@codewizard-dt/bootstrap 2.11.2 → 2.14.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +9 -9
- package/lib/README.md +1 -1
- package/lib/hooks/lib/serena.js +20 -6
- package/lib/prompts/migrate-wiki.md +2 -2
- package/lib/prompts/setup-strict-typechecks.md +18 -7
- package/lib/scripts/README.md +8 -8
- package/lib/scripts/bootstrap-serena.sh +8 -6
- package/lib/scripts/build-mcp-guide.sh +3 -3
- package/lib/scripts/install-mcps.sh +71 -28
- package/lib/scripts/lib.sh +35 -8
- package/lib/scripts/merge-gitignore.sh +102 -29
- package/lib/scripts/migrate-project.sh +9 -2
- package/lib/scripts/setup-deployment.sh +9 -0
- package/lib/scripts/sync-wiki-scaffold.sh +145 -24
- package/lib/scripts/templates/CLAUDE-wiki.md +6 -2
- package/lib/scripts/templates/guides/stubs/serena.md +7 -7
- package/lib/scripts/templates/wiki/conventions.md +2 -0
- package/lib/scripts/templates/wiki/index.md +6 -0
- package/lib/skills/bug-close/SKILL.md +1 -1
- package/lib/skills/bug-file/SKILL.md +2 -2
- package/lib/skills/bug-triage/SKILL.md +1 -1
- package/lib/skills/debug-logs/SKILL.md +2 -2
- package/lib/skills/decision-create/SKILL.md +1 -1
- package/lib/skills/decision-finalize/SKILL.md +1 -1
- package/lib/skills/decision-next/SKILL.md +1 -1
- package/lib/skills/decision-walkthrough/SKILL.md +1 -1
- package/lib/skills/demo/SKILL.md +1 -1
- package/lib/skills/eval-create/SKILL.md +7 -3
- package/lib/skills/eval-gap/SKILL.md +6 -2
- package/lib/skills/eval-run/SKILL.md +1 -1
- package/lib/skills/extract-feature/SKILL.md +1 -1
- package/lib/skills/gap-assess/SKILL.md +1 -1
- package/lib/skills/git-commit/SKILL.md +1 -1
- package/lib/skills/lint/SKILL.md +1 -1
- package/lib/skills/marp-slideshow/SKILL.md +1 -1
- package/lib/skills/mermaid-flowchart/SKILL.md +1 -1
- package/lib/skills/now/SKILL.md +1 -1
- package/lib/skills/port-feature/SKILL.md +1 -1
- package/lib/skills/power-mode/SKILL.md +1 -1
- package/lib/skills/primer/SKILL.md +2 -2
- package/lib/skills/project-readme/SKILL.md +1 -1
- package/lib/skills/req-create/SKILL.md +1 -1
- package/lib/skills/req-extract-decisions/SKILL.md +1 -1
- package/lib/skills/req-finalize/SKILL.md +1 -1
- package/lib/skills/req-retire/SKILL.md +2 -2
- package/lib/skills/req-update/SKILL.md +1 -1
- package/lib/skills/research/SKILL.md +1 -1
- package/lib/skills/roadmap-add/SKILL.md +2 -2
- package/lib/skills/roadmap-create/SKILL.md +3 -3
- package/lib/skills/roadmap-next/SKILL.md +1 -1
- package/lib/skills/serena-config/SKILL.md +1 -1
- package/lib/skills/simplify/SKILL.md +1 -1
- package/lib/skills/tackle/SKILL.md +3 -3
- package/lib/skills/task-add/SKILL.md +1 -1
- package/lib/skills/task-audit/SKILL.md +2 -2
- package/lib/skills/task-trash/SKILL.md +1 -1
- package/lib/skills/task-update/SKILL.md +2 -2
- package/lib/skills/uat-auto/SKILL.md +1 -1
- package/lib/skills/uat-auto-plus/SKILL.md +1 -1
- package/lib/skills/uat-generate/SKILL.md +1 -1
- package/lib/skills/uat-skip/SKILL.md +1 -1
- package/lib/skills/uat-walk/SKILL.md +1 -1
- package/lib/skills/uat-walk/UAT-CORE.md +1 -1
- package/lib/skills/update-docs/SKILL.md +2 -2
- package/lib/skills/wiki-ingest/SKILL.md +1 -1
- package/lib/skills/wiki-lint/SKILL.md +1 -1
- package/lib/skills/wiki-query/SKILL.md +1 -1
- package/package.json +1 -1
- package/raw/guides/type-checking-templates/README.md +7 -7
- package/raw/guides/type-checking-templates/eslint/eslint.config.ts +1 -1
- package/raw/research/mcp-add-scope-writes/index.md +46 -0
- package/raw/research/mcp-add-scope-writes/sources.md +38 -0
- package/raw/research/mcp-scope-conflict-handling/index.md +61 -0
- package/raw/research/mcp-scope-conflict-handling/sources.md +32 -0
- package/.github/workflows/build.yml +0 -88
- package/raw/guides/mcp-tools.md +0 -335
- package/raw/guides/task-spec.md +0 -79
|
@@ -8,7 +8,7 @@ argument-hint: "[stage: golden|scenarios|replay|rubric] [description of the eval
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`.
|
|
12
12
|
|
|
13
13
|
$ARGUMENTS
|
|
14
14
|
|
|
@@ -36,7 +36,7 @@ Parse `$ARGUMENTS` immediately. The argument string can take several forms:
|
|
|
36
36
|
**Direct mode** (any non-empty argument that is not a bare stage keyword):
|
|
37
37
|
|
|
38
38
|
1. Acknowledge the request: "Creating a golden set eval for: `<extracted description>`"
|
|
39
|
-
2. Read
|
|
39
|
+
2. Read `wiki/guides/evals-framework.md` (always required — if missing, stop and tell the user to re-run `npx @codewizard-dt/bootstrap update` and opt in to `evals-framework.md`, as in Step 1)
|
|
40
40
|
3. Survey `evals/golden/` to find the next ID and check bootstrap vs gap-fill state
|
|
41
41
|
4. Go directly to **Step 4-Direct** — skip Steps 1–3
|
|
42
42
|
|
|
@@ -48,7 +48,11 @@ Parse `$ARGUMENTS` immediately. The argument string can take several forms:
|
|
|
48
48
|
|
|
49
49
|
## Step 1: Read the framework
|
|
50
50
|
|
|
51
|
-
Read
|
|
51
|
+
Read `wiki/guides/evals-framework.md` in full. This is authoritative for stage definitions, schemas, check types, and anti-patterns. Do not proceed until you have read it.
|
|
52
|
+
|
|
53
|
+
If the file does not exist, STOP — do not proceed from memory. Tell the user:
|
|
54
|
+
|
|
55
|
+
> This project doesn't have the evals framework guide installed. Run `npx @codewizard-dt/bootstrap update` and answer **yes** when prompted to install the optional guide `evals-framework.md`, then re-run this skill.
|
|
52
56
|
|
|
53
57
|
---
|
|
54
58
|
|
|
@@ -8,7 +8,7 @@ argument-hint: [optional: stage — golden | scenarios | replay | rubric | all]
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`.
|
|
12
12
|
|
|
13
13
|
$ARGUMENTS
|
|
14
14
|
|
|
@@ -24,7 +24,11 @@ Read-only audit of the project's eval suite. Produces a prioritised gap report a
|
|
|
24
24
|
|
|
25
25
|
## Step 1: Read the framework
|
|
26
26
|
|
|
27
|
-
Read
|
|
27
|
+
Read `wiki/guides/evals-framework.md`. This defines the expected shape of each stage and is required context for meaningful gap analysis.
|
|
28
|
+
|
|
29
|
+
If the file does not exist, STOP — do not proceed from memory. Tell the user:
|
|
30
|
+
|
|
31
|
+
> This project doesn't have the evals framework guide installed. Run `npx @codewizard-dt/bootstrap update` and answer **yes** when prompted to install the optional guide `evals-framework.md`, then re-run this skill.
|
|
28
32
|
|
|
29
33
|
---
|
|
30
34
|
|
|
@@ -8,7 +8,7 @@ argument-hint: <feature name or description>
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
12
|
|
|
13
13
|
# Extract Feature
|
|
14
14
|
|
|
@@ -8,7 +8,7 @@ argument-hint: <expected functionality — inline description or path to a requi
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
12
|
|
|
13
13
|
# Gap Assess
|
|
14
14
|
|
package/lib/skills/lint/SKILL.md
CHANGED
|
@@ -7,7 +7,7 @@ argument-hint: <path to source file> [optional output path]
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# Marp Slideshow
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <path to source file> [optional output path]
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# Mermaid Flowchart
|
|
13
13
|
|
package/lib/skills/now/SKILL.md
CHANGED
|
@@ -8,7 +8,7 @@ argument-hint: <task description>
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
12
|
|
|
13
13
|
$ARGUMENTS
|
|
14
14
|
|
|
@@ -8,7 +8,7 @@ argument-hint: <absolute-path-to-source-project> <functionality description>
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
12
|
|
|
13
13
|
# Port Feature
|
|
14
14
|
|
|
@@ -46,7 +46,7 @@ Inspect the path argument:
|
|
|
46
46
|
Every agent spawned in power-mode MUST include `mode: "bypassPermissions"` and the following footer appended to its prompt:
|
|
47
47
|
|
|
48
48
|
```
|
|
49
|
-
IMPORTANT: Follow
|
|
49
|
+
IMPORTANT: Follow wiki/guides/mcp-tools.md for all file and code operations. Use Serena (mcp__serena__*) for ALL file/directory exploration and ALL code editing. Never use ls, cat, find, grep, sed, awk, or any shell command to inspect or modify files. Use Read/Edit/Write only for markdown and config files.
|
|
50
50
|
|
|
51
51
|
IMPORTANT: If at any point you are not 100% sure how to fix an issue or which implementation strategy to use, invoke /research first and act on its recommendation before proceeding.
|
|
52
52
|
```
|
|
@@ -6,7 +6,7 @@ model: claude-haiku-4-5-20251001
|
|
|
6
6
|
disable-model-invocation: false
|
|
7
7
|
user-invocable: true
|
|
8
8
|
---
|
|
9
|
-
**Prereqs:** obey
|
|
9
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`.
|
|
10
10
|
|
|
11
11
|
# MANDATORY REQUIREMENTS
|
|
12
12
|
|
|
@@ -69,7 +69,7 @@ Keep memories current and useful for future conversations:
|
|
|
69
69
|
3. **Rename disorganized memories**: Use `mcp__serena__rename_memory` to move memories into proper topic hierarchies
|
|
70
70
|
4. **Do NOT write memories for**: information already in code comments or docs, temporary state, easily re-derivable facts
|
|
71
71
|
|
|
72
|
-
See
|
|
72
|
+
See `wiki/guides/mcp-tools.md` for the complete Serena memory reference.
|
|
73
73
|
|
|
74
74
|
---
|
|
75
75
|
|
|
@@ -7,7 +7,7 @@ argument-hint: "[path to project directory (defaults to cwd)] [custom instructio
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`.
|
|
11
11
|
|
|
12
12
|
Generate (or update) a **project README** structured for optimal AI parsing and portfolio presentation. The strict section format is machine-readable by AI tools that extract project metadata (name, description, architecture, technologies, use cases, skills).
|
|
13
13
|
|
|
@@ -8,7 +8,7 @@ argument-hint: <feature description, problem statement, or product initiative ti
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
12
|
**Check `wiki/work/requirements/lifecycle.md`** for the REQ template, status lifecycle, required-non-empty fields, and anti-patterns this skill enforces; **`wiki/work/requirements/index.md`** for the index row format.
|
|
13
13
|
|
|
14
14
|
# Create Requirement
|
|
@@ -8,7 +8,7 @@ argument-hint: <path/to/req.md, NNN-slug, or NNN>
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
12
|
|
|
13
13
|
|
|
14
14
|
# Requirement to Decisions
|
|
@@ -8,7 +8,7 @@ argument-hint: <path/to/req.md, NNN-slug, or NNN>
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
12
|
|
|
13
13
|
|
|
14
14
|
# Finalize Requirement
|
|
@@ -7,7 +7,7 @@ argument-hint: <wiki/work/requirements/REQ-NNN-slug.md, NNN-slug, or NNN> [reaso
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
**Read `wiki/work/requirements/lifecycle.md` first** — it defines the requirement lifecycle, terminal states, and the archive rule.
|
|
12
12
|
|
|
13
13
|
# Retire Requirement
|
|
@@ -179,7 +179,7 @@ Print a tabular summary:
|
|
|
179
179
|
2. **Never auto-cascade** to linked decisions or tasks. Surface them as suggestions only.
|
|
180
180
|
3. **Confirm with the user before any edits** — `AskUserQuestion` is mandatory in Step 3.
|
|
181
181
|
4. **Retirement reason is required** — refuse to retire without a documented reason.
|
|
182
|
-
5. **Never use `sed` / `awk` / `echo >>` / `cat <<EOF`** — always `Edit`. `Bash` is permitted only for `git mv`. See
|
|
182
|
+
5. **Never use `sed` / `awk` / `echo >>` / `cat <<EOF`** — always `Edit`. `Bash` is permitted only for `git mv`. See `wiki/guides/mcp-tools.md`.
|
|
183
183
|
6. **Refuse if already retired or superseded** — these are terminal states; running again is a no-op, not an error.
|
|
184
184
|
7. Maximum 3 sub-processes at a time if delegating any step.
|
|
185
185
|
8. Always terminate background processes when done.
|
|
@@ -7,7 +7,7 @@ argument-hint: <path/to/req.md, NNN-slug, or NNN> [optional change description]
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# Update Requirement
|
|
13
13
|
|
|
@@ -8,7 +8,7 @@ argument-hint: <topic or question to research>
|
|
|
8
8
|
disable-model-invocation: false
|
|
9
9
|
user-invocable: true
|
|
10
10
|
---
|
|
11
|
-
**Prereqs:** obey
|
|
11
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
12
12
|
|
|
13
13
|
# Research
|
|
14
14
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <ROADMAP-NNN> [--phase "<name>"] [--task NNN | <task path> | <inl
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
$ARGUMENTS
|
|
13
13
|
|
|
@@ -217,7 +217,7 @@ If the added item is an inline placeholder, append this note after the table:
|
|
|
217
217
|
|
|
218
218
|
| Anti-Pattern | Remedy |
|
|
219
219
|
|--------------|--------|
|
|
220
|
-
| Editing the roadmap with `sed`, `awk`, `echo >>`, or `cat <<EOF` | **Never.** Always use `Read` + `Edit`. See
|
|
220
|
+
| Editing the roadmap with `sed`, `awk`, `echo >>`, or `cat <<EOF` | **Never.** Always use `Read` + `Edit`. See `wiki/guides/mcp-tools.md` |
|
|
221
221
|
| Using `Write` to rewrite the whole roadmap file | Use surgical `Edit` calls only |
|
|
222
222
|
| Inventing a task title when the task file is missing | Ask via `AskUserQuestion` whether to fall back to inline, or cancel |
|
|
223
223
|
| Bumping the `Progress` numerator | This skill **never** touches the numerator — that is auto-checkoff's job (`/tackle`, `/uat-walk`, `/uat-auto`, `/uat-auto-plus`, `/uat-skip`) |
|
|
@@ -7,7 +7,7 @@ argument-hint: <initiative/goal description>
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
**Read `wiki/work/roadmaps/lifecycle.md` first — it is authoritative for the roadmap frontmatter schema, status lifecycle, and ID/filename rules. The file template, item-format rules, index format, and anti-patterns are specified inline in this skill below.**
|
|
12
12
|
**Run `/research <topic>` on the roadmap topic BEFORE any Q&A or file creation. Do not skip this step.**
|
|
13
13
|
|
|
@@ -168,7 +168,7 @@ Edit `wiki/work/roadmaps/index.md` to add a new bullet line (active items only
|
|
|
168
168
|
|
|
169
169
|
where `<title>` is the roadmap's H1 sub-title (without any `Roadmap NNN:` prefix), `<one-line summary>` is a short description of the goal, and `<total>` is the count of `- [ ]` checkboxes you just wrote across all phases.
|
|
170
170
|
|
|
171
|
-
Use `Edit` (not `sed`, `awk`, `echo >>`, or any shell redirection). See
|
|
171
|
+
Use `Edit` (not `sed`, `awk`, `echo >>`, or any shell redirection). See `wiki/guides/mcp-tools.md`.
|
|
172
172
|
|
|
173
173
|
### Step 8: Refresh the hot cache
|
|
174
174
|
|
|
@@ -217,7 +217,7 @@ This is informational only — no action required now.
|
|
|
217
217
|
|
|
218
218
|
1. **Refuse to write the file if any required field is empty or fails its quality bar** (Goal, Owner, ≥1 phase with ≥1 item). Loop back to Step 3 — do not silently fill gaps with invented content.
|
|
219
219
|
2. **Never invent task links.** Every `[[TASK-NNN: ...]]` wiki link must correspond to a real file under `wiki/work/tasks/`. Verify with `mcp__serena__find_file` before rendering.
|
|
220
|
-
3. **Never use `sed`, `awk`, `echo >>`, or shell redirection to edit markdown.** Always `Read` then `Edit`. See
|
|
220
|
+
3. **Never use `sed`, `awk`, `echo >>`, or shell redirection to edit markdown.** Always `Read` then `Edit`. See `wiki/guides/mcp-tools.md`.
|
|
221
221
|
4. **Never auto-create downstream artifacts.** This skill creates exactly one roadmap file (plus the index row edit). Do **not** create tasks, PRDs, or ADRs as a side effect — the user can file tasks afterward via `/task-add --roadmap ROADMAP-NNN`.
|
|
222
222
|
5. **Redirect step-level detail to task territory** — if the user starts specifying *how* under an item, restate the question as "what's the single checkable unit?" and re-elicit.
|
|
223
223
|
6. **Status starts as `active` and stays there.** This skill never writes `done`. The flip from `active` → `done` is a manual decision the human makes when every box is `[x]`. After flipping, the file may be moved to `wiki/work/roadmaps/archive/` — `/roadmap-next` will suggest this step.
|
|
@@ -7,7 +7,7 @@ argument-hint: "[path to roadmap file, NNN-slug, or number] (optional)"
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# Next Step
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: "[relative_path]"
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
**Purpose**: Analyze files or directories to remove redundant information and simplify overly complex structures.
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <path/to/task.md, number-slug, or description>
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/tasks/lifecycle.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# Tackle Outline
|
|
13
13
|
|
|
@@ -73,9 +73,9 @@ Every delegated sub-agent **MUST** use Serena, non-negotiable:
|
|
|
73
73
|
| Find files / dirs | `find_file`, `list_dir` | `Glob`, `find`, `ls`, `cat` |
|
|
74
74
|
| Library docs | Context7 | `WebSearch`/`WebFetch` |
|
|
75
75
|
|
|
76
|
-
Standard Read/Edit/Write are allowed for markdown and config (JSON, YAML, `.env`) only. **Every** sub-agent prompt must include: *"Use Serena for all code exploration/editing and all file/directory exploration. Standard Read/Edit/Write for markdown and config only. Never bash `ls`/`cat`/`find`/`grep`/`sed`. See
|
|
76
|
+
Standard Read/Edit/Write are allowed for markdown and config (JSON, YAML, `.env`) only. **Every** sub-agent prompt must include: *"Use Serena for all code exploration/editing and all file/directory exploration. Standard Read/Edit/Write for markdown and config only. Never bash `ls`/`cat`/`find`/`grep`/`sed`. See `wiki/guides/mcp-tools.md`."*
|
|
77
77
|
|
|
78
|
-
**Verification scope: static gates only** (`bash -n`, typecheck, lint, unit tests). Runtime/E2E is the UAT phase's job — see
|
|
78
|
+
**Verification scope: static gates only** (`bash -n`, typecheck, lint, unit tests). Runtime/E2E is the UAT phase's job — see `wiki/guides/command-anti-patterns.md#verification-belongs-to-the-right-phase`.
|
|
79
79
|
|
|
80
80
|
---
|
|
81
81
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <task description> [--decision DEC-NNNN#DM] [--roadmap ROADMAP-NN
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
$ARGUMENTS
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: [--json]
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/tasks/lifecycle.md`.
|
|
11
11
|
|
|
12
12
|
# Task Audit
|
|
13
13
|
|
|
@@ -189,7 +189,7 @@ Report what Step 2 discovered and changed:
|
|
|
189
189
|
### Auto-Completed Steps
|
|
190
190
|
| Task | Step | Evidence |
|
|
191
191
|
|------|------|----------|
|
|
192
|
-
| 005-command-anti-patterns | "Add mcp-tools.md guide" | File found at
|
|
192
|
+
| 005-command-anti-patterns | "Add mcp-tools.md guide" | File found at wiki/guides/mcp-tools.md |
|
|
193
193
|
|
|
194
194
|
### Fully-Completed Tasks Moved
|
|
195
195
|
| Task | Action |
|
|
@@ -7,7 +7,7 @@ argument-hint: <path/to/task-file.md>
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/tasks/lifecycle.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# Trash Task
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <path/to/task.md, number-slug, or number> [optional instructions]
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/tasks/lifecycle.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# Update Task
|
|
13
13
|
|
|
@@ -121,7 +121,7 @@ When adding specificity to vague steps, follow the `/research` workflow (see `li
|
|
|
121
121
|
### Present changes before applying
|
|
122
122
|
Before writing the updated task file, present a summary of proposed changes and ask the user to confirm using `AskUserQuestion`.
|
|
123
123
|
|
|
124
|
-
After confirmation, update the task file using the **`Edit`** tool (or `Write` for a full rewrite). **Never** use `sed`, `awk`, `perl -i`, or `echo >>` — call `Edit` once per change, even if there are many. See
|
|
124
|
+
After confirmation, update the task file using the **`Edit`** tool (or `Write` for a full rewrite). **Never** use `sed`, `awk`, `perl -i`, or `echo >>` — call `Edit` once per change, even if there are many. See `wiki/guides/mcp-tools.md` "Common anti-patterns".
|
|
125
125
|
|
|
126
126
|
---
|
|
127
127
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <path/to/uat-file.md, number-slug, or description>
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/uat/lifecycle.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
Read `~/.claude/skills/uat-walk/UAT-CORE.md` now — it defines Steps 1–5 (resolution, prerequisites, classification, judging, closure). This file defines only what differs for **headless, fail-closed** mode.
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <path/to/uat-file.md, number-slug, or description>
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/uat/lifecycle.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
Read `~/.claude/skills/uat-walk/UAT-CORE.md` now — it defines Steps 1–5 (resolution, prerequisites, classification, judging, closure). This file defines only what differs for **autonomous-fix** mode.
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <TASK-NNN | path/to/task-file.md | feature description>
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# UAT Generator
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <TASK-NNN or path/to/task-file.md>
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
# UAT Skip
|
|
13
13
|
|
|
@@ -7,7 +7,7 @@ argument-hint: <path/to/uat-file.md, number-slug, or description>
|
|
|
7
7
|
disable-model-invocation: false
|
|
8
8
|
user-invocable: true
|
|
9
9
|
---
|
|
10
|
-
**Prereqs:** obey
|
|
10
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/uat/lifecycle.md`; run /primer if not done this session.
|
|
11
11
|
|
|
12
12
|
Read `~/.claude/skills/uat-walk/UAT-CORE.md` now — it defines Steps 1–5 (resolution, prerequisites, classification, judging, closure). This file defines only what differs for **interactive** mode.
|
|
13
13
|
|
|
@@ -105,7 +105,7 @@ Forbidden (each triggers an approval prompt and obscures output): multiple `curl
|
|
|
105
105
|
|
|
106
106
|
## Step 5 — Update the file per verdict
|
|
107
107
|
|
|
108
|
-
Use the **`Edit`** tool — **one `Edit` call per status line**, even when many flip in a row. **Never** `sed`, `awk`, `perl -i`, or `echo` to flip a marker (each triggers an approval prompt; see
|
|
108
|
+
Use the **`Edit`** tool — **one `Edit` call per status line**, even when many flip in a row. **Never** `sed`, `awk`, `perl -i`, or `echo` to flip a marker (each triggers an approval prompt; see `wiki/guides/mcp-tools.md` "Common anti-patterns"). Replace only the status line with the appropriate marker + `<!-- YYYY-MM-DD -->`. Do not modify any other part of the test block — preserve all metadata, headings, and whitespace exactly.
|
|
109
109
|
|
|
110
110
|
---
|
|
111
111
|
|
|
@@ -6,7 +6,7 @@ model: claude-sonnet-5
|
|
|
6
6
|
disable-model-invocation: false
|
|
7
7
|
user-invocable: true
|
|
8
8
|
---
|
|
9
|
-
**Prereqs:** obey
|
|
9
|
+
**Prereqs:** obey `wiki/guides/mcp-tools.md` + `wiki/work/tasks/lifecycle.md`.
|
|
10
10
|
|
|
11
11
|
# Update Documentation
|
|
12
12
|
|
|
@@ -26,7 +26,7 @@ In scope:
|
|
|
26
26
|
Out of scope (do NOT touch):
|
|
27
27
|
- **Serena memories — NEVER call `mcp__serena__write_memory` or `mcp__serena__edit_memory` here, for any reason.**
|
|
28
28
|
- ADR or PRD files
|
|
29
|
-
-
|
|
29
|
+
- `wiki/guides/` files
|
|
30
30
|
- Any doc unrelated to the changes in this session
|
|
31
31
|
|
|
32
32
|
---
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@codewizard-dt/bootstrap",
|
|
3
|
-
"version": "2.
|
|
3
|
+
"version": "2.14.0",
|
|
4
4
|
"description": "Bootstrap Claude Code projects with an LLM Wiki, reusable skills, hooks, and MCP setup",
|
|
5
5
|
"homepage": "https://github.com/codewizard-dt/bootstrap-wiki#readme",
|
|
6
6
|
"bugs": {
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Type-Checking & Linting Config Templates
|
|
2
2
|
|
|
3
|
-
Best-practice templates synthesized from analysis of
|
|
3
|
+
Best-practice templates synthesized from analysis of real-world project configs. Each template includes inline annotations explaining every non-obvious decision.
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
@@ -79,9 +79,9 @@ Run basedpyright alongside mypy with `typeCheckingMode = "off"` — opt in only
|
|
|
79
79
|
|
|
80
80
|
**Anti-patterns observed in the wild:**
|
|
81
81
|
- `ignore_errors = true` on internal modules — silences real type errors, not just stub gaps
|
|
82
|
-
-
|
|
82
|
+
- Manually approximating strict mode with individual flags instead of `strict = true` — always leaves gaps
|
|
83
83
|
- Missing `[tool.ruff.lint.isort]` `known-first-party` — isort can't distinguish first-party vs third-party without it
|
|
84
|
-
-
|
|
84
|
+
- Skipping the `pydantic.mypy` plugin in a Pydantic-heavy project
|
|
85
85
|
|
|
86
86
|
---
|
|
87
87
|
|
|
@@ -95,9 +95,9 @@ Run basedpyright alongside mypy with `typeCheckingMode = "off"` — opt in only
|
|
|
95
95
|
- Let the TypeScript parser handle `ecmaVersion`; do not hard-code it
|
|
96
96
|
|
|
97
97
|
**Anti-patterns observed in the wild:**
|
|
98
|
-
-
|
|
99
|
-
-
|
|
100
|
-
- `
|
|
98
|
+
- Missing `parserOptions.projectService` — all type-aware lint rules silently disabled
|
|
99
|
+
- Using a `FlatCompat` bridge for jest — use `jest.configs['flat/recommended']` instead
|
|
100
|
+
- `no-undef`, `no-unused-vars`, `no-redeclare` downgraded to `"warn"` — silent tech debt
|
|
101
101
|
|
|
102
102
|
---
|
|
103
103
|
|
|
@@ -108,5 +108,5 @@ Run basedpyright alongside mypy with `typeCheckingMode = "off"` — opt in only
|
|
|
108
108
|
- `"standard"` is a safe project-wide floor; use per-file suppressions for legacy code
|
|
109
109
|
|
|
110
110
|
**Anti-patterns observed in the wild:**
|
|
111
|
-
-
|
|
111
|
+
- Omitting `typeCheckingMode` entirely — Pyright defaults to `"off"` and does nothing
|
|
112
112
|
- `reportMissingImports: "warning"` — broken imports should always be errors
|
|
@@ -32,7 +32,7 @@ export default defineConfig([
|
|
|
32
32
|
js.configs.recommended,
|
|
33
33
|
// strictTypeChecked = recommended + strict + ALL type-aware lint rules.
|
|
34
34
|
// Requires parserOptions.projectService below — without it, type-aware
|
|
35
|
-
// rules are silently disabled
|
|
35
|
+
// rules are silently disabled — the most common gap seen in real configs.
|
|
36
36
|
tseslint.configs.strictTypeChecked,
|
|
37
37
|
// stylisticTypeChecked adds formatting-adjacent TS rules (optional)
|
|
38
38
|
tseslint.configs.stylisticTypeChecked,
|