@codewizard-dt/bootstrap 2.10.0
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/.github/workflows/build.yml +88 -0
- package/.github/workflows/security.yml +24 -0
- package/.gitleaks.toml +15 -0
- package/README.md +472 -0
- package/bin/cli.js +47 -0
- package/lib/README.md +27 -0
- package/lib/hooks/README.md +316 -0
- package/lib/hooks/env-file-guard.js +45 -0
- package/lib/hooks/git-protected-ops-block.js +77 -0
- package/lib/hooks/lib/serena-languages.js +158 -0
- package/lib/hooks/lib/serena.js +787 -0
- package/lib/hooks/mv-absolute-path-block.js +53 -0
- package/lib/hooks/serena-bash-grep-block.js +501 -0
- package/lib/hooks/serena-edit-guard.js +74 -0
- package/lib/hooks/serena-first-glob-guard.js +94 -0
- package/lib/hooks/serena-first-guard.js +74 -0
- package/lib/hooks/serena-first-read-guard.js +167 -0
- package/lib/hooks/serena-pre-delegation.js +117 -0
- package/lib/hooks/serena-session-reset.js +45 -0
- package/lib/hooks/serena-usage-tracker.js +186 -0
- package/lib/hooks/serena-write-guard.js +58 -0
- package/lib/prompts/README.md +16 -0
- package/lib/prompts/migrate-wiki.md +111 -0
- package/lib/prompts/setup-deployment.md +322 -0
- package/lib/prompts/setup-design-system.md +162 -0
- package/lib/prompts/setup-strict-typechecks.md +139 -0
- package/lib/scripts/README.md +49 -0
- package/lib/scripts/bootstrap-serena.sh +145 -0
- package/lib/scripts/build-mcp-guide.sh +108 -0
- package/lib/scripts/install-global.sh +78 -0
- package/lib/scripts/install-mcps.sh +131 -0
- package/lib/scripts/lib.sh +154 -0
- package/lib/scripts/merge-gitignore.sh +65 -0
- package/lib/scripts/migrate-project.sh +273 -0
- package/lib/scripts/setup-deployment.sh +104 -0
- package/lib/scripts/setup-project.sh +55 -0
- package/lib/scripts/setup-runner.sh +99 -0
- package/lib/scripts/setup-strict-typechecks.sh +29 -0
- package/lib/scripts/startup.sh +42 -0
- package/lib/scripts/sync-wiki-scaffold.sh +104 -0
- package/lib/scripts/templates/CLAUDE-env-safety.md +3 -0
- package/lib/scripts/templates/CLAUDE-wiki.md +60 -0
- package/lib/scripts/templates/gitignore +136 -0
- package/lib/scripts/templates/guides/stubs/00-header.md +15 -0
- package/lib/scripts/templates/guides/stubs/brave-search.md +20 -0
- package/lib/scripts/templates/guides/stubs/context7.md +26 -0
- package/lib/scripts/templates/guides/stubs/playwright.md +26 -0
- package/lib/scripts/templates/guides/stubs/serena.md +219 -0
- package/lib/scripts/templates/wiki/conventions.md +100 -0
- package/lib/scripts/templates/wiki/dashboard.html +1733 -0
- package/lib/scripts/templates/wiki/hot.md +21 -0
- package/lib/scripts/templates/wiki/index.md +46 -0
- package/lib/scripts/templates/wiki/knowledge/concepts/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/components/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/organisations/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/people/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/tools/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/sources/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/log.md +14 -0
- package/lib/scripts/templates/wiki/work/bugs/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/bugs/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/bugs/index.md +12 -0
- package/lib/scripts/templates/wiki/work/bugs/lifecycle.md +39 -0
- package/lib/scripts/templates/wiki/work/decisions/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/decisions/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/decisions/index.md +12 -0
- package/lib/scripts/templates/wiki/work/decisions/lifecycle.md +42 -0
- package/lib/scripts/templates/wiki/work/requirements/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/requirements/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/requirements/index.md +12 -0
- package/lib/scripts/templates/wiki/work/requirements/lifecycle.md +34 -0
- package/lib/scripts/templates/wiki/work/roadmaps/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/roadmaps/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/roadmaps/index.md +12 -0
- package/lib/scripts/templates/wiki/work/roadmaps/lifecycle.md +32 -0
- package/lib/scripts/templates/wiki/work/tasks/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/tasks/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/tasks/index.md +12 -0
- package/lib/scripts/templates/wiki/work/tasks/lifecycle.md +39 -0
- package/lib/scripts/templates/wiki/work/uat/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/uat/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/uat/index.md +12 -0
- package/lib/scripts/templates/wiki/work/uat/lifecycle.md +48 -0
- package/lib/scripts/templates/wiki/work/uat/screenshots/.gitkeep +0 -0
- package/lib/scripts/update-project.sh +75 -0
- package/lib/scripts/wiki-dashboard-server.js +146 -0
- package/lib/skills/README.md +146 -0
- package/lib/skills/anti-slop/SKILL.md +183 -0
- package/lib/skills/bug-close/SKILL.md +136 -0
- package/lib/skills/bug-file/SKILL.md +114 -0
- package/lib/skills/bug-triage/SKILL.md +140 -0
- package/lib/skills/company-align/SKILL.md +203 -0
- package/lib/skills/debug-logs/SKILL.md +129 -0
- package/lib/skills/decision-create/SKILL.md +220 -0
- package/lib/skills/decision-finalize/SKILL.md +181 -0
- package/lib/skills/decision-next/SKILL.md +129 -0
- package/lib/skills/decision-walkthrough/SKILL.md +169 -0
- package/lib/skills/demo/SKILL.md +183 -0
- package/lib/skills/elevator-pitch/SKILL.md +125 -0
- package/lib/skills/eval-create/SKILL.md +344 -0
- package/lib/skills/eval-gap/SKILL.md +150 -0
- package/lib/skills/eval-run/SKILL.md +214 -0
- package/lib/skills/extract-feature/SKILL.md +344 -0
- package/lib/skills/flashcard/SKILL.md +513 -0
- package/lib/skills/frontend-taste/SKILL.md +184 -0
- package/lib/skills/gap-assess/SKILL.md +97 -0
- package/lib/skills/git-commit/SKILL.md +164 -0
- package/lib/skills/lint/SKILL.md +99 -0
- package/lib/skills/marp-slideshow/SKILL.md +212 -0
- package/lib/skills/mermaid-flowchart/SKILL.md +194 -0
- package/lib/skills/now/SKILL.md +36 -0
- package/lib/skills/port-feature/SKILL.md +315 -0
- package/lib/skills/power-mode/SKILL.md +184 -0
- package/lib/skills/primer/SKILL.md +84 -0
- package/lib/skills/project-readme/SKILL.md +166 -0
- package/lib/skills/req-compile/SKILL.md +131 -0
- package/lib/skills/req-create/SKILL.md +124 -0
- package/lib/skills/req-extract-decisions/SKILL.md +241 -0
- package/lib/skills/req-finalize/SKILL.md +251 -0
- package/lib/skills/req-retire/SKILL.md +185 -0
- package/lib/skills/req-update/SKILL.md +265 -0
- package/lib/skills/research/SKILL.md +250 -0
- package/lib/skills/research-company/SKILL.md +345 -0
- package/lib/skills/roadmap-add/SKILL.md +238 -0
- package/lib/skills/roadmap-create/SKILL.md +223 -0
- package/lib/skills/roadmap-next/SKILL.md +132 -0
- package/lib/skills/security-audit/SKILL.md +246 -0
- package/lib/skills/serena-config/SKILL.md +92 -0
- package/lib/skills/simplify/SKILL.md +227 -0
- package/lib/skills/tackle/SKILL.md +156 -0
- package/lib/skills/task-add/SKILL.md +208 -0
- package/lib/skills/task-audit/SKILL.md +294 -0
- package/lib/skills/task-trash/SKILL.md +115 -0
- package/lib/skills/task-update/SKILL.md +136 -0
- package/lib/skills/uat-auto/SKILL.md +69 -0
- package/lib/skills/uat-auto-plus/SKILL.md +115 -0
- package/lib/skills/uat-generate/SKILL.md +289 -0
- package/lib/skills/uat-skip/SKILL.md +169 -0
- package/lib/skills/uat-walk/SKILL.md +164 -0
- package/lib/skills/uat-walk/UAT-CORE.md +140 -0
- package/lib/skills/update-docs/SKILL.md +75 -0
- package/lib/skills/wiki-archive/SKILL.md +96 -0
- package/lib/skills/wiki-ingest/SKILL.md +139 -0
- package/lib/skills/wiki-lint/SKILL.md +131 -0
- package/lib/skills/wiki-query/SKILL.md +71 -0
- package/lib/skills/wiki-rotate-log/SKILL.md +90 -0
- package/lib/skills/wiki-tidy/SKILL.md +107 -0
- package/package.json +32 -0
- package/raw/.gitkeep +0 -0
- package/raw/design-principles.md +65 -0
- package/raw/guides/command-anti-patterns.md +79 -0
- package/raw/guides/deployment-strategy.md +448 -0
- package/raw/guides/evals-framework.md +452 -0
- package/raw/guides/mcp-tools.md +335 -0
- package/raw/guides/task-spec.md +79 -0
- package/raw/guides/type-checking-templates/README.md +112 -0
- package/raw/guides/type-checking-templates/eslint/eslint.config.ts +105 -0
- package/raw/guides/type-checking-templates/python/mypy.ini +69 -0
- package/raw/guides/type-checking-templates/python/pyproject.toml +164 -0
- package/raw/guides/type-checking-templates/python/pyrightconfig.json +67 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.app.jsonc +45 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.lib.jsonc +44 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.node-esm.jsonc +40 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.node.jsonc +34 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.vite-root.json +8 -0
- package/raw/harness-notes.md +20 -0
- package/raw/house-style/components/Badge.tsx +16 -0
- package/raw/house-style/components/Button.tsx +32 -0
- package/raw/house-style/components/Card.tsx +26 -0
- package/raw/house-style/components/Chip.tsx +57 -0
- package/raw/house-style/components/IconButton.tsx +67 -0
- package/raw/house-style/components/Modal.tsx +18 -0
- package/raw/house-style/components/Stepper.tsx +141 -0
- package/raw/house-style/components/icons.tsx +128 -0
- package/raw/house-style/preview/src/index.css +46 -0
- package/raw/house-style/tokens/tailwind.preset.ts +49 -0
- package/raw/house-style/tokens/tokens.json +62 -0
- package/raw/llm-wiki-2.md +162 -0
- package/raw/llm-wiki.md +75 -0
- package/raw/research/dark-mode-theme/index.md +85 -0
- package/raw/research/dark-mode-theme/sources.md +49 -0
- package/raw/research/serena-mcp-disconnect/index.md +81 -0
- package/raw/research/serena-mcp-disconnect/sources.md +87 -0
- package/raw/research/wiki-tooling-improvements/index.md +126 -0
- package/raw/research/wiki-tooling-improvements/sources.md +73 -0
- package/raw/software-factory-case-study.pdf +0 -0
|
@@ -0,0 +1,146 @@
|
|
|
1
|
+
#!/usr/bin/env node
|
|
2
|
+
|
|
3
|
+
// Zero-dependency static file server for the live wiki dashboard.
|
|
4
|
+
// Serves the dashboard HTML client (bundled next to this script) and the
|
|
5
|
+
// target project's wiki/ tree read-only over HTTP. Node builtins only.
|
|
6
|
+
|
|
7
|
+
const http = require('http');
|
|
8
|
+
const fs = require('fs');
|
|
9
|
+
const path = require('path');
|
|
10
|
+
|
|
11
|
+
const DEFAULT_PORT = 4317;
|
|
12
|
+
const MAX_PORT_ATTEMPTS = 10;
|
|
13
|
+
|
|
14
|
+
// --- CLI arg parsing (simple/positional) --------------------------------
|
|
15
|
+
// First non-flag arg = project directory (default process.cwd())
|
|
16
|
+
// `--port <n>` OR a positional numeric arg = port (default 4317)
|
|
17
|
+
function parseArgs(argv) {
|
|
18
|
+
let projectDir = null;
|
|
19
|
+
let port = null;
|
|
20
|
+
|
|
21
|
+
for (let i = 0; i < argv.length; i++) {
|
|
22
|
+
const arg = argv[i];
|
|
23
|
+
if (arg === '--port') {
|
|
24
|
+
port = parseInt(argv[++i], 10);
|
|
25
|
+
} else if (/^\d+$/.test(arg)) {
|
|
26
|
+
port = parseInt(arg, 10);
|
|
27
|
+
} else if (!arg.startsWith('--')) {
|
|
28
|
+
if (projectDir === null) projectDir = arg;
|
|
29
|
+
}
|
|
30
|
+
}
|
|
31
|
+
|
|
32
|
+
return {
|
|
33
|
+
projectDir: projectDir || process.cwd(),
|
|
34
|
+
port: Number.isInteger(port) ? port : DEFAULT_PORT,
|
|
35
|
+
};
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
const { projectDir, port: startPort } = parseArgs(process.argv.slice(2));
|
|
39
|
+
|
|
40
|
+
const DASHBOARD_HTML = path.join(__dirname, 'templates', 'wiki', 'dashboard.html');
|
|
41
|
+
const WIKI_ROOT = path.resolve(projectDir, 'wiki');
|
|
42
|
+
|
|
43
|
+
const CONTENT_TYPES = {
|
|
44
|
+
'.html': 'text/html',
|
|
45
|
+
'.md': 'text/markdown',
|
|
46
|
+
'.json': 'application/json',
|
|
47
|
+
};
|
|
48
|
+
|
|
49
|
+
function contentType(filePath) {
|
|
50
|
+
return CONTENT_TYPES[path.extname(filePath).toLowerCase()] || 'text/plain';
|
|
51
|
+
}
|
|
52
|
+
|
|
53
|
+
function noCacheHeaders(extra) {
|
|
54
|
+
return Object.assign(
|
|
55
|
+
{
|
|
56
|
+
'Cache-Control': 'no-store',
|
|
57
|
+
Pragma: 'no-cache',
|
|
58
|
+
Expires: '0',
|
|
59
|
+
},
|
|
60
|
+
extra || {}
|
|
61
|
+
);
|
|
62
|
+
}
|
|
63
|
+
|
|
64
|
+
function send(res, status, body, filePath) {
|
|
65
|
+
const headers = noCacheHeaders(
|
|
66
|
+
filePath ? { 'Content-Type': contentType(filePath) } : { 'Content-Type': 'text/plain' }
|
|
67
|
+
);
|
|
68
|
+
res.writeHead(status, headers);
|
|
69
|
+
res.end(body);
|
|
70
|
+
}
|
|
71
|
+
|
|
72
|
+
function serveFile(res, filePath) {
|
|
73
|
+
fs.readFile(filePath, (err, data) => {
|
|
74
|
+
if (err) {
|
|
75
|
+
send(res, 404, 'Not Found');
|
|
76
|
+
return;
|
|
77
|
+
}
|
|
78
|
+
res.writeHead(200, noCacheHeaders({ 'Content-Type': contentType(filePath) }));
|
|
79
|
+
res.end(data);
|
|
80
|
+
});
|
|
81
|
+
}
|
|
82
|
+
|
|
83
|
+
function requestHandler(req, res) {
|
|
84
|
+
if (req.method !== 'GET') {
|
|
85
|
+
send(res, 405, 'Method Not Allowed');
|
|
86
|
+
return;
|
|
87
|
+
}
|
|
88
|
+
|
|
89
|
+
// Strip query string, then decode.
|
|
90
|
+
const rawPath = req.url.split('?')[0];
|
|
91
|
+
let urlPath;
|
|
92
|
+
try {
|
|
93
|
+
urlPath = decodeURIComponent(rawPath);
|
|
94
|
+
} catch (e) {
|
|
95
|
+
send(res, 400, 'Bad Request');
|
|
96
|
+
return;
|
|
97
|
+
}
|
|
98
|
+
|
|
99
|
+
// Dashboard client (may 404 gracefully if not yet built).
|
|
100
|
+
if (urlPath === '/' || urlPath === '/dashboard.html') {
|
|
101
|
+
serveFile(res, DASHBOARD_HTML);
|
|
102
|
+
return;
|
|
103
|
+
}
|
|
104
|
+
|
|
105
|
+
// Wiki tree, read-only, cwd/project-relative.
|
|
106
|
+
if (urlPath === '/wiki' || urlPath.startsWith('/wiki/')) {
|
|
107
|
+
const subpath = urlPath.slice('/wiki'.length).replace(/^\/+/, '');
|
|
108
|
+
const resolved = path.resolve(path.join(WIKI_ROOT, subpath));
|
|
109
|
+
|
|
110
|
+
// Path-traversal defense: resolved path must stay inside WIKI_ROOT.
|
|
111
|
+
if (resolved !== WIKI_ROOT && !resolved.startsWith(WIKI_ROOT + path.sep)) {
|
|
112
|
+
send(res, 403, 'Forbidden');
|
|
113
|
+
return;
|
|
114
|
+
}
|
|
115
|
+
|
|
116
|
+
fs.stat(resolved, (err, stats) => {
|
|
117
|
+
if (err || !stats.isFile()) {
|
|
118
|
+
send(res, 404, 'Not Found');
|
|
119
|
+
return;
|
|
120
|
+
}
|
|
121
|
+
serveFile(res, resolved);
|
|
122
|
+
});
|
|
123
|
+
return;
|
|
124
|
+
}
|
|
125
|
+
|
|
126
|
+
send(res, 404, 'Not Found');
|
|
127
|
+
}
|
|
128
|
+
|
|
129
|
+
// --- Listen with port fallback on EADDRINUSE ----------------------------
|
|
130
|
+
function listen(port, attempt) {
|
|
131
|
+
const server = http.createServer(requestHandler);
|
|
132
|
+
|
|
133
|
+
server.on('error', (err) => {
|
|
134
|
+
if (err.code === 'EADDRINUSE' && attempt < MAX_PORT_ATTEMPTS) {
|
|
135
|
+
listen(port + 1, attempt + 1);
|
|
136
|
+
} else {
|
|
137
|
+
throw err;
|
|
138
|
+
}
|
|
139
|
+
});
|
|
140
|
+
|
|
141
|
+
server.listen(port, () => {
|
|
142
|
+
console.log(`Wiki dashboard server running at http://localhost:${port}`);
|
|
143
|
+
});
|
|
144
|
+
}
|
|
145
|
+
|
|
146
|
+
listen(startPort, 1);
|
|
@@ -0,0 +1,146 @@
|
|
|
1
|
+
# skills/
|
|
2
|
+
|
|
3
|
+
One directory per Claude Code skill, each containing a `SKILL.md` (Skills directory format). `install-global.sh` copies this whole folder verbatim to `~/.claude/skills/`, which makes every skill below available as a `/slash-command` in any Claude Code session on the machine — not just in this repo.
|
|
4
|
+
|
|
5
|
+
Most skills operate on the LLM Wiki (`wiki/`, `raw/`) described in the root `CLAUDE.md`; a handful are general-purpose utilities unrelated to the wiki. `uat-walk/` is the one skill with an extra file beyond `SKILL.md` — `UAT-CORE.md`, a shared module of UAT walkthrough logic factored out so other UAT skills (`uat-auto`, `uat-auto-plus`) can reference it instead of duplicating it.
|
|
6
|
+
|
|
7
|
+
## Wiki operations
|
|
8
|
+
|
|
9
|
+
| Skill | Purpose |
|
|
10
|
+
|-------|---------|
|
|
11
|
+
| `wiki-ingest` | Process a source from `raw/` into the wiki — summary page, entity/concept updates, index + log entry |
|
|
12
|
+
| `wiki-query` | Answer a question from the wiki with citations; offer to file the answer back as a new page |
|
|
13
|
+
| `wiki-lint` | Health-check the wiki — contradictions, stale claims, orphan pages, missing concept pages, missing cross-references, never-ingested raw sources |
|
|
14
|
+
| `wiki-archive` | Batch-move terminal work items into `<family>/archive/`, update `archive/index.md`, log the operation |
|
|
15
|
+
| `wiki-rotate-log` | Rotate `wiki/log.md` into a timestamped archive file once it exceeds ~500 lines |
|
|
16
|
+
| `wiki-tidy` | One-shot cleanup: lint, archive terminal items across all families, rotate the log if overgrown — phases confirmed in sequence |
|
|
17
|
+
|
|
18
|
+
## Requirements
|
|
19
|
+
|
|
20
|
+
| Skill | Purpose |
|
|
21
|
+
|-------|---------|
|
|
22
|
+
| `req-create` | Draft a new requirement (REQ-NNN) via Socratic Q&A — problem, personas, user stories, success metrics, non-goals |
|
|
23
|
+
| `req-finalize` | Run a completeness audit on a draft requirement, resolve gaps via Q&A, flip `status: draft → approved` |
|
|
24
|
+
| `req-extract-decisions` | Extract Architecturally Significant Requirements from an approved requirement and propose Decision Group candidates |
|
|
25
|
+
| `req-update` | Amend an approved requirement with a tracked, append-only Amendment block; direct edits for drafts |
|
|
26
|
+
| `req-compile` | Compile a requirement into a running, self-verifying system — routes every claim to its cheapest re-runnable check |
|
|
27
|
+
| `req-retire` | Retire a requirement — set `status: retired`, document why, move to `archive/`, log it |
|
|
28
|
+
|
|
29
|
+
## Decisions
|
|
30
|
+
|
|
31
|
+
| Skill | Purpose |
|
|
32
|
+
|-------|---------|
|
|
33
|
+
| `decision-create` | Create a Decision Group file with one or more proposed decisions, table-only comparisons, and mermaid flowcharts |
|
|
34
|
+
| `decision-finalize` | Finalize a single proposed decision — E-C-A-D-R audit, supersession check, flip to `accepted` |
|
|
35
|
+
| `decision-walkthrough` | Walk a decision file decision-by-decision, confirming each architecture choice with the user via Q&A |
|
|
36
|
+
| `decision-next` | Read-only — find the first accepted decision missing a task reference; suggest `/task-add` |
|
|
37
|
+
|
|
38
|
+
## Roadmaps
|
|
39
|
+
|
|
40
|
+
| Skill | Purpose |
|
|
41
|
+
|-------|---------|
|
|
42
|
+
| `roadmap-create` | Create an execution-plan roadmap via short Socratic Q&A — goal, phases, hybrid task-link/inline checklist |
|
|
43
|
+
| `roadmap-add` | Append a new item to an existing roadmap, optionally under a named phase |
|
|
44
|
+
| `roadmap-next` | Point at the first unchecked roadmap item(s), grouped into parallelizable waves; auto-archive fully-checked roadmaps |
|
|
45
|
+
|
|
46
|
+
## Tasks
|
|
47
|
+
|
|
48
|
+
| Skill | Purpose |
|
|
49
|
+
|-------|---------|
|
|
50
|
+
| `task-add` | Create a structured, execution-ready task file in `wiki/work/tasks/` |
|
|
51
|
+
| `task-update` | Assess and modify an existing task's scope or steps |
|
|
52
|
+
| `task-audit` | Generate a dependency graph of active tasks — what blocks what, what can run in parallel; flags unannotated implementations |
|
|
53
|
+
| `task-trash` | Trash a task and its related UAT files — move to `archive/`, remove all active-index references |
|
|
54
|
+
|
|
55
|
+
## UAT (user acceptance testing)
|
|
56
|
+
|
|
57
|
+
| Skill | Purpose |
|
|
58
|
+
|-------|---------|
|
|
59
|
+
| `uat-generate` | Generate UAT tests in `wiki/work/uat/` for a task |
|
|
60
|
+
| `uat-walk` | Interactively walk a pending UAT file test-by-test with the user (shares logic via `UAT-CORE.md`) |
|
|
61
|
+
| `uat-auto` | Non-interactively run every test in a pending UAT file and auto-judge verdicts (headless, fail-closed) |
|
|
62
|
+
| `uat-auto-plus` | Autonomous-fix variant of `uat-auto` — diagnoses failures, fixes them, re-runs until green or attempts exhausted; for `--dangerously-skip-permissions` agents |
|
|
63
|
+
| `uat-skip` | Skip UAT for a task — set UAT and task `status: skipped/done`, remove index rows, auto-checkoff the roadmap |
|
|
64
|
+
|
|
65
|
+
## Bugs
|
|
66
|
+
|
|
67
|
+
| Skill | Purpose |
|
|
68
|
+
|-------|---------|
|
|
69
|
+
| `bug-file` | File a new bug report with required-on-report fields; append it to the bug index |
|
|
70
|
+
| `bug-triage` | Set priority/assignee/tags/impact, then advance to `in-progress`, keep `triaged`, or reject (wontfix/duplicate/cannot-reproduce) and archive |
|
|
71
|
+
| `bug-close` | Close an in-progress bug — record root cause and resolution, require a regression test, move to `archive/` |
|
|
72
|
+
|
|
73
|
+
## Evals
|
|
74
|
+
|
|
75
|
+
| Skill | Purpose |
|
|
76
|
+
|-------|---------|
|
|
77
|
+
| `eval-create` | Assess eval coverage against the 5-stage framework and create new evals one at a time, with user approval at each step |
|
|
78
|
+
| `eval-run` | Execute the eval suite (golden sets, scenarios, replays), report pass/fail, surface regressions |
|
|
79
|
+
| `eval-gap` | Read-only gap report against the 5-stage framework — what's missing, what's thin, what to build next |
|
|
80
|
+
|
|
81
|
+
## Execution / orchestration
|
|
82
|
+
|
|
83
|
+
| Skill | Purpose |
|
|
84
|
+
|-------|---------|
|
|
85
|
+
| `now` | Plan and delegate a task to subagents (max 3 concurrent) |
|
|
86
|
+
| `tackle` | Execute an outlined task file step-by-step with subagent delegation |
|
|
87
|
+
| `power-mode` | Orchestrator for parallel agent teams — drives roadmap or task files through the full tackle → uat-generate → uat-auto pipeline |
|
|
88
|
+
|
|
89
|
+
## Docs & quality
|
|
90
|
+
|
|
91
|
+
| Skill | Purpose |
|
|
92
|
+
|-------|---------|
|
|
93
|
+
| `lint` | Get IDE diagnostics, then fix issues one-by-one in verify cycles |
|
|
94
|
+
| `update-docs` | Update task, UAT, and project documentation to reflect implementation work just completed |
|
|
95
|
+
| `simplify` | Analyze files or directories to remove redundancy and simplify complexity |
|
|
96
|
+
| `project-readme` | Generate or update a portfolio-ready project README |
|
|
97
|
+
| `demo` | Audit all project functionality and produce a 2-3 minute demo run book plus a Marp slideshow |
|
|
98
|
+
| `gap-assess` | Audit actual vs. expected functionality; produce an approvable gap-assessment plan (subagent-delegated, runs in plan mode) |
|
|
99
|
+
| `debug-logs` | Diagnose points of failure from session context, running processes, and log stores; produce ranked likely causes without applying fixes |
|
|
100
|
+
|
|
101
|
+
## Security
|
|
102
|
+
|
|
103
|
+
| Skill | Purpose |
|
|
104
|
+
|-------|---------|
|
|
105
|
+
| `security-audit` | Audit an LLM/AI application across 11 categories — internal posture (observability, rate limiting, access controls, HITL policy, benchmarking) and external threats (prompt injection, data leakage, output XSS, excessive agency, supply chain, token DoS) |
|
|
106
|
+
|
|
107
|
+
## Porting & extraction
|
|
108
|
+
|
|
109
|
+
| Skill | Purpose |
|
|
110
|
+
|-------|---------|
|
|
111
|
+
| `extract-feature` | Analyze a feature and produce a SOLID-compliant standalone module extraction plan (compatible with `port-feature`) |
|
|
112
|
+
| `port-feature` | Assess a feature in an external project and produce a concrete porting plan into the current project's conventions |
|
|
113
|
+
|
|
114
|
+
## Research
|
|
115
|
+
|
|
116
|
+
| Skill | Purpose |
|
|
117
|
+
|-------|---------|
|
|
118
|
+
| `research` | Deep research on a topic — codebase analysis, library docs, web search — writes the report plus primary sources to `raw/research/<slug>/` |
|
|
119
|
+
| `research-company` | Comprehensive company research — mission, operations, leadership, products/services, ~5 years of recent news |
|
|
120
|
+
| `company-align` | Analyse project–company fit against researched company context; surface gaps, strengths, and talking points |
|
|
121
|
+
|
|
122
|
+
## Presentation
|
|
123
|
+
|
|
124
|
+
| Skill | Purpose |
|
|
125
|
+
|-------|---------|
|
|
126
|
+
| `marp-slideshow` | Summarize a file and emit a Marp/Marpit slideshow markdown deck |
|
|
127
|
+
| `mermaid-flowchart` | Summarize an architecture file (markdown, YAML, Compose) into a Mermaid flowchart |
|
|
128
|
+
| `flashcard` | Turn markdown/research files into a self-contained interactive flashcard HTML page |
|
|
129
|
+
|
|
130
|
+
## Misc utility
|
|
131
|
+
|
|
132
|
+
| Skill | Purpose |
|
|
133
|
+
|-------|---------|
|
|
134
|
+
| `git-commit` | Stage all changes and commit with an auto-generated message |
|
|
135
|
+
| `primer` | Refresh codebase context via Serena memories |
|
|
136
|
+
| `serena-config` | Interactively configure Serena language servers in `.serena/project.yml` |
|
|
137
|
+
| `anti-slop` | Detect and remove AI writing patterns from copy so it reads like a person, not a language model |
|
|
138
|
+
| `frontend-taste` | Wire the house-style design system (`~/code/house-style`) into the current project — tokens, Tailwind preset, component patterns, base CSS layer |
|
|
139
|
+
| `elevator-pitch` | Generate a short, punchy elevator pitch for a project |
|
|
140
|
+
|
|
141
|
+
## Conventions
|
|
142
|
+
|
|
143
|
+
- Every skill directory name matches its slash-command name (`lib/skills/req-create/` → `/req-create`).
|
|
144
|
+
- Frontmatter in each `SKILL.md` (`name`, `description`, optional `category`/`model`) drives Claude Code's skill picker — the `description` is what decides relevance, so it should stay specific about triggers and scope.
|
|
145
|
+
- Skills that read/write the wiki follow the family lifecycle files under `wiki/work/*/lifecycle.md` in the target project, not anything hardcoded here — this repo's own `wiki/` is just the reference instance.
|
|
146
|
+
- New skills should be added as a new subdirectory with a `SKILL.md`, then listed in the appropriate table above and in the root `CLAUDE.md` Custom Commands table.
|
|
@@ -0,0 +1,183 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: anti-slop
|
|
3
|
+
description: Detect and remove AI writing patterns from any copy — blogs, social posts, emails, landing pages, ad copy, pitch decks, or internal documents — so the writing sounds like a real person thinking out loud instead of a language model producing persuasive text. Use this skill whenever someone needs to write or edit copy that should not read as AI-generated, whenever previous AI output has come back generic or hollow, or whenever a piece of writing feels technically correct but somehow off. Triggers include: "this sounds like AI," "make this sound more human," "edit this copy," "write a LinkedIn post," "write a blog," "rewrite this," "clean up this draft," or any request to produce or improve written marketing copy. Always apply the master prompt at the end of any copy prompt, never at the beginning.
|
|
4
|
+
category: executing
|
|
5
|
+
model: claude-sonnet-4-6
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
# Anti-Slop
|
|
9
|
+
|
|
10
|
+
AI writing is recognizable not because of emojis or em dashes anymore. Those were the first generation of tells and most people have already eliminated them. The current tells live in structure — repeating sentence patterns, rhetorical framing borrowed from persuasive writing, and hype language that sounds like something without actually saying anything.
|
|
11
|
+
|
|
12
|
+
The way to identify a slop pattern is to copy examples of writing that feel off and ask an AI: "What grammatical structure is happening here?" It will identify the pattern by name. Then ask: "Write a prompt that prevents this structure from appearing." AI is useful for teaching you exactly how to stop writing like AI.
|
|
13
|
+
|
|
14
|
+
Below are the five labeled patterns, what they look like, and how to prompt against them. After the patterns is the master prompt — a single block you paste at the end of any copy prompt to enforce all of them at once.
|
|
15
|
+
|
|
16
|
+
---
|
|
17
|
+
|
|
18
|
+
## The five slop patterns
|
|
19
|
+
|
|
20
|
+
### 1. ANAPHORA — repeated sentence openings
|
|
21
|
+
|
|
22
|
+
AI repeats the same opening word or phrase across consecutive sentences because the rhythm sounds persuasive.
|
|
23
|
+
|
|
24
|
+
What it looks like:
|
|
25
|
+
> "We tested the system. We deployed the system. We expanded the system."
|
|
26
|
+
|
|
27
|
+
Once readers notice this pattern it feels mechanical and staged, even if they cannot name what they are seeing.
|
|
28
|
+
|
|
29
|
+
Prompt to fix it:
|
|
30
|
+
```
|
|
31
|
+
Avoid anaphora and repeated opening phrases. Do not repeat the same beginning
|
|
32
|
+
across multiple sentences. Write sentences with varied structure and natural flow.
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
### 2. DUAL_CLAUSE_CONTRAST — the "X, not Y" construction
|
|
38
|
+
|
|
39
|
+
AI defines ideas through comparison, setting up one concept and dismissing another in the same sentence. It creates a false sense of clarity.
|
|
40
|
+
|
|
41
|
+
What it looks like:
|
|
42
|
+
> "Great operators build systems, not workflows."
|
|
43
|
+
> "This is a leadership decision, not a technical one."
|
|
44
|
+
|
|
45
|
+
When every post uses this pattern, the writing starts to sound scripted regardless of what is being said.
|
|
46
|
+
|
|
47
|
+
Prompt to fix it:
|
|
48
|
+
```
|
|
49
|
+
Avoid contrast-based sentence structures and rhetorical opposition.
|
|
50
|
+
Explain ideas directly without defining them through comparison with another concept.
|
|
51
|
+
```
|
|
52
|
+
|
|
53
|
+
---
|
|
54
|
+
|
|
55
|
+
### 3. COLON_TITLE — dual clause headers that simulate depth
|
|
56
|
+
|
|
57
|
+
AI writes titles that split into two halves around a colon. The first half creates intrigue, the second half sounds analytical.
|
|
58
|
+
|
|
59
|
+
What it looks like:
|
|
60
|
+
> "The Future Of Marketing: Why Systems Win"
|
|
61
|
+
> "From Data To Strategy: A New Perspective"
|
|
62
|
+
|
|
63
|
+
The structure looks organized but it is mostly decorative. It signals that the writer was performing depth rather than expressing it.
|
|
64
|
+
|
|
65
|
+
Prompt to fix it:
|
|
66
|
+
```
|
|
67
|
+
Avoid colon-based dual clause titles. Write titles that describe the idea directly
|
|
68
|
+
without splitting a concept into two rhetorical halves.
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
---
|
|
72
|
+
|
|
73
|
+
### 4. BUZZWORD_GENERIC — hype language that carries no information
|
|
74
|
+
|
|
75
|
+
AI relies on words that sound impressive but do not say anything specific. If you remove the adjective and the meaning stays the same, it was filler.
|
|
76
|
+
|
|
77
|
+
What it looks like:
|
|
78
|
+
> "Unlocking the power of AI for actionable insights."
|
|
79
|
+
> "Cutting-edge solutions that empower teams to drive impact."
|
|
80
|
+
|
|
81
|
+
Prompt to fix it:
|
|
82
|
+
```
|
|
83
|
+
No emojis. Avoid using em dashes — use commas or periods instead. Do not use any
|
|
84
|
+
of the following words or any derivatives: unlock, leverage, harness, insights,
|
|
85
|
+
democratize, explore, discover, dive in, elevate, enhance, witness, revolutionize,
|
|
86
|
+
transform, embrace, unleash, dive, indulge, actionable, reveal, unmatched, delve,
|
|
87
|
+
era, collaboration, cutting-edge, matters, impact, fusion, advancing, navigate,
|
|
88
|
+
drive, problem solver, changemaker, game changer, ensure, transformational,
|
|
89
|
+
powerful, derailed, delighted, cheat code.
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
---
|
|
93
|
+
|
|
94
|
+
### 5. NO_SPECIFICS — vague claims without evidence
|
|
95
|
+
|
|
96
|
+
The sentence makes an assertion but contains no concrete detail. Readers stop trusting writing that stays abstract for too long.
|
|
97
|
+
|
|
98
|
+
What it looks like:
|
|
99
|
+
> "A tool that helps teams move with clarity and get answers faster."
|
|
100
|
+
> "A solution that helps companies make better decisions."
|
|
101
|
+
|
|
102
|
+
Prompt to fix it:
|
|
103
|
+
```
|
|
104
|
+
Avoid vague claims without specifics. Include numbers, concrete examples, named
|
|
105
|
+
tools, or measurable outcomes when possible.
|
|
106
|
+
```
|
|
107
|
+
|
|
108
|
+
---
|
|
109
|
+
|
|
110
|
+
## Why these patterns keep appearing
|
|
111
|
+
|
|
112
|
+
Language models are trained on massive collections of persuasive writing — blog posts, LinkedIn content, marketing copy, keynote transcripts. The patterns above are common in that training data because they were effective at one point. When millions of people start using the same model, those structures appear everywhere at once and readers begin to recognize the rhythm before they can articulate what is wrong.
|
|
113
|
+
|
|
114
|
+
Removing the em dash was a surface fix. The structure underneath did not change. That is why people can still sense slop even in writing that has been cleaned up at the punctuation level.
|
|
115
|
+
|
|
116
|
+
---
|
|
117
|
+
|
|
118
|
+
## The master prompt
|
|
119
|
+
|
|
120
|
+
Paste this block at the end of any copy prompt. It must come last — after your context, after your instructions, after your examples. Placing it at the beginning reduces its effectiveness. The reason is not fully understood, but in practice it consistently performs better as the final instruction.
|
|
121
|
+
|
|
122
|
+
```
|
|
123
|
+
No emojis. Avoid using em dashes; use commas or periods instead. Do not use any
|
|
124
|
+
of the following words or any derivatives: unlock, leverage, harness, insights,
|
|
125
|
+
democratize, explore, discover, dive in, elevate, enhance, witness, revolutionize,
|
|
126
|
+
transform, embrace, unleash, dive, indulge, actionable, reveal, unmatched, delve,
|
|
127
|
+
era, collaboration, cutting-edge, matters, impact, fusion, advancing, navigate,
|
|
128
|
+
drive, problem solver, changemaker, game changer, ensure, transformational,
|
|
129
|
+
powerful, derailed, delighted, cheat code.
|
|
130
|
+
|
|
131
|
+
If there are titles or headers, write them as direct one-liners under 10 words
|
|
132
|
+
based on the actual insight, not the topic category. Titles can be informal but
|
|
133
|
+
they need to say something specific.
|
|
134
|
+
|
|
135
|
+
Avoid contrastive negation, antithesis, and rhetorical contrast. No "X, not Y"
|
|
136
|
+
constructions. Write in a natural, conversational tone.
|
|
137
|
+
|
|
138
|
+
Avoid sentence fragments, anaphora, and asyndeton. Do not use short standalone
|
|
139
|
+
phrases or stacked clauses without conjunctions. Write in complete, naturally
|
|
140
|
+
flowing sentences.
|
|
141
|
+
|
|
142
|
+
Avoid repeated sentence openings across multiple sentences and vary sentence
|
|
143
|
+
structure so the same word or phrase does not begin consecutive sentences.
|
|
144
|
+
|
|
145
|
+
Do not structure paragraphs around rhythmic rhetorical patterns that sound like
|
|
146
|
+
speeches or persuasion frameworks. Prioritize clarity over dramatic phrasing.
|
|
147
|
+
|
|
148
|
+
Avoid colon-based dual clause titles or headings that try to simulate depth.
|
|
149
|
+
Write titles that describe the idea directly.
|
|
150
|
+
|
|
151
|
+
Remove buzzwords, hype language, and filler adjectives. Replace vague
|
|
152
|
+
marketing-style phrasing with clear descriptions of what actually happens.
|
|
153
|
+
|
|
154
|
+
Avoid vague claims and include concrete examples, numbers, tools, constraints,
|
|
155
|
+
or specific situations whenever possible so the writing contains real information.
|
|
156
|
+
|
|
157
|
+
Prefer straightforward explanation over rhetorical emphasis. Write sentences
|
|
158
|
+
that sound like a thoughtful person explaining an idea, not a motivational post
|
|
159
|
+
or keynote speech.
|
|
160
|
+
|
|
161
|
+
When editing text, simplify sentences that sound formulaic or generic and replace
|
|
162
|
+
abstract language with precise wording that reflects a real observation or
|
|
163
|
+
experience.
|
|
164
|
+
```
|
|
165
|
+
|
|
166
|
+
---
|
|
167
|
+
|
|
168
|
+
## How to use this in practice
|
|
169
|
+
|
|
170
|
+
For any piece of copy — blog, email, social post, landing page, ad, deck slide — build your prompt normally: give context, specify the audience, explain what the piece needs to do. Then paste the master prompt at the very end before hitting send.
|
|
171
|
+
|
|
172
|
+
For editing existing copy, paste the copy and the master prompt together and ask the AI to rewrite it according to those constraints.
|
|
173
|
+
|
|
174
|
+
For evaluating copy before publishing, paste it and ask: "Does any of this violate the constraints in the following prompt?" Then paste the master prompt. The AI will flag what it finds.
|
|
175
|
+
|
|
176
|
+
---
|
|
177
|
+
|
|
178
|
+
## Notes
|
|
179
|
+
|
|
180
|
+
- The master prompt is a constraint block, not a style guide. It tells the AI what not to do. You still need to give it the context, voice, and substance of what to write. Constraints protect the output; context shapes the thinking.
|
|
181
|
+
- This prompt was developed by running real examples of slop through an AI, identifying the grammatical structure behind each pattern, and building a targeted constraint for each one. The five labeled patterns above came from that process.
|
|
182
|
+
- The master prompt works for all copy types: blogs, LinkedIn posts, email campaigns, landing pages, ad copy, pitch decks, internal communications, and anywhere else writing needs to sound like a real person.
|
|
183
|
+
- Apply it last. Every time.
|
|
@@ -0,0 +1,136 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: bug-close
|
|
3
|
+
description: Close an in-progress bug — record root cause and resolution, require a regression test, then move it to archive/ (or delete it for late wontfix decisions)
|
|
4
|
+
category: executing
|
|
5
|
+
model: claude-sonnet-4-6
|
|
6
|
+
argument-hint: <BUG-NNNN, path, or number-slug>
|
|
7
|
+
disable-model-invocation: false
|
|
8
|
+
user-invocable: true
|
|
9
|
+
---
|
|
10
|
+
**Prereqs:** obey `.docs/guides/mcp-tools.md` + `wiki/work/bugs/lifecycle.md`; run /primer if not done this session.
|
|
11
|
+
|
|
12
|
+
# Close Bug
|
|
13
|
+
|
|
14
|
+
Finalize a bug that has been fixed. Records the root cause, the resolution (commit, PR, regression test), and moves the file to `wiki/work/bugs/archive/`. Refuses to close without a regression test — silent closes are the worst-case anti-pattern.
|
|
15
|
+
|
|
16
|
+
---
|
|
17
|
+
|
|
18
|
+
**Input**: $ARGUMENTS
|
|
19
|
+
|
|
20
|
+
---
|
|
21
|
+
|
|
22
|
+
## Instructions
|
|
23
|
+
|
|
24
|
+
### Step 1: Resolve the Bug File
|
|
25
|
+
|
|
26
|
+
Parse `$ARGUMENTS`. Accepted forms:
|
|
27
|
+
- `BUG-NNNN` (e.g. `BUG-0042`)
|
|
28
|
+
- `NNNN` (e.g. `0042` or `42`)
|
|
29
|
+
- `NNNN-slug` (e.g. `0042-csv-export`)
|
|
30
|
+
- Full path
|
|
31
|
+
|
|
32
|
+
Resolution order:
|
|
33
|
+
1. If full path: confirm with `mcp__serena__list_dir`.
|
|
34
|
+
2. Otherwise normalize and search `wiki/work/bugs/` first via `mcp__serena__find_file`.
|
|
35
|
+
3. If found in `wiki/work/bugs/` root: STOP and tell the user the bug must be triaged and worked first — `/bug-triage` → choose "Start work now" → land a fix → re-run `/bug-close`.
|
|
36
|
+
4. If found in `archive/`: STOP — already terminal.
|
|
37
|
+
5. If not found anywhere: STOP and report the error.
|
|
38
|
+
|
|
39
|
+
Read the bug file in full.
|
|
40
|
+
|
|
41
|
+
### Step 2: Read the Spec
|
|
42
|
+
|
|
43
|
+
Read `wiki/work/bugs/lifecycle.md` for the close-gate requirements (Root Cause Analysis, fix commit, and regression test) and the valid terminal statuses.
|
|
44
|
+
|
|
45
|
+
### Step 3: Audit Pre-Close Fields
|
|
46
|
+
|
|
47
|
+
A bug in `in-progress/` should already carry triage values. Re-check that all of these are present and non-templated:
|
|
48
|
+
|
|
49
|
+
- `Status` is `in-progress` or `fixed`
|
|
50
|
+
- Severity, Priority, Assignee, Reporter, Reported, Tags — all set
|
|
51
|
+
- `Impact`, `Workaround` — non-empty (Workaround may legitimately be `None known`)
|
|
52
|
+
- Environment, Steps to Reproduce, Expected, Actual — unchanged from filing
|
|
53
|
+
|
|
54
|
+
If any are missing or templated, ask the user to fill them via `AskUserQuestion` before proceeding. Update the file with `Edit`.
|
|
55
|
+
|
|
56
|
+
### Step 4: Decide the Outcome
|
|
57
|
+
|
|
58
|
+
Use `AskUserQuestion` (single-select):
|
|
59
|
+
|
|
60
|
+
| Choice | Effect | When to pick |
|
|
61
|
+
|--------|--------|--------------|
|
|
62
|
+
| **Verify and close** (default) | Status → `verified`; **move file** to `archive/` | A fix has been merged and validated |
|
|
63
|
+
| **Mark fixed (not yet verified)** | Status → `fixed`; file stays in `wiki/work/bugs/` | Patch landed but waiting on UAT or staging soak |
|
|
64
|
+
| **Won't fix (late decision)** | Status → `wontfix`; **move file** to `archive/` | Investigation revealed the fix isn't worth the cost or invalidates a constraint |
|
|
65
|
+
| **Cannot reproduce (re-evaluated)** | Status → `cannot-reproduce`; **move file** to `archive/` | Work started, repro never re-surfaced, abandoning |
|
|
66
|
+
|
|
67
|
+
For **Mark fixed** and **Verify and close**, continue to Steps 5–6. For trash outcomes, jump to Step 7 (with rationale captured in `## Resolution`).
|
|
68
|
+
|
|
69
|
+
### Step 5: Gather Root Cause Analysis
|
|
70
|
+
|
|
71
|
+
If `## Root Cause Analysis` is empty or still contains the templated placeholder line, prompt for it.
|
|
72
|
+
|
|
73
|
+
Use `AskUserQuestion` free-text:
|
|
74
|
+
|
|
75
|
+
> One paragraph: what was the underlying defect? Why did the symptom occur? Avoid restating the symptom — explain the *cause*.
|
|
76
|
+
|
|
77
|
+
Edit the bug file to replace the placeholder line under `## Root Cause Analysis` with the user's text. Remove the `> Filled in during or after the fix — not on report.` quote line.
|
|
78
|
+
|
|
79
|
+
### Step 6: Gather Resolution Fields
|
|
80
|
+
|
|
81
|
+
Use `AskUserQuestion` (batched where the UI permits):
|
|
82
|
+
|
|
83
|
+
| Field | Form | Required for `verified`? |
|
|
84
|
+
|-------|------|--------------------------|
|
|
85
|
+
| Fix commit | Short SHA (or "see PR") | **Yes** |
|
|
86
|
+
| Fix version | Release tag or `—` | No |
|
|
87
|
+
| Linked PR | `#NNN` or full URL or `—` | No (recommended) |
|
|
88
|
+
| Linked task | `[[TASK-NNN]]` or `—` | No |
|
|
89
|
+
| **Regression test** | Path to an automated test that fails-before / passes-after, **or** path to a UAT entry that exercises the fix | **Yes** |
|
|
90
|
+
|
|
91
|
+
For **Verify and close**, both required fields must be supplied. If the user cannot name a regression test, STOP and tell them:
|
|
92
|
+
|
|
93
|
+
> Cannot close `BUG-NNNN` — every close requires a regression test path (automated test or UAT entry). If automation is infeasible, add a manual check to a UAT file and link it here.
|
|
94
|
+
|
|
95
|
+
For **Mark fixed**, the commit is required; the regression test can wait until verification.
|
|
96
|
+
|
|
97
|
+
Edit the bug file to populate the `## Resolution` table with the gathered values, removing the `> Filled in on close.` quote line.
|
|
98
|
+
|
|
99
|
+
### Step 7: Move the File
|
|
100
|
+
|
|
101
|
+
Update `Status:` and `Last updated:` in the bug file via `Edit` before moving.
|
|
102
|
+
|
|
103
|
+
| Outcome | Action |
|
|
104
|
+
|---------|--------|
|
|
105
|
+
| Verify and close | Archive-move sequence (see below) with status `verified` |
|
|
106
|
+
| Mark fixed | No move |
|
|
107
|
+
| Won't fix / Cannot reproduce | Archive-move sequence (see below) with the appropriate status |
|
|
108
|
+
|
|
109
|
+
**Archive-move sequence** (for all terminal outcomes — `Bash` only for `git mv`):
|
|
110
|
+
|
|
111
|
+
1. `Bash`: `git mv wiki/work/bugs/NNNN-slug.md wiki/work/bugs/archive/NNNN-slug.md`
|
|
112
|
+
2. `Edit`: remove the bug's row from `wiki/work/bugs/index.md`
|
|
113
|
+
3. `Edit`: append to `wiki/work/bugs/archive/index.md`: `| [[BUG-NNNN]] | <title> | <status> | YYYY-MM-DD |`
|
|
114
|
+
4. `Edit`: append to `wiki/log.md`
|
|
115
|
+
|
|
116
|
+
### Step 8: Update the Bug Index
|
|
117
|
+
|
|
118
|
+
For all terminal outcomes (`verified`, `wontfix`, `cannot-reproduce`), the archive-move sequence in Step 7 already removes the active index row and appends to `archive/index.md`. No further index edits are needed for those outcomes.
|
|
119
|
+
|
|
120
|
+
For `fixed` (no move): find the row for this bug in `wiki/work/bugs/index.md` and update the `Status` column to `fixed`.
|
|
121
|
+
|
|
122
|
+
Use **`Edit`** — one targeted call. Never `sed`, `awk`, `perl -i`, or `echo >>`.
|
|
123
|
+
|
|
124
|
+
### Step 9: Cross-Linking
|
|
125
|
+
|
|
126
|
+
- If a `Linked task` was provided in `[[TASK-NNN]]` format: resolve the task file using `mcp__serena__find_file` with pattern `TASK-NNN-*` searching `wiki/work/tasks/` (finds active or archived). Then open the task file and append `- Closes BUG-NNNN` to its footer (after the existing UAT link section, or under a new `**Closes**:` line). Use `Edit`.
|
|
127
|
+
- If a `Linked PR` was provided and PR is open: remind the user to add `Closes BUG-NNNN` to the PR description so GitHub auto-references the bug record.
|
|
128
|
+
|
|
129
|
+
### Step 10: Report Completion
|
|
130
|
+
|
|
131
|
+
Print:
|
|
132
|
+
- Bug ID, title
|
|
133
|
+
- Old status → new status; folder move (if any)
|
|
134
|
+
- Resolution summary: fix commit, regression test path
|
|
135
|
+
- For `verified`: a one-line clustering check — search `wiki/work/bugs/archive/` for the last 3 closes with overlapping `Tags` and surface them as "related recent closes" so the user can spot systemic issues.
|
|
136
|
+
- For `fixed`: remind the user to re-run `/bug-close` once verification lands.
|