.md +22 -3
  3. package/bin/cli.js +16 -0
  4. package/lib/hooks/README.md +124 -3
  5. package/lib/hooks/claude-settings-guard.js +8 -2
  6. package/lib/prompts/README.md +1 -1
  7. package/lib/prompts/migrate-wiki.md +7 -7
  8. package/lib/scripts/README.md +111 -10
  9. package/lib/scripts/bootstrap-prefs-tui.js +1222 -0
  10. package/lib/scripts/install-global.sh +137 -6
  11. package/lib/scripts/migrate-project.sh +53 -11
  12. package/lib/scripts/rename-wiki-ids.js +232 -0
  13. package/lib/scripts/templates/CLAUDE-wiki.md +6 -6
  14. package/lib/scripts/templates/bootstrap-prefs-schema.json +11 -2
  15. package/lib/scripts/templates/settings-deny.json +1 -1
  16. package/lib/scripts/templates/settings-sandbox-unattended.json +36 -0
  17. package/lib/scripts/templates/settings-sandbox.json +7 -0
  18. package/lib/scripts/templates/wiki/conventions.md +9 -9
  19. package/lib/scripts/templates/wiki/dashboard.html +527 -23
  20. package/lib/scripts/templates/wiki/index.md +2 -2
  21. package/lib/scripts/templates/wiki/work/bugs/lifecycle.md +1 -1
  22. package/lib/scripts/templates/wiki/work/decisions/index.md +12 -4
  23. package/lib/scripts/templates/wiki/work/decisions/lifecycle.md +11 -9
  24. package/lib/scripts/templates/wiki/work/requirements/index.md +12 -4
  25. package/lib/scripts/templates/wiki/work/requirements/lifecycle.md +8 -8
  26. package/lib/scripts/templates/wiki/work/roadmaps/index.md +11 -3
  27. package/lib/scripts/templates/wiki/work/roadmaps/lifecycle.md +7 -5
  28. package/lib/scripts/templates/wiki/work/tasks/index.md +1 -1
  29. package/lib/scripts/templates/wiki/work/tasks/lifecycle.md +16 -8
  30. package/lib/scripts/templates/wiki/work/uat/lifecycle.md +3 -3
  31. package/lib/scripts/wiki-dashboard-server.js +98 -0
  32. package/lib/skills/README.md +27 -22
  33. package/lib/skills/_shared/ARCHIVE-WORK-ITEM.md +103 -0
  34. package/lib/skills/_shared/ID-RESOLUTION.md +142 -0
  35. package/lib/skills/_shared/SKILL-BOILERPLATE.md +50 -0
  36. package/lib/skills/adr-assess/SKILL.md +112 -0
  37. package/lib/skills/{decision-create → adr-create}/SKILL.md +26 -26
  38. package/lib/skills/adr-deprecate/SKILL.md +190 -0
  39. package/lib/skills/adr-extract/SKILL.md +255 -0
  40. package/lib/skills/{decision-finalize → adr-finalize}/SKILL.md +38 -38
  41. package/lib/skills/{decision-next → adr-next}/SKILL.md +20 -19
  42. package/lib/skills/{decision-walkthrough → adr-walkthrough}/SKILL.md +23 -29
  43. package/lib/skills/architecture-audit/SKILL.md +1 -1
  44. package/lib/skills/autopilot/SKILL.md +110 -0
  45. package/lib/skills/bootstrap-config/SKILL.md +1 -1
  46. package/lib/skills/bug-assess/SKILL.md +3 -3
  47. package/lib/skills/bug-close/SKILL.md +13 -27
  48. package/lib/skills/{bug-file → bug-create}/SKILL.md +10 -14
  49. package/lib/skills/bug-triage/SKILL.md +5 -19
  50. package/lib/skills/demo/SKILL.md +1 -1
  51. package/lib/skills/extract-feature/SKILL.md +3 -3
  52. package/lib/skills/git-commit/SKILL.md +4 -4
  53. package/lib/skills/port-feature/SKILL.md +3 -3
  54. package/lib/skills/power-mode/SKILL.md +42 -49
  55. package/lib/skills/prd-assess/SKILL.md +105 -0
  56. package/lib/skills/{req-compile → prd-compile}/SKILL.md +6 -13
  57. package/lib/skills/{req-create → prd-create}/SKILL.md +19 -19
  58. package/lib/skills/prd-deprecate/SKILL.md +173 -0
  59. package/lib/skills/{req-finalize → prd-finalize}/SKILL.md +20 -29
  60. package/lib/skills/primer/SKILL.md +2 -2
  61. package/lib/skills/research/SKILL.md +3 -3
  62. package/lib/skills/roadmap-assess/SKILL.md +20 -20
  63. package/lib/skills/roadmap-create/SKILL.md +19 -29
  64. package/lib/skills/roadmap-next/SKILL.md +16 -28
  65. package/lib/skills/security-audit/SKILL.md +1 -1
  66. package/lib/skills/tackle/SKILL.md +13 -15
  67. package/lib/skills/{task-audit → task-assess}/SKILL.md +34 -44
  68. package/lib/skills/task-close/SKILL.md +73 -0
  69. package/lib/skills/{task-add → task-create}/SKILL.md +25 -24
  70. package/lib/skills/uat-assess/SKILL.md +124 -0
  71. package/lib/skills/uat-auto/SKILL.md +9 -7
  72. package/lib/skills/uat-auto-plus/SKILL.md +2 -2
  73. package/lib/skills/{uat-generate → uat-create}/SKILL.md +10 -12
  74. package/lib/skills/uat-skip/SKILL.md +5 -9
  75. package/lib/skills/uat-walk/SKILL.md +2 -2
  76. package/lib/skills/uat-walk/UAT-CORE.md +29 -16
  77. package/lib/skills/update-docs/SKILL.md +1 -1
  78. package/lib/skills/usage-report/SKILL.md +52 -0
  79. package/lib/skills/usage-report/scripts/pricing.json +22 -0
  80. package/lib/skills/usage-report/scripts/usage-report.js +518 -0
  81. package/lib/skills/whats-next/SKILL.md +177 -0
  82. package/lib/skills/wiki-archive/SKILL.md +12 -23
  83. package/lib/skills/wiki-lint/SKILL.md +23 -13
  84. package/lib/skills/wiki-query/SKILL.md +1 -1
  85. package/lib/skills/wiki-rotate-log/SKILL.md +1 -1
  86. package/lib/skills/wiki-tidy/SKILL.md +6 -9
  87. package/package.json +3 -3
  88. package/lib/scripts/templates/wiki/work/decisions/archive/index.md +0 -10
  89. package/lib/scripts/templates/wiki/work/requirements/archive/index.md +0 -10
  90. package/lib/scripts/templates/wiki/work/roadmaps/archive/index.md +0 -10
  91. package/lib/skills/req-extract-decisions/SKILL.md +0 -241
  92. package/lib/skills/req-retire/SKILL.md +0 -185
  93. package/lib/skills/req-update/SKILL.md +0 -265
  94. package/lib/skills/task-trash/SKILL.md +0 -115
  95. package/lib/skills/task-update/SKILL.md +0 -136
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: roadmap-next
3
- description: Point at the first unchecked item(s) in a single roadmap; create task files for inline placeholders; group items into parallelizable waves; auto-archive when fully checked. Requires a roadmap argument — run /roadmap-assess first to see status and priority across all active roadmaps.
3
+ description: Point at the first unchecked item(s) in a single roadmap; create task files for inline placeholders; group items into parallelizable waves; auto-close when fully checked. Requires a roadmap argument — run /roadmap-assess first to see status and priority across all active roadmaps.
4
4
  category: researching
5
5
  model: claude-haiku-4-5-20251001
6
6
  argument-hint: <path to roadmap file, NNN-slug, or number>
@@ -12,7 +12,7 @@ user-invocable: true
12
12
 
13
13
  # Next Step
14
14
 
15
- Surface unchecked items in a single roadmap, grouped into parallelizable waves, and tell the user how to act. When the roadmap has all items checked, flip its status to `done` and move it to `archive/`.
15
+ Surface unchecked items in a single roadmap, grouped into parallelizable waves, and tell the user how to act. When the roadmap has all items checked, flip its status to `done` and move its index row to Closed.
16
16
 
17
17
  **Roadmap Input**: $ARGUMENTS
18
18
 
@@ -24,11 +24,7 @@ This skill operates on exactly one roadmap — it no longer scans across all roa
24
24
 
25
25
  ## Step 1: Resolve the file (`find_file`/`list_dir`, never bash)
26
26
 
27
- | Input | Action |
28
- | ------------------ | ----------------------------------------------------------------------------------------------------------------------------------- |
29
- | File path | confirm exists (`find_file`); missing → `Roadmap file not found: <path>` + STOP |
30
- | `NNN-slug` | match in `wiki/work/roadmaps/`; none → `No roadmap matching '<input>' found…` + STOP |
31
- | Number (`1`/`001`) | `list_dir`, match zero-padded prefix; ambiguous → list + `AskUserQuestion`; none → `No roadmap with number '<input>' found.` + STOP |
27
+ Resolve the file per ~/.claude/skills/_shared/ID-RESOLUTION.md — family: roadmaps · scope: active · ambiguous: interactive · empty: STOP (Step 0)
32
28
 
33
29
  ## Step 2: Parse → upgrade inline items → parallelism analysis
34
30
 
@@ -42,42 +38,34 @@ Run the three shared procedures below, in order, on the resolved file.
42
38
 
43
39
  `Read` the file (markdown). Extract: **phases** (`## Phase N: <name>` in order), **items** (`- [ ]` unchecked / `- [x]` checked), **status** (`- **Status**: active | done`), and the `roadmap_id` (`- **ID**: ROADMAP-NNNN` front matter — always read this first — or, as a fallback, the filename prefix, e.g. `ROADMAP-0013-billing.md` → `ROADMAP-0013`, or a legacy 3-digit file `ROADMAP-012-billing.md` → `ROADMAP-012`). Per item capture: `phase` (nearest preceding heading, or `(no phase)`), `checked`, `text`, `kind` (`task-link` if body starts `[[TASK-NNNN`, else `inline`), `task_id` (from `[[TASK-NNNN: title]]`), `task_path` (`find_file` `TASK-NNNN-*` in `wiki/work/tasks/` — matches active or archived). Compute `total`, `done`. Collect unchecked items into `candidate_items`, **capped at 9 total**.
44
40
 
45
- For each `candidate_items` item that is already `kind == 'task-link'` (skip this for `inline` items until after they're upgraded below): `Read` `task_path`'s frontmatter and store `task_status` (`todo | in-progress | pending-uat | done | trashed`, per [tasks lifecycle](../tasks/lifecycle.md)). If `task_status == 'pending-uat'`, also resolve `uat_path` — read the task's `uat:` frontmatter field if present and `find_file` it; if empty or not found, leave `uat_path` unset (implementation finished but `/uat-generate` hasn't run yet).
41
+ For each `candidate_items` item that is already `kind == 'task-link'` (skip this for `inline` items until after they're upgraded below): `Read` `task_path`'s frontmatter and store `task_status` (`todo | in-progress | pending-uat | done | trashed`, per [tasks lifecycle](../tasks/lifecycle.md)). If `task_status == 'pending-uat'`, also resolve `uat_path` — read the task's `uat:` frontmatter field if present and `find_file` it; if empty or not found, leave `uat_path` unset (implementation finished but `/uat-create` hasn't run yet).
46
42
 
47
43
  ### Upgrade inline items to task files
48
44
 
49
45
  **All roadmap items must eventually be task files** — inline items are placeholders. For each `candidate_items` item with `kind == 'inline'`:
50
46
 
51
47
  1. Announce: `Inline item found: "<text>"[ (in <roadmap_title>)] — checking for an existing task before creating one.`
52
- 2. **Check for an existing task:** `Read` `wiki/work/tasks/index.md`, scan its active-item bullets for one whose title/summary plausibly covers the intent; if likely, `Read` that task to confirm. Found → use its `TASK-NNNN` + path, skip to step 5 (do **not** call `task-add`).
53
- 3. Else invoke `Skill` `task-add` with the item text as `args` (**no** `--roadmap` flag — the link is managed here to avoid a duplicate item).
54
- 4. Extract the new task path + ID from task-add's summary (`File path` row); if parsing fails, `list_dir` `wiki/work/tasks/` for the newest `.md` not present before, and `Read` it to confirm `TASK-NNNN` + title (from `# NNN: <title>`).
48
+ 2. **Check for an existing task:** `Read` `wiki/work/tasks/index.md`, scan its active-item bullets for one whose title/summary plausibly covers the intent; if likely, `Read` that task to confirm. Found → use its `TASK-NNNN` + path, skip to step 5 (do **not** call `task-create`).
49
+ 3. Else invoke `Skill` `task-create` with the item text as `args` (**no** `--roadmap` flag — the link is managed here to avoid a duplicate item).
50
+ 4. Extract the new task path + ID from task-create's summary (`File path` row); if parsing fails, `list_dir` `wiki/work/tasks/` for the newest `.md` not present before, and `Read` it to confirm `TASK-NNNN` + title (from `# NNN: <title>`).
55
51
  5. `Edit` the roadmap: `- [ ] <item_text>` → `- [ ] [[TASK-NNNN: <title>]]`.
56
52
  6. Update the record: `kind='task-link'`, `task_id`, `task_path` (from `find_file`). A freshly created task is always `status: todo` — set `task_status = 'todo'` directly, no need to re-read the file.
57
53
 
58
- If `task-add` fails/cancels, **stop and report**: `Task creation cancelled for: "<text>"[ (in <roadmap_title>)]. Inline items cannot be worked on without a task file. Re-run /roadmap-next after /task-add <description>.`
54
+ If `task-create` fails/cancels, **stop and report**: `Task creation cancelled for: "<text>"[ (in <roadmap_title>)]. Inline items cannot be worked on without a task file. Re-run /roadmap-next after /task-create <description>.`
59
55
 
60
56
  ### Parallelism analysis → waves
61
57
 
62
58
  After upgrades, for each item: `Read` its `task_path`, find `## Dependencies` / `## Blocked by`, extract `TASK-NNNN` refs; an **active blocker** is a dep whose `TASK-NNNN` also appears in `candidate_items`. Store as `blockers`. Topological sort: **Wave 1** = empty `blockers`; **Wave 2** = blockers all in Wave 1; **Wave 3** = blockers all in Wave 1∪2. Omit Wave 4+. **Cap each wave at 3 items** (document order); note overflow count. Store as `waves`.
63
59
 
64
- ### Archive a fully-complete roadmap (`total > 0` and `done == total`) — run automatically, no prompt
60
+ ### Close a fully-complete roadmap (`total > 0` and `done == total`) — run automatically, no prompt
65
61
 
66
- 1. If `status: active`, `Edit` → `status: done`.
67
- 2. Remove its row from `wiki/work/roadmaps/index.md` (active-only index).
68
- 3. `git mv <roadmap_path> wiki/work/roadmaps/archive/<filename>` (Bash — `git mv` only).
69
- 4. Append to `wiki/work/roadmaps/archive/index.md`: `| [[ROADMAP-NNNN]] | <title> | done | YYYY-MM-DD |`.
70
- 5. Append to `wiki/log.md`:
71
- ```
72
- ## [YYYY-MM-DD] archive | <ROADMAP-NNNN> — completed, moved to archive
73
- All items checked. Moved to wiki/work/roadmaps/archive/<filename>.
74
- ```
62
+ Read `~/.claude/skills/_shared/ARCHIVE-WORK-ITEM.md` now and run its **In-place close (roadmaps, decisions, requirements)** section: `family: roadmaps`, `terminal_status: done`, default log entry; no prompt. The roadmap file stays in place — only its `status:` flips and its row moves from `## Active` to `## Closed` in `wiki/work/roadmaps/index.md`.
75
63
 
76
64
  ---
77
65
 
78
66
  ## Step 3: Report
79
67
 
80
- - **All checked** (`done == total`, `total > 0`) → run the shared archive procedure, then report: `Progress: <total>/<total> — all done!` / `Status → done. Archived → wiki/work/roadmaps/archive/<filename>.`
68
+ - **All checked** (`done == total`, `total > 0`) → run the shared close procedure (ARCHIVE-WORK-ITEM.md, above), then report: `Progress: <total>/<total> — all done!` / `Status → done. Moved to Closed in wiki/work/roadmaps/index.md.`
81
69
  - **Unchecked items remain** → progress line + one table per non-empty wave (every item is a task-link post-upgrade):
82
70
 
83
71
  ```
@@ -97,16 +85,16 @@ After upgrades, for each item: `Read` its `task_path`, find `## Dependencies` /
97
85
  **Action cell by `task_status`** (this is the fix for the tackle→UAT visibility gap — a `pending-uat` task needs testing, not more implementation):
98
86
  - `todo` / `in-progress` (default) → `` `/tackle <task_path>` ``
99
87
  - `pending-uat` with `uat_path` resolved → `` `/uat-walk <uat_path>` `` — annotate the Item cell with a trailing `⏳ awaiting UAT`
100
- - `pending-uat` with no `uat_path` → `` `/uat-generate <task_path>` `` — annotate the Item cell with a trailing `⏳ awaiting UAT (no tests yet)`
88
+ - `pending-uat` with no `uat_path` → `` `/uat-create <task_path>` `` — annotate the Item cell with a trailing `⏳ awaiting UAT (no tests yet)`
101
89
  - `task_path` not found → `` `/tackle <task_path>` `` with ` (file not found)` appended, regardless of status (can't read a status that isn't there)
102
90
 
103
- - **Zero items** → `Roadmap has no checklist items yet. Edit the roadmap file directly to add items, or link a new task to it with /task-add --roadmap <ROADMAP-NNNN> <description>.`
91
+ - **Zero items** → `Roadmap has no checklist items yet. Edit the roadmap file directly to add items, or link a new task to it with /task-create --roadmap <ROADMAP-NNNN> <description>.`
104
92
 
105
93
  ---
106
94
 
107
95
  ## Constraints
108
96
 
109
- - **Never flip checkboxes.** The only permitted content writes are: (1) `Status: active → done` before archiving; (2) inline-placeholder → task-link replacement (upgrade step); (3) archive/log appends when archiving.
110
- - Permitted tools: `list_dir`, `find_file`, `Read`, `Edit`, `Bash`, `AskUserQuestion`, `Skill` (only for `task-add` on inline items).
111
- - `Bash` only for `git mv` when archiving. Never bash reads (`cat`/`find`/`grep`/`sed`/`ls`).
97
+ - **Never flip checkboxes.** The only permitted content writes are: (1) inline-placeholder → task-link replacement (upgrade step); (2) the status flip, index edits, and log append performed by ARCHIVE-WORK-ITEM.md's in-place close when closing.
98
+ - Permitted tools: `list_dir`, `find_file`, `Read`, `Edit`, `AskUserQuestion`, `Skill` (only for `task-create` on inline items).
99
+ - No `Bash` needed — closing a roadmap never moves a file. Never bash reads (`cat`/`find`/`grep`/`sed`/`ls`).
112
100
  - Keep the final report terse — one block per wave, no preamble, no closing summary.
@@ -243,7 +243,7 @@ Categories audited: [list]
243
243
  2. **Cite specific files and line numbers** for every PASS or FAIL — say where you looked; "no evidence found" alone is insufficient.
244
244
  3. **Serena for all code navigation** (`find_symbol`, `search_for_pattern`, `get_symbols_overview`) — no shell grep.
245
245
  4. **Flag NEEDS-REVIEW honestly** — controls needing runtime observation (e.g. live rate limiting) get flagged with what to verify manually.
246
- 5. **Do not fix** — audit and report only; hand off fixes to the user or `/task-add`.
246
+ 5. **Do not fix** — audit and report only; hand off fixes to the user or `/task-create`.
247
247
  6. **Scope to the repo** — don't speculate about external infra unless config files are present.
248
248
  7. **One category at a time** — complete each fully before the next; don't interleave findings.
249
249
  8. **Persist the report** — write it to `wiki/reports/security-audit/` (see Reporting) in addition to printing it; a report that only lives in the chat leaves no trail for the next audit to compare against.
@@ -19,15 +19,13 @@ Execute a pre-planned task file step-by-step. **The task file IS the plan — no
19
19
 
20
20
  ## Step 0: Resolve the task file
21
21
 
22
- Resolve `$ARGUMENTS` (use Serena `find_file`/`list_dir`):
22
+ Resolve the file per ~/.claude/skills/_shared/ID-RESOLUTION.md — family: tasks · scope: active · ambiguous: interactive (list + ask) · empty: run **Roadmap Auto-Discovery** (0a) first; only then the task survey
23
+
24
+ A missing path or no match is not a resolution error here — fall through:
23
25
 
24
26
  | Input | Action |
25
27
  |-------|--------|
26
- | File path (`wiki/work/tasks/3-user-auth.md`) | confirm exists; else fall through |
27
- | Number-slug (`3-user-auth`) | match in `wiki/work/tasks/`; else fall through |
28
- | Number / description (`3`, `user auth`) | search `wiki/work/tasks/`; ambiguous → list + ask; no match → fall through |
29
- | Empty | run **Roadmap Auto-Discovery** (0a) first; only then the task survey |
30
- | Non-empty but unresolved | task survey — recommend, never auto-pick |
28
+ | Non-empty but unresolved (missing path, no match, or free-text description) | task survey — recommend, never auto-pick |
31
29
 
32
30
  Use the resolved path as the outline for all later steps.
33
31
 
@@ -37,8 +35,8 @@ Use the resolved path as the outline for all later steps.
37
35
 
38
36
  Zero-click: find the first actionable roadmap item and tackle it, **no prompts**.
39
37
 
40
- 1. `mcp__serena__list_dir("wiki/work/roadmaps/", recursive=false)` — root `.md` files only (exclude `archive/`, `README.md`). None → task survey.
41
- 2. `Read` each roadmap (markdown). Select the one with the most `[x]` items (furthest along); tie/single → use it. No prompt.
38
+ 1. `mcp__serena__list_dir("wiki/work/roadmaps/", recursive=false)` — root `.md` files only (exclude `archive/`, `README.md`, `index.md`, `lifecycle.md`). None → task survey.
39
+ 2. `Read` each roadmap (markdown); keep only those with frontmatter `status: active` (closed roadmaps stay in the directory). Select the one with the most `[x]` items (furthest along); tie/single → use it. No prompt.
42
40
  3. Scan top-to-bottom for the first `## Phase N` (or flat list) containing a `- [ ]` item. None unchecked → roadmap done → task survey.
43
41
  4. Take the first `- [ ]` line in that phase:
44
42
  - **Task link** (markdown link into `wiki/work/tasks/`) → extract path, use as outline. Announce: `Roadmap auto-selected: <roadmap> → Phase <N>: <name> → <link text>`.
@@ -47,15 +45,15 @@ Zero-click: find the first actionable roadmap item and tackle it, **no prompts**
47
45
  ### Task survey (empty OR unresolved)
48
46
 
49
47
  Recommend from the index; **do not auto-pick**.
50
- - **Read only `wiki/work/tasks/index.md`** (canonical active list: bullet lines `- [TASK-NNNN — Title](TASK-NNNN-slug.md) — one-line summary · status`). Do NOT read individual task files, `grep`, `bash`, or aggregate across `wiki/work/tasks/` — the index exists to prevent exactly that. The only per-file read is the chosen task in Step 1.
51
- - Missing `index.md` / no active-item bullets → STOP: `Task index at wiki/work/tasks/index.md is empty or missing. Add tasks with /task-add, or invoke /tackle <path-or-slug> directly.` Do not scan every file.
48
+ - **Read only `wiki/work/tasks/index.md`** (canonical active list: bullet lines `- [TASK-NNNN — Title](TASK-NNNN-slug.md) — one-line summary · status`; if a family index has `## Active` / `## Closed` sections, read only under `## Active`). Do NOT read individual task files, `grep`, `bash`, or aggregate across `wiki/work/tasks/` — the index exists to prevent exactly that. The only per-file read is the chosen task in Step 1.
49
+ - Missing `index.md` / no active-item bullets → STOP: `Task index at wiki/work/tasks/index.md is empty or missing. Add tasks with /task-create, or invoke /tackle <path-or-slug> directly.` Do not scan every file.
52
50
  - `index.md` carries no progress columns — it lists title + one-line summary + `status` only, and `status` now directly distinguishes `todo` / `in-progress` / `pending-uat` (see [lifecycle](../tasks/lifecycle.md)) — no need to infer UAT-awaiting state from file existence. If a bullet points at a task file that no longer exists (moved/archived), note the drift in one sentence and skip it — don't pre-emptively fix the index.
53
51
  - Empty active list → STOP: "No active tasks to tackle".
54
52
  - Present the active items as a compact table (`TASK-NNNN` · title · status). Below it, a **Recommendation** ranking top 1–3 by priority, using `status` alone:
55
53
  1. `status: in-progress` — finish what's started.
56
54
  2. `status: todo`, lowest-numbered first.
57
- - Tasks at `status: pending-uat` are excluded from recommendations and listed under `**Awaiting UAT**:` — `mcp__serena__list_dir` on `wiki/work/uat/` for the matching `UAT-NNNN-*` file; if found, suggest `/uat-walk wiki/work/uat/UAT-NNNN-<slug>.md`; if none found (implementation finished but `/uat-generate` never ran), suggest `/uat-generate wiki/work/tasks/TASK-NNNN-<slug>.md` instead.
58
- - Progress counts, `[BLOCKED]`/`[FAILED]` flags, and per-step state are **not** in `index.md` by design — they live in the task files. This no-args survey deliberately ranks on `status` + UAT presence alone rather than re-reading every task file; use `/task-audit` when the full progress/blocker picture is needed. (Design note: the survey was simplified to `index.md`'s real bullet schema rather than expanding `index.md` with Progress/UAT/Flags columns, which would violate the "active items only, flat list" convention in `wiki/conventions.md`.)
55
+ - Tasks at `status: pending-uat` are excluded from recommendations and listed under `**Awaiting UAT**:` — `mcp__serena__list_dir` on `wiki/work/uat/` for the matching `UAT-NNNN-*` file; if found, suggest `/uat-walk wiki/work/uat/UAT-NNNN-<slug>.md`; if none found (implementation finished but `/uat-create` never ran), suggest `/uat-create wiki/work/tasks/TASK-NNNN-<slug>.md` instead.
56
+ - Progress counts, `[BLOCKED]`/`[FAILED]` flags, and per-step state are **not** in `index.md` by design — they live in the task files. This no-args survey deliberately ranks on `status` + UAT presence alone rather than re-reading every task file; use `/task-assess` when the full progress/blocker picture is needed. (Design note: the survey was simplified to `index.md`'s real bullet schema rather than expanding `index.md` with Progress/UAT/Flags columns, which would violate the "active items only, flat list" convention in `wiki/conventions.md`.)
59
57
  - Use `AskUserQuestion` (top rec first, labelled `(Recommended)`; up to 2 more; `header` = number-slug). If input was unresolved, prefix one line noting it. Do NOT proceed to Step 1 until the user chooses.
60
58
 
61
59
  ---
@@ -89,7 +87,7 @@ Standard Read/Edit/Write are allowed for markdown and config (JSON, YAML, `.env`
89
87
 
90
88
  **Delegate to the agent type named in that section's annotation.** All implementation runs in a sub-agent, never the main context. Next-step priority: (1) fix blockers, (2) continue WIP, (3) start first incomplete section.
91
89
 
92
- **Delegate directly — no re-planning.** Pass the step's checkboxes and sub-details verbatim. Do not research, re-plan, or ask questions (that was `/task-add`'s job).
90
+ **Delegate directly — no re-planning.** Pass the step's checkboxes and sub-details verbatim. Do not research, re-plan, or ask questions (that was `/task-create`'s job).
93
91
 
94
92
  **CRITICAL:** max **3** sub-processes at a time; **always terminate** processes when done (dev servers, type checkers, long-running commands).
95
93
 
@@ -105,7 +103,7 @@ Every sub-agent prompt MUST include:
105
103
 
106
104
  ⛔ **HARD RULE — update immediately, never batch.** The moment a Step 2 sub-agent returns, the *next thing you do* is flip that step's checkboxes on disk. Do not dispatch the next sub-agent, continue the cycle, or defer updates. Step N's update lands before step N+1 begins.
107
105
 
108
- 1. Use **`Edit`** — one call per checkbox line. **Never** `sed`/`awk`/`perl -i`/`echo` on task files, however many flip (ten `Edit`s right; one `sed` wrong + triggers approval). Markers: `[x]` done · `[WIP]` partial · `[BLOCKED: reason]` · `[FAILED: reason]`.
106
+ 1. Edit only — see `~/.claude/skills/_shared/SKILL-BOILERPLATE.md` § Edit hygiene — one call per checkbox line, however many flip. Markers: `[x]` done · `[WIP]` partial · `[BLOCKED: reason]` · `[FAILED: reason]`.
109
107
  2. Add `<!-- Updated: YYYY-MM-DD HH:MM -->`.
110
108
  3. Add any subtasks discovered during execution.
111
109
  4. **Keep `wiki/work/tasks/index.md` in sync** — `index.md` has no progress or flags columns, so there is nothing to recount there. The one thing to maintain is the `· status` suffix on this task's bullet line: if this cycle flips the task's frontmatter `status` (e.g. `todo` → `in-progress`), update the matching `· status` on its `index.md` line with a single `Edit` (skip if unchanged). Progress and flags live only in the task file.
@@ -136,7 +134,7 @@ Before anything else: `Edit` the task's frontmatter `status` → `pending-uat` (
136
134
  This is a real state, not a formality — `/roadmap-next` uses it to recommend `/uat-walk`/`/uat-auto` instead of `/tackle` for this task going forward. Do this even if you're about to immediately answer "No" to the UAT-generation gate below — a task with no UAT still needs `pending-uat` recorded (an explicit skip is `/uat-skip`'s job, not silence).
137
135
 
138
136
  ### Step 6: UAT generation gate — ⛔ HARD STOP (never skip or reorder)
139
- Ask via `AskUserQuestion`: **"Generate UAT tests for this task?"** — **Yes** → run `/uat-generate wiki/work/tasks/<filename>` (creates the matching UAT file); **No** → skip. **Wait** for the answer (and for `/uat-generate` to finish, if invoked) before Step 6b.
137
+ Ask via `AskUserQuestion`: **"Generate UAT tests for this task?"** — **Yes** → run `/uat-create wiki/work/tasks/<filename>` (creates the matching UAT file); **No** → skip. **Wait** for the answer (and for `/uat-create` to finish, if invoked) before Step 6b.
140
138
 
141
139
  ### Step 6b: Type-check gate
142
140
  Try in order, stop at the first that runs (exit 0 or type errors); skip to next only if not found / target missing: (1) `Skill(typecheck)`, (2) `make typecheck`. Suppress output from not-found/missing-target commands — surface only real type errors. None available → skip silently.
@@ -1,6 +1,6 @@
1
1
  ---
2
- name: task-audit
3
- description: Generate a dependency graph of active tasks showing which block others and which can run in parallel; also checks for unannotated implementations and auto-completes tasks
2
+ name: task-assess
3
+ description: Assess active tasks — generate a dependency graph showing which block others and which can run in parallel; also checks for unannotated implementations and auto-completes tasks
4
4
  category: researching
5
5
  model: claude-sonnet-5
6
6
  argument-hint: [--json]
@@ -9,9 +9,9 @@ user-invocable: true
9
9
  ---
10
10
  **Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/tasks/lifecycle.md`.
11
11
 
12
- # Task Audit
12
+ # Task Assess
13
13
 
14
- Analyse all active tasks: verify implementation completeness, auto-check unannotated finished steps, move fully-completed tasks, parse dependency blocks, build a directed dependency graph, and surface which tasks block others and which can be safely parallelised.
14
+ Analyse all active tasks: verify implementation completeness, auto-check unannotated finished steps, move fully-completed tasks, read dependency fields, build a directed dependency graph, and surface which tasks block others and which can be safely parallelised.
15
15
 
16
16
  ---
17
17
 
@@ -27,7 +27,7 @@ Read `wiki/work/tasks/index.md` using the `Read` tool.
27
27
 
28
28
  - Parse every active-item bullet line — format `- [TASK-NNNN — Title](TASK-NNNN-slug.md) — one-line summary · status`. Extract the `TASK-NNNN` ID and the linked file path (e.g. `wiki/work/tasks/TASK-001-project-registry-push.md`) for each.
29
29
  - `index.md` lists active items only and carries no progress or flags columns — those are computed from each task file in Step 2.
30
- - If the list is empty, report "No active tasks — nothing to audit." and STOP.
30
+ - If the list is empty, report "No active tasks — nothing to assess." and STOP.
31
31
 
32
32
  Do **not** scan the directory directly. The index is authoritative for active tasks.
33
33
 
@@ -65,26 +65,16 @@ After applying all updates, recount `checked` and `total`. Track which tasks had
65
65
 
66
66
  If `checked == total` (all steps are now checked) after 2c:
67
67
 
68
- 1. Set `status: done` in the task file's frontmatter using `Edit`, then move it from `wiki/work/tasks/` to `wiki/work/tasks/archive/` using `Bash` (`git mv` only).
69
- 2. Delete its line from `wiki/work/tasks/index.md` and append it to `wiki/work/tasks/archive/index.md`.
70
- 3. Scan all other active task files for references to this task's ID (e.g. in their dependency blocks). For each reference found, note it in the Step 4 report as a **now-resolved dependency** — do not auto-edit those files, but suggest `/task-update <NNN>` to clean them up.
71
- 4. Mark the task as `completed: true` in its node record so Step 3 treats it as resolved.
68
+ 1. Read `~/.claude/skills/_shared/ARCHIVE-WORK-ITEM.md` now and run its Procedure for the task: `family: tasks`, `terminal_status: done`, default log entry. It sets the status, moves the file, updates both indexes, and appends the log entry.
69
+ 2. Scan all other active task files for references to this task's ID (in their `depends_on` / `blocks` frontmatter). For each reference found, note it in the Step 4 report as a **now-resolved dependency** — do not auto-edit those files, but suggest that the user edit the task file directly to clean them up.
70
+ 3. Mark the task as `completed: true` in its node record so Step 3 treats it as resolved.
72
71
 
73
- ### 2e. Parse the Dependency Block
72
+ ### 2e. Read the Dependency Fields
74
73
 
75
- In the same file read, locate the dependency blockquote appearing **immediately after the `# NNN —` title line** and **before `## Objective`**:
74
+ From the task file's YAML frontmatter (already in hand from the Step 2 read), read `depends_on`, `blocks`, and `parallel_safe_with` — format per `wiki/work/tasks/lifecycle.md` ("Dependency fields"), not restated here.
76
75
 
77
- ```markdown
78
- > **Depends on**: [002-foo](002-foo.md), [003-bar](003-bar.md)
79
- > **Blocks**: [008-baz](008-baz.md)
80
- > **Parallel-safe with**: [005-qux](005-qux.md), [006-quux](006-quux.md)
81
- ```
82
-
83
- - Values may be `none` if the field is empty.
84
- - Links follow the pattern `[NNN-slug](NNN-slug.md)` — extract the NNN-slug identifier from each link.
85
- - A task with no dependency block at all is treated as having `Depends on: none`, `Blocks: none`, `Parallel-safe with: none`.
86
-
87
- Going forward, task files should also carry one `depends_on::[[TASK-NNNN]]` line per dependency and one `blocks::[[TASK-NNNN]]` line per blocked task, directly below the blockquote — these are additive typed links for Obsidian/Breadcrumbs graph visualization. `/task-audit`'s own parser continues to read only the blockquote above, unchanged.
76
+ - A missing key is treated as an empty list.
77
+ - If none of the three keys is present at all, record `missing_deps` for the report.
88
78
 
89
79
  ### 2f. Build the Node Record
90
80
 
@@ -92,20 +82,20 @@ For each task (skipping any moved to completed in 2d), produce a record:
92
82
 
93
83
  ```
94
84
  {
95
- id: "NNN-slug",
85
+ id: "TASK-NNNN",
96
86
  num: NNN,
97
- depends_on: ["NNN-slug", ...], # tasks that must complete before this one
98
- blocks: ["NNN-slug", ...], # tasks this one must complete before they can start
99
- parallel_safe: ["NNN-slug", ...], # tasks explicitly marked safe to run alongside
87
+ depends_on: ["TASK-NNNN", ...], # tasks that must complete before this one
88
+ blocks: ["TASK-NNNN", ...], # tasks this one must complete before they can start
89
+ parallel_safe: ["TASK-NNNN", ...], # tasks explicitly marked safe to run alongside
100
90
  progress: "X/Y", # updated count after auto-checkmarks
101
91
  flags: "[WIP]" | "—" | etc,
102
- missing_block: true/false, # true if the dependency block was absent entirely
92
+ missing_deps: true/false, # true if none of the three frontmatter keys is present
103
93
  auto_checked: ["step description", ...], # steps that were auto-completed in 2c
104
94
  unverified: ["step description", ...] # unchecked steps whose implementation could not be confirmed
105
95
  }
106
96
  ```
107
97
 
108
- Note tasks missing the dependency block — list them in the Step 4 issues report so the user knows to run `/task-update` on them.
98
+ Note tasks missing dependency fields — list them in the Step 4 issues report so the user knows to edit the task file directly to add them.
109
99
 
110
100
  ---
111
101
 
@@ -133,7 +123,7 @@ Within a wave, all tasks are parallelisable with each other unless an explicit `
133
123
 
134
124
  ---
135
125
 
136
- ## Step 4: Output the Audit Report
126
+ ## Step 4: Output the Assessment Report
137
127
 
138
128
  Print the full report in this order:
139
129
 
@@ -196,7 +186,7 @@ Report what Step 2 discovered and changed:
196
186
  ### Fully-Completed Tasks Moved
197
187
  | Task | Action |
198
188
  |------|--------|
199
- | 005-command-anti-patterns | Moved to wiki/work/tasks/archive/ — update references: /task-update 007 |
189
+ | 005-command-anti-patterns | Moved to wiki/work/tasks/archive/ — update references: edit task 007 directly |
200
190
 
201
191
  ### Unverified Steps (implementation unclear)
202
192
  | Task | Step |
@@ -213,16 +203,16 @@ Omit any section whose table would be empty.
213
203
 
214
204
  | Task | Issue |
215
205
  |------|-------|
216
- | 006-migrate-commands-to-skills | Missing dependency block — run `/task-update 006` to add one |
217
- | 009-audit-skills-vs-sdlc | Stale reference: depends_on "003-deleted-task" not in active index |
206
+ | 006-migrate-commands-to-skills | Missing dependency fields — edit the task file's frontmatter directly to add them |
207
+ | 009-audit-skills-vs-sdlc | Stale reference: depends_on "TASK-0003" not in active index |
218
208
  ```
219
209
 
220
210
  Categories:
221
- - **Missing dependency block** — task file has no `> **Depends on**:` block
211
+ - **Missing dependency fields** — task frontmatter has none of `depends_on` / `blocks` / `parallel_safe_with`
222
212
  - **Stale reference** — referenced task ID not found in active index
223
213
  - **Asymmetric edge** — A blocks B but B doesn't list A in depends_on
224
214
  - **Cycle** — dependency cycle detected (list all members)
225
- - **Now-resolved dependency** — a task was moved to completed; other tasks still reference it in their dependency blocks
215
+ - **Now-resolved dependency** — a task was moved to completed; other tasks still reference it in their dependency fields
226
216
 
227
217
  If no issues: "No issues found."
228
218
 
@@ -237,12 +227,12 @@ Wave 1 tasks are unblocked and can start immediately:
237
227
  /tackle wiki/work/tasks/001-project-registry-push.md
238
228
  /tackle wiki/work/tasks/005-command-anti-patterns.md ← run in parallel
239
229
 
240
- Fix missing dependency blocks:
241
- /task-update 006
242
- /task-update 009
230
+ Fix missing dependency fields (edit each task file's frontmatter directly):
231
+ 006-migrate-commands-to-skills
232
+ 009-audit-skills-vs-sdlc
243
233
 
244
- Clean up now-resolved dependency references:
245
- /task-update 007 (005 was moved to completed)
234
+ Clean up now-resolved dependency references (edit the task file directly):
235
+ 007 (005 was moved to completed)
246
236
  ```
247
237
 
248
238
  ---
@@ -263,7 +253,7 @@ updated: YYYY-MM-DD
263
253
 
264
254
  # Task Dependency Graph
265
255
 
266
- > Auto-generated by `/task-audit` on YYYY-MM-DD. Re-run to refresh. Do not edit by hand.
256
+ > Auto-generated by `/task-assess` on YYYY-MM-DD. Re-run to refresh. Do not edit by hand.
267
257
 
268
258
  <paste the Mermaid block from Step 4a>
269
259
 
@@ -272,7 +262,7 @@ updated: YYYY-MM-DD
272
262
  <paste the Blocking Chains section from Step 4c>
273
263
  ```
274
264
 
275
- 2. Ensure `wiki/work/tasks/index.md` carries a one-line cross-link to the graph, directly under its `Entry format:` line: `Dependency graph: [dependency-graph.md](dependency-graph.md) — regenerated by /task-audit.` If that line is already present, leave it; if absent, add it with a single `Edit`.
265
+ 2. Ensure `wiki/work/tasks/index.md` carries a one-line cross-link to the graph, directly under its `Entry format:` line: `Dependency graph: [dependency-graph.md](dependency-graph.md) — regenerated by /task-assess.` If that line is already present, leave it; if absent, add it with a single `Edit`.
276
266
 
277
267
  There must be **exactly one** `dependency-graph.md` file after this step, and it holds the only copy of the graph. Never write the graph into `index.md` or a `README.md`.
278
268
 
@@ -284,10 +274,10 @@ Print the raw adjacency list as a fenced JSON block:
284
274
  {
285
275
  "tasks": [
286
276
  {
287
- "id": "001-project-registry-push",
277
+ "id": "TASK-0001",
288
278
  "depends_on": [],
289
- "blocks": ["007-publish-npm-package"],
290
- "parallel_safe": ["005-command-anti-patterns"],
279
+ "blocks": ["TASK-0007"],
280
+ "parallel_safe": ["TASK-0005"],
291
281
  "progress": "0/18",
292
282
  "flags": "—"
293
283
  }
@@ -0,0 +1,73 @@
1
+ ---
2
+ name: task-close
3
+ description: Close out an abandoned task and its related UAT files — sets status trashed, moves them to archive/, and removes all active-index references
4
+ category: planning
5
+ model: claude-haiku-4-5-20251001
6
+ argument-hint: <path/to/task-file.md>
7
+ disable-model-invocation: false
8
+ user-invocable: true
9
+ ---
10
+ **Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/tasks/lifecycle.md`; run /primer if not done this session.
11
+
12
+ # Close Task
13
+
14
+ Move a task file (and any related UAT files) to `archive/`, then remove all active-index references. No files are ever deleted — archiving is the terminal action.
15
+
16
+ ---
17
+
18
+ **Task File**: $ARGUMENTS
19
+
20
+ ---
21
+
22
+ ## Instructions
23
+
24
+ ### Step 1: Resolve the Task File
25
+
26
+ Resolve the file per ~/.claude/skills/_shared/ID-RESOLUTION.md — family: tasks · scope: active+archive · ambiguous: interactive (list matches, ask the user to clarify) · empty: STOP and report the error
27
+
28
+ Then:
29
+
30
+ 1. Determine which directory the task currently lives in (`wiki/work/tasks/` or `wiki/work/tasks/archive/`)
31
+ 2. Extract the task's **number-slug identifier** (e.g., `TASK-0003-user-auth` from `TASK-0003-user-auth.md`)
32
+
33
+ ### Step 2: Find Related UAT Files
34
+
35
+ Using the task's number-slug identifier, search for matching UAT files:
36
+
37
+ 1. Check `wiki/work/uat/` for `<number>-<slug>.uat.md`
38
+ 2. Check `wiki/work/uat/archive/` for `<number>-<slug>.uat.md`
39
+ 3. Collect all matches — there may be zero, one, or multiple related UAT files
40
+
41
+ ### Step 3: Confirm with the User
42
+
43
+ Before moving anything, use `AskUserQuestion` to confirm. Show:
44
+
45
+ - **Task file** to be trashed: `$ARGUMENTS`
46
+ - **UAT file(s)** to be trashed (list each, or "None found")
47
+ - Ask: **"Archive these files as trashed? (Yes/No)"**
48
+
49
+ If the user says **No**, STOP.
50
+
51
+ ### Step 4: Archive the task and its UAT files
52
+
53
+ Read `~/.claude/skills/_shared/ARCHIVE-WORK-ITEM.md` now. Run its Procedure for the task (`family: tasks`, `terminal_status: trashed`, log op `task-trashed`), then once per related UAT file (`family: uat`, `terminal_status: trashed`, `log: skip`).
54
+
55
+ The task's log entry (the procedure's `log` input) is:
56
+
57
+ ```
58
+ ## [YYYY-MM-DD] task-trashed | TASK-NNNN <title> — archived to wiki/work/tasks/archive/
59
+ ```
60
+
61
+ **Do NOT remove references from roadmaps, decisions, or other files** — `[[TASK-NNNN]]` and `[[UAT-NNNN]]` IDs remain valid regardless of file location.
62
+
63
+ ### Step 5: Report Completion
64
+
65
+ Report what was done:
66
+
67
+ | Field | Value |
68
+ |-------|-------|
69
+ | Task file | `wiki/work/tasks/<file>.md` → `wiki/work/tasks/archive/<file>.md` |
70
+ | UAT file(s) | `wiki/work/uat/<file>.md` → `wiki/work/uat/archive/<file>.md` (or "None") |
71
+ | Active index rows removed | task index, UAT index (as applicable) |
72
+ | Archive index rows added | task archive index, UAT archive index (as applicable) |
73
+ | wiki/log.md entry | yes |
@@ -1,9 +1,9 @@
1
1
  ---
2
- name: task-add
2
+ name: task-create
3
3
  description: Create a structured, execution-ready task file in wiki/work/tasks/
4
4
  category: planning
5
5
  model: claude-sonnet-5
6
- argument-hint: <task description> [--decision DEC-NNNN#DM] [--roadmap ROADMAP-NNNN] [--knowledge <slug>]
6
+ argument-hint: <task description> [--decision ADR-NNNN#DM] [--roadmap ROADMAP-NNNN] [--knowledge <slug>]
7
7
  disable-model-invocation: false
8
8
  user-invocable: true
9
9
  ---
@@ -19,21 +19,21 @@ $ARGUMENTS
19
19
 
20
20
  Extract the core task objective, scope, and any specific requirements from `$ARGUMENTS`.
21
21
 
22
- ### Step 2: Parse and validate decision reference (only if `$ARGUMENTS` contains `--decision` or a `DEC-` token)
22
+ ### Step 2: Parse and validate decision reference (only if `$ARGUMENTS` contains `--decision`, an `ADR-` token, or a legacy `DEC-` token)
23
23
 
24
- Detect a decision reference in any of these forms:
25
- - `DEC-NNNN#DM` (e.g. `DEC-0007#D2`) — specific decision
24
+ Detect a decision reference in any of these forms (`ADR-` is the current prefix; legacy `DEC-` is accepted too — the number, not the prefix, selects the file):
25
+ - `ADR-NNNN#DM` (e.g. `ADR-0007#D2`) or legacy `DEC-NNNN#DM` (e.g. `DEC-0007#D2`) — specific decision
26
26
  - `NNNN#DM` (e.g. `0007#D2`) — specific decision
27
- - `--decision DEC-NNNN#DM` or `--decision NNNN#DM` — flag form
28
- - `DEC-NNNN` (no `#DM`) — **auto-detect** first accepted decision without a task
27
+ - `--decision ADR-NNNN#DM` (or legacy `--decision DEC-NNNN#DM`) or `--decision NNNN#DM` — flag form
28
+ - `ADR-NNNN` or legacy `DEC-NNNN` (no `#DM`) — **auto-detect** first accepted decision without a task
29
29
 
30
30
  Strip the decision token and any `--decision` flag from `$ARGUMENTS` to get the clean task description.
31
31
 
32
- Locate the decision file: use `mcp__serena__find_file` to find `NNNN-*.md` in `wiki/work/decisions/`.
32
+ Resolve the decision file per ~/.claude/skills/_shared/ID-RESOLUTION.md — family: decisions · scope: active · ambiguous: interactive · empty: n/a (the `#DM` suffix is split off and handed back per that doc).
33
33
 
34
- **If no `#DM` was given (auto-detect)**: walk `## D1.`, `## D2.`, … blocks in order; find the first where `status: accepted` and the `### Links` section has no `Source task(s):` line. If every accepted decision already has a task reference, STOP and tell the user. If no accepted decisions exist, STOP and tell the user to run `/decision-finalize` first.
34
+ **If no `#DM` was given (auto-detect)**: walk `## D1.`, `## D2.`, … blocks in order; find the first where `status: accepted` and the `### Links` section has no `Source task(s):` line. If every accepted decision already has a task reference, STOP and tell the user. If no accepted decisions exist, STOP and tell the user to run `/adr-finalize` first.
35
35
 
36
- **Refuse if the resolved decision is not `accepted`**: STOP and tell the user to run `/decision-finalize <file>#DM` first.
36
+ **Refuse if the resolved decision is not `accepted`**: STOP and tell the user to run `/adr-finalize <file>#DM` first.
37
37
 
38
38
  Store `(decision_file_path, decision_id, decision_anchor)` for later steps.
39
39
 
@@ -47,7 +47,7 @@ Detect:
47
47
 
48
48
  Strip the roadmap token from `$ARGUMENTS`.
49
49
 
50
- Locate: `mcp__serena__find_file` for `NNN-*.md` in `wiki/work/roadmaps/`. If not found, STOP and report.
50
+ Resolve the roadmap file per ~/.claude/skills/_shared/ID-RESOLUTION.md — family: roadmaps · scope: active · ambiguous: interactive · empty: n/a. If not found, STOP and report.
51
51
 
52
52
  Confirm the file has `status: active` in its frontmatter. If `status: done`, warn the user and ask whether to proceed.
53
53
 
@@ -73,11 +73,7 @@ If no knowledge reference: skip this step entirely.
73
73
 
74
74
  ### Step 4: Determine the next task number
75
75
 
76
- Scan **all** task locations to find the next available number:
77
- - `mcp__serena__list_dir` on `wiki/work/tasks/` and `wiki/work/tasks/archive/` (skip either that doesn't exist).
78
- - Collect every `TASK-<digits>` prefix from filenames across **both** directories. Take `max + 1`, zero-pad the result to 4 digits. In a brand-new project the first task is `TASK-0001`; in this repo, continue from the current max (do not restart at 1). Collect the numeric value from every `TASK-<digits>-` prefix regardless of digit count — existing tasks are 3-digit, new ones are 4-digit — ignoring leading zeros when comparing.
79
- - Also scan `wiki/work/tasks/index.md` for any reserved IDs not yet on disk.
80
- - Never re-use a number — IDs are immutable references, and archived tasks keep their original number forever (terminal tasks move to `archive/`; they don't stay in `wiki/work/tasks/`).
76
+ Allocate the next ID per `~/.claude/skills/_shared/SKILL-BOILERPLATE.md` § Number allocation (family: `wiki/work/tasks/`, prefix: `TASK-`, also scan `index.md` for reserved IDs).
81
77
 
82
78
  This number is a preview for planning; re-verify immediately before writing (Step 7a).
83
79
 
@@ -88,7 +84,9 @@ Review active tasks by listing `wiki/work/tasks/` and reading the index at `wiki
88
84
  - **blocks** it (must complete before that task can start)
89
85
  - **parallel_safe_with** it (can run concurrently without conflict)
90
86
 
91
- Present a compact table and confirm with the user via `AskUserQuestion` before proceeding.
87
+ Also read `wiki/work/bugs/index.md` and scan its active rows (status `open`/`triaged`/`in-progress`) for a bug whose title/summary plausibly matches the new task's objective (a judgment call — the same "plausible match" test `roadmap-next`'s inline-upgrade step applies to tasks). This scan is additive: the task-to-task dependency detection above is unchanged. A match is a candidate **origin bug** — the bug this task is being created to fix. Skip silently if `wiki/work/bugs/index.md` is missing or has no active rows.
88
+
89
+ Present a compact table and confirm with the user via `AskUserQuestion` before proceeding. When a candidate origin bug was found, add an "Origin bug" row (`BUG-NNNN` and its title) alongside the depends_on/blocks/parallel_safe_with rows so the user confirms or rejects the bug link in the same round-trip. Store the confirmed `BUG-NNNN` (or none) for Step 8.
92
90
 
93
91
  ### Step 6: Research and clarify approach
94
92
 
@@ -105,7 +103,7 @@ Confirm with the user via `AskUserQuestion`.
105
103
 
106
104
  ### Step 7a: Re-verify next task number — IMMEDIATELY before writing
107
105
 
108
- Re-run the scan from Step 4, collecting the numeric value from every `TASK-<digits>-` prefix regardless of digit count and zero-padding the result to 4 digits. If the number planned in Step 7 is now taken, silently bump to the new next-available number. **Never call `Write` before completing this re-scan.**
106
+ Repeat § Number allocation step 6 (same family and prefix as Step 4); never call `Write` before completing it.
109
107
 
110
108
  ### Step 8: Create the task file
111
109
 
@@ -123,19 +121,22 @@ updated: YYYY-MM-DD
123
121
  depends_on: []
124
122
  blocks: []
125
123
  parallel_safe_with: []
124
+ origin_bug: ""
126
125
  uat: ""
127
126
  tags: []
128
127
  ---
129
128
  ```
130
129
 
131
- Populate `depends_on`, `blocks`, and `parallel_safe_with` from Step 5 as lists of `TASK-NNNN` IDs (empty list if none).
130
+ Populate `depends_on`, `blocks`, and `parallel_safe_with` from Step 5 per the schema in `wiki/work/tasks/lifecycle.md` ("Dependency fields").
131
+
132
+ `origin_bug` is an optional, singular field (per `DEC-0001#D1`): set it to the `BUG-NNNN` ID the user confirmed as this task's origin in Step 5, or leave it `""` when no origin bug was confirmed. Do not write it as a list. The bug side's `linked_task` is not written here — that back-link is owned by `/bug-triage` and `/bug-close`.
132
133
 
133
134
  **Body structure**:
134
135
 
135
136
  ```markdown
136
137
  # TASK-NNNN — Task Title
137
138
 
138
- implements::[[DEC-NNNN#DM]] ← only when a decision reference was provided
139
+ implements::[[ADR-NNNN#DM]] ← only when a decision reference was provided (write the resolved file's own `id:` form — `ADR-` for new items, legacy `DEC-` until migrated)
139
140
  relates_to::[[<slug>]] ← only when Step 2b resolved a knowledge reference
140
141
  depends_on::[[TASK-NNNN]] ← one line per dependency from Step 5; omit entirely if none
141
142
  blocks::[[TASK-NNNN]] ← one line per blocked task from Step 5; omit entirely if none
@@ -164,11 +165,11 @@ blocks::[[TASK-NNNN]] ← one line per blocked task from Step 5; omit entirely
164
165
 
165
166
  Agent type annotations: valid types are `general-purpose`, `Explore`, `Plan`.
166
167
 
167
- **Decision link** (only when Step 2 found an accepted decision reference): Insert `implements::[[DEC-NNNN#DM]]` as a typed link on the line immediately after the H1, before `## Objective`.
168
+ **Decision link** (only when Step 2 found an accepted decision reference): Insert `implements::[[ADR-NNNN#DM]]` (legacy `DEC-NNNN#DM` when the resolved file's `id:` is still `DEC-`) as a typed link on the line immediately after the H1, before `## Objective`.
168
169
 
169
170
  **Knowledge link** (only when Step 2b resolved a knowledge reference): Insert `relates_to::[[<slug>]]` as a typed link in the same position — immediately after `implements::` when it's present, or immediately after the H1 when it isn't.
170
171
 
171
- **Dependency links** (from the Step 5 data, no re-derivation needed): insert one `depends_on::[[TASK-NNNN]]` line per dependency and one `blocks::[[TASK-NNNN]]` line per blocked task, in the same position — immediately after `implements::` when it's present, or immediately after the H1 when it isn't. *Aside: these typed-link lines are additive to the existing `> **Depends on**:`/`> **Blocks**:` blockquote format, not a replacement, and creating them here does not backfill any pre-existing task file.*
172
+ **Dependency links** (from the Step 5 data, no re-derivation needed): insert one `depends_on::[[TASK-NNNN]]` line per dependency and one `blocks::[[TASK-NNNN]]` line per blocked task, in the same position — immediately after `implements::` when it's present, or immediately after the H1 when it isn't. These lines are an optional graph-view mirror of the frontmatter arrays (see `wiki/work/tasks/lifecycle.md`, "Dependency fields"); creating them here does not backfill any pre-existing task file.
172
173
 
173
174
  ### Step 9: Update the family index
174
175
 
@@ -188,7 +189,7 @@ In the decision's `### Links` section, add or append a `Source task(s):` line:
188
189
  - Source task(s): [[TASK-NNNN]] — **WIP** (added YYYY-MM-DD)
189
190
  ```
190
191
 
191
- If no `### Links` section exists, create one before the closing `---` separator of that decision block. Use `Read` then `Edit` — never shell redirection.
192
+ If no `### Links` section exists, create one before the closing `---` separator of that decision block. Edit only — see `~/.claude/skills/_shared/SKILL-BOILERPLATE.md` § Edit hygiene.
192
193
 
193
194
  ### Step 11: Update the roadmap file (only when Step 3 found a roadmap reference)
194
195
 
@@ -223,7 +224,7 @@ Report:
223
224
 
224
225
  ```
225
226
  To implement: /tackle wiki/work/tasks/TASK-NNNN-slug.md
226
- To generate tests: /uat-generate TASK-NNNN
227
+ To generate tests: /uat-create TASK-NNNN
227
228
  ```
228
229
 
229
230
  If linked to a roadmap, mention which roadmap was updated and suggest: