chill-agent 1.2.0 → 1.4.0

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.
Files changed (87) hide show
  1. package/.agents/plugins/marketplace.json +39 -0
  2. package/.claude-plugin/plugin.json +35 -0
  3. package/.cline-plugin/plugin.json +35 -0
  4. package/.clinerules/chill-agent +274 -0
  5. package/.codex-plugin/plugin.json +35 -0
  6. package/.cursor/rules/chill-agent.mdc +278 -0
  7. package/.cursor-plugin/plugin.json +35 -0
  8. package/.devin-plugin/plugin.json +35 -0
  9. package/.grok-plugin/plugin.json +35 -0
  10. package/.kimi-plugin/plugin.json +35 -0
  11. package/.omp-plugin/plugin.json +35 -0
  12. package/.openclaw/skills/chill-audit/SKILL.md +103 -0
  13. package/.openclaw/skills/chill-debt/SKILL.md +44 -0
  14. package/.openclaw/skills/chill-gain/SKILL.md +52 -0
  15. package/.openclaw/skills/chill-help/SKILL.md +76 -0
  16. package/.openclaw/skills/chill-review/SKILL.md +101 -0
  17. package/.openclaw/skills/chill-slop/SKILL.md +274 -0
  18. package/.openclaw/skills/chill-slop-code/SKILL.md +93 -0
  19. package/.openclaw/skills/chill-slop-copywriting/SKILL.md +80 -0
  20. package/.openclaw/skills/chill-slop-human/SKILL.md +73 -0
  21. package/.openclaw/skills/chill-slop-mobile/SKILL.md +95 -0
  22. package/.openclaw/skills/chill-slop-ui/SKILL.md +114 -0
  23. package/.opencode/command/chill-audit.toml +2 -0
  24. package/.opencode/command/chill-debt.toml +2 -0
  25. package/.opencode/command/chill-gain.toml +2 -0
  26. package/.opencode/command/chill-help.toml +2 -0
  27. package/.opencode/command/chill-review.toml +2 -0
  28. package/.opencode/command/chill.toml +2 -0
  29. package/.qoder-plugin/plugin.json +35 -0
  30. package/.windsurf/rules/chill-agent.md +274 -0
  31. package/GUIDE.md +47 -0
  32. package/INSTALL.md +78 -0
  33. package/after-install.md +23 -0
  34. package/antislop.md +764 -0
  35. package/benchmarks/README.md +10 -0
  36. package/benchmarks/loc.js +21 -0
  37. package/benchmarks/results/token-efficiency.md +10 -0
  38. package/chillslop.md +764 -0
  39. package/commands/chill-audit.toml +2 -0
  40. package/commands/chill-debt.toml +2 -0
  41. package/commands/chill-gain.toml +2 -0
  42. package/commands/chill-help.toml +2 -0
  43. package/commands/chill-review.toml +2 -0
  44. package/commands/chill.toml +2 -0
  45. package/docs/agent-portability.md +62 -0
  46. package/docs/cursor-hooks.md +200 -0
  47. package/examples/README.md +8 -0
  48. package/examples/anti-slop-copy.md +7 -0
  49. package/examples/anti-slop-ui.md +14 -0
  50. package/examples/csv-sum.md +27 -0
  51. package/examples/debounce.md +22 -0
  52. package/examples/deep-clone.md +14 -0
  53. package/examples/modal-dialog.md +19 -0
  54. package/gemini-extension.json +6 -0
  55. package/hooks/chill-activate.js +19 -0
  56. package/hooks/chill-mode-tracker.js +23 -0
  57. package/hooks/chill-statusline.ps1 +10 -0
  58. package/hooks/chill-statusline.sh +9 -0
  59. package/hooks/claude-codex-hooks.json +11 -0
  60. package/hooks/copilot-hooks.json +11 -0
  61. package/hooks/cursor-hooks.json +17 -0
  62. package/hooks/qoder-hooks.json +11 -0
  63. package/i18n/README.es.md +17 -0
  64. package/i18n/README.id.md +25 -0
  65. package/i18n/README.ja.md +17 -0
  66. package/i18n/README.zh-CN.md +17 -0
  67. package/opencode.json +18 -0
  68. package/package.json +38 -3
  69. package/plugin.json +3 -0
  70. package/plugin.yaml +12 -0
  71. package/rules/antislop.md +764 -0
  72. package/rules/chillslop.md +764 -0
  73. package/rules/chillslop.mdc +764 -0
  74. package/skills/chill-audit/SKILL.md +103 -0
  75. package/skills/chill-debt/SKILL.md +44 -0
  76. package/skills/chill-gain/SKILL.md +52 -0
  77. package/skills/chill-help/SKILL.md +76 -0
  78. package/skills/chill-review/SKILL.md +101 -0
  79. package/skills/chill-slop/VERSION +1 -0
  80. package/skills/chill-slop-human/contrast-check.py +168 -0
  81. package/skills/chill-slop-human/contrast-mcp.py +121 -0
  82. package/skills/chill-slop-human/references/A11Y-PATTERNS.md +249 -0
  83. package/skills/chill-slop-human/references/WCAG.md +127 -0
  84. package/skills/chill-slop-ui/references/CORE-WEB-VITALS.md +181 -0
  85. package/skills/chill-slop-ui/references/WEB-BASELINE.md +28 -0
  86. package/tests/manifests.test.js +29 -0
  87. package/tests/rules.test.js +34 -0
@@ -0,0 +1,73 @@
1
+ ---
2
+ name: chill-slop-human
3
+ description: "Comprehensive Ergonomics, Human Factors & Accessibility Standard. Enforces WCAG AA 4.5:1 contrast, visible focus rings, 44px touch targets, Escape-key dialogs, and accessible screen-reader semantics."
4
+ license: MIT
5
+ ---
6
+
7
+ # ChillSlop Human: Comprehensive Ergonomics & Accessibility Standard
8
+
9
+ > *"Accessibility is not an optional polish phase. An interface that cannot be used by everyone is simply an unfinished interface."*
10
+
11
+ ---
12
+
13
+ ## 1. Contrast Ratios & Visual Legibility
14
+
15
+ ### WCAG AA Minimum Thresholds
16
+ - **Normal Body Text (< 18pt regular):** Minimum contrast ratio of **4.5:1** against its immediate background.
17
+ - **Large Text (>= 18pt regular or >= 14pt bold):** Minimum contrast ratio of **3:1**.
18
+ - **Interactive UI Components & Hairlines:** Minimum contrast ratio of **3:1** against adjacent surfaces.
19
+
20
+ ### Banned Contrast Sins
21
+ - **No Low-Contrast Gray-on-Gray Slop:** Never place `#71717A` body text on a `#18181B` card surface. Secondary metadata may use muted text only if text size is at least 11px and contrast is verified >= 4.5:1.
22
+ - **No White Text Over Light Gradients:** If using a gradient, text passing over it must maintain 4.5:1 contrast across the *entire* gradient spectrum, not just the dark endpoint.
23
+
24
+ ---
25
+
26
+ ## 2. Keyboard Navigation & Focus Management
27
+
28
+ ### Visible Focus Indicators
29
+ - Every interactive element (`<button>`, `<a>`, `<input>`, `<select>`, `<textarea>`) must display a visible, unclipped focus indicator upon keyboard Tab navigation:
30
+ ```css
31
+ :focus-visible {
32
+ outline: 2px solid #818CF8;
33
+ outline-offset: 2px;
34
+ }
35
+ ```
36
+ - **FORBIDDEN:** Setting `outline: none` or `outline: 0` without immediately supplying a custom focus indicator.
37
+
38
+ ### Modals, Drawers & Focus Trapping
39
+ - **Escape Key Interception:** Any open modal, drawer, dropdown, or overlay dialog MUST close immediately upon pressing the `Escape` key.
40
+ - **Focus Restoration:** Upon closing an overlay, focus must return directly to the trigger button that launched it.
41
+ - **Focus Trap:** When a modal is open, keyboard `Tab` cycles only through interactive elements inside the modal; background page content must be inert (`aria-hidden="true"` or `inert`).
42
+
43
+ ---
44
+
45
+ ## 3. Touch Targets & Tactile Ergonomics
46
+
47
+ - **Minimum Dimensions:** All buttons, toggle switches, links, and icon triggers on touch screens must measure at least **44x44px** (or provide 44px of hit area via padding).
48
+ - **Spacing Between Targets:** Adjacent touch controls must have at least `8px` of separation to prevent accidental mis-taps.
49
+
50
+ ---
51
+
52
+ ## 4. Semantics & Screen Reader Affordances
53
+
54
+ ### Native HTML First
55
+ - Use `<button>` for actions. Use `<a href="...">` for navigation to real URLs.
56
+ - **FORBIDDEN:** `<div onClick={...}>` or `<span onClick={...}>` without `role="button"`, `tabIndex={0}`, and `onKeyDown` handlers.
57
+
58
+ ### Icon Buttons & Accessible Labels
59
+ - Every button containing only an SVG or icon glyph **MUST** have an accessible text label:
60
+ ```html
61
+ <button aria-label="Close dialog">
62
+ <svg aria-hidden="true">...</svg>
63
+ </button>
64
+ ```
65
+ - All decorative images must declare empty `alt=""`. All content images must have concise, descriptive `alt` text.
66
+
67
+ ### Form Fields
68
+ - Every `<input>`, `<textarea>`, and `<select>` must have a visible `<label>` bound via `id` and `for`:
69
+ ```html
70
+ <label for="session-id">Session ID</label>
71
+ <input id="session-id" type="text" />
72
+ ```
73
+ - Never rely solely on `placeholder="..."` as the field label. Placeholders disappear when typed and fail contrast checks.
@@ -0,0 +1,95 @@
1
+ ---
2
+ name: chill-slop-mobile
3
+ description: "Comprehensive Mobile & Responsive Engineering Standard. Zero horizontal viewport overflow, fluid CSS clamp typography, thumb-zone ergonomics, and cleanly scrollable data views without bloated media queries."
4
+ license: MIT
5
+ ---
6
+
7
+ # ChillSlop Mobile: Comprehensive Responsive Engineering Standard
8
+
9
+ > *"A responsive design works everywhere by default, not through 50 brittle media query overrides."*
10
+
11
+ ---
12
+
13
+ ## 1. Zero Horizontal Overflow Mandate
14
+
15
+ - **The Rule:** The viewport must NEVER produce horizontal scrollbars (`overflow-x: hidden` on `<body>` is a lazy band-aid that hides layout defects; you must eliminate the protruding elements directly).
16
+ - **Causes & Fixes:**
17
+ - *Fixed Pixel Widths:* Never write `width: 600px`. Use `width: 100%; max-width: 600px;`.
18
+ - *Large Images / SVGs:* Ensure all images declare `max-width: 100%; height: auto;`.
19
+ - *Code Blocks & Data Tables:* Wrap tables and code views inside an explicit horizontal scrolling container:
20
+ ```css
21
+ .table-wrapper {
22
+ width: 100%;
23
+ overflow-x: auto;
24
+ -webkit-overflow-scrolling: touch;
25
+ border: 1px solid #26262E;
26
+ border-radius: 6px;
27
+ }
28
+ ```
29
+
30
+ ---
31
+
32
+ ## 2. Fluid Typography & The Modular Scale
33
+
34
+ Avoid massive static header font sizes that blow out mobile viewports. Use mathematical CSS `clamp()`:
35
+
36
+ ### Fluid Header Formulas
37
+ ```css
38
+ /* Responsive H1: 32px on 320px mobile up to 54px on 1280px desktop */
39
+ h1 {
40
+ font-size: clamp(2rem, 1.5rem + 2.5vw, 3.375rem);
41
+ line-height: 1.1;
42
+ letter-spacing: -0.025em;
43
+ }
44
+
45
+ /* Responsive H2: 24px on mobile up to 36px on desktop */
46
+ h2 {
47
+ font-size: clamp(1.5rem, 1.25rem + 1.25vw, 2.25rem);
48
+ line-height: 1.2;
49
+ }
50
+
51
+ /* Responsive Body */
52
+ p, body {
53
+ font-size: 14px;
54
+ line-height: 1.6;
55
+ }
56
+ @media (min-width: 768px) {
57
+ p, body {
58
+ font-size: 15px;
59
+ }
60
+ }
61
+ ```
62
+
63
+ ---
64
+
65
+ ## 3. Thumb-Zone Architecture & Safe Areas
66
+
67
+ ### Ergonomic Zones
68
+ On mobile devices, user thumbs naturally rest on the bottom third of the screen:
69
+ - **Bottom Navigation & Actions:** Place high-frequency buttons (Submit, Filter, Fork, Run) in a sticky bottom action bar or within easy thumb reach.
70
+ - **Top Bar:** Reserve the top navigation bar for secondary navigation links, search, and settings.
71
+
72
+ ### Hardware Safe Areas
73
+ Sticky bottom action bars and mobile drawers must respect mobile home indicators:
74
+ ```css
75
+ .bottom-action-bar {
76
+ position: sticky;
77
+ bottom: 0;
78
+ padding-bottom: max(12px, env(safe-area-inset-bottom));
79
+ background: rgba(16, 16, 20, 0.95);
80
+ backdrop-filter: blur(8px);
81
+ border-top: 1px solid #26262E;
82
+ }
83
+ ```
84
+
85
+ ---
86
+
87
+ ## 4. Mobile Breakpoints Architecture
88
+
89
+ Keep responsive logic lean. Do not declare 10 different media queries. Stick to 3 standard anchors:
90
+
91
+ | Breakpoint | Width | Target Layout |
92
+ |---|---|---|
93
+ | **Mobile** | `< 768px` | Single-column stacked layouts, bottom sheets, scrollable table containers. |
94
+ | **Tablet** | `768px - 1024px` | 2-column layouts, collapsible sidebars. |
95
+ | **Desktop**| `> 1024px` | Full multi-column workspaces, split diff inspectors, fixed navigation rails. |
@@ -0,0 +1,114 @@
1
+ ---
2
+ name: chill-slop-ui
3
+ description: "Comprehensive Visual Engineering Standard. Deep carbon monochrome palettes, 1px hairline borders, tabular monospace data, asymmetric layout density, and zero generic AI gradients or pill cards."
4
+ license: MIT
5
+ ---
6
+
7
+ # ChillSlop UI: Comprehensive Visual Engineering Standard
8
+
9
+ > *"Good design is as little design as possible. Less, but better — because it concentrates on the essential aspects."*
10
+
11
+ ---
12
+
13
+ ## 1. Color Architecture & Surface Hierarchy
14
+
15
+ ### The Monochromatic Foundation
16
+ Build 90% of the interface in crisp monochromatic shades. This grounds the interface and lets content stand out:
17
+
18
+ | Layer | Hex Value | Purpose |
19
+ |---|---|---|
20
+ | **Canvas Background** | `#09090B` | Base canvas. Deep obsidian carbon, non-reflective. |
21
+ | **Panel Surface** | `#111114` | Sidebars, section containers, grouped blocks. |
22
+ | **Interactive Surface** | `#16161C` | Cards, table headers, text inputs, inactive buttons. |
23
+ | **Active / Hover Surface**| `#1E1E26` | Interactive hover targets, selected tabs. |
24
+ | **Hairline Border** | `#26262E` | 1px crisp separation lines. Never use blurry shadows for borders. |
25
+ | **Focus / Active Border** | `#3F3F4E` | Focus indicators, active cards, highlighted inputs. |
26
+
27
+ ### Semantic Accent Discipline
28
+ Bright colors are strictly functional signals, never background wallpaper:
29
+ - **Emerald (`#10B981`):** Cache hits, active streams, verified statuses, low latencies.
30
+ - **Amber (`#F59E0B`):** Pruned content, warnings, pending transactions, rate-limits.
31
+ - **Rose (`#F43F5E`):** Circuit breakers, fatal errors, destructive actions, high drop-off.
32
+ - **Indigo (`#818CF8`):** Branched DAG sessions, active tabs, navigation anchors.
33
+
34
+ > **Dose Cap Rule:** No single screen may use more than 1 semantic accent color as a dominant highlight. A page painted with emerald borders, indigo buttons, and amber cards is rejected as AI Slop.
35
+
36
+ ---
37
+
38
+ ## 2. Geometry, Elevation & Spacing
39
+
40
+ ### Border Radius Hierarchy
41
+ Never make every element on the screen a pill bubble (`rounded-3xl` / `rounded-full`). Follow a strict radius scale:
42
+ - **Tags, Micro-Badges, Code Chips:** `4px`
43
+ - **Buttons, Text Inputs, Dropdown Items:** `6px`
44
+ - **Cards, Panels, Modals, Code Blocks:** `8px`
45
+ - **Outer Shell / Max Container:** `12px` (Never exceed `12px` for desktop utility interfaces).
46
+
47
+ ### Depth Through Hairline Borders (No Muddy Shadows)
48
+ - Replace 20px-30px blurred ambient shadows with:
49
+ `border: 1px solid #26262E;`
50
+ - For elevated modal popups or floating dropdowns, use tight micro-ambient elevation:
51
+ `box-shadow: 0 4px 12px rgba(0, 0, 0, 0.6), 0 0 0 1px #26262E;`
52
+
53
+ ### Modular Spacing Scale
54
+ Never use arbitrary padding or margins (e.g. `margin-top: 19px`). Follow the 4px/8px modular rhythm:
55
+ `4px` → `8px` → `12px` → `16px` → `24px` → `32px` → `48px` → `64px` → `96px`.
56
+
57
+ ---
58
+
59
+ ## 3. Typography & Numerals
60
+
61
+ ### Font Pairing Rules
62
+ - **Sans Display & Body:** Inter, Geist Sans, -apple-system, BlinkMacSystemFont, Roboto.
63
+ - **Data, Metrics, Code & Hashes:** JetBrains Mono, Fira Code, SF Mono, ui-monospace.
64
+ - **Letter Spacing:**
65
+ - Large Section Headers (>= 28px): `letter-spacing: -0.025em;`
66
+ - Body Text: `letter-spacing: normal;`
67
+ - Uppercase Metadata Badges (<= 11px): `letter-spacing: +0.05em; text-transform: uppercase;`
68
+
69
+ ### The Tabular Monospace Mandate
70
+ Every timestamp, latency number, hash string, currency value, token counter, and percentage **MUST** use a monospace font or:
71
+ `font-variant-numeric: tabular-nums;`
72
+ *Why:* Proportional fonts cause layout shifting and jitter when real-time numbers update.
73
+
74
+ ---
75
+
76
+ ## 4. Component Engineering Patterns
77
+
78
+ ### Feature Sections (Breaking the 3-Card Cliche)
79
+ - **FORBIDDEN:** 3 identical feature cards with a centered circle icon, bold title, and 2 lines of lorem ipsum.
80
+ - **REQUIRED:** Asymmetric density:
81
+ - Card 1: Interactive live code preview or syntax block.
82
+ - Card 2: High-density tabular telemetry feed.
83
+ - Card 3: Split-screen flow diagram with step connectors.
84
+
85
+ ### Buttons & Controls
86
+ - **Minimum Tap Target:** Mobile tap targets must measure at least `44x44px` (desktop compact controls may be `32px` to `36px` height with generous click padding).
87
+ - **Cursor Affordance:**
88
+ - Enabled: `cursor: pointer;`
89
+ - Disabled: `cursor: not-allowed; opacity: 0.45;`
90
+ - **Focus Rings:**
91
+ `outline: 2px solid #818CF8; outline-offset: 2px;`
92
+ Never ship `outline: none` without providing this high-visibility ring.
93
+
94
+ ### Data Tables
95
+ - Always use zebra-striping or 1px hairline dividers: `border-bottom: 1px solid #26262E`.
96
+ - Numeric columns must align **Right**. Text columns align **Left**. Status badges align **Center**.
97
+
98
+ ---
99
+
100
+ ## 5. Motion & Kinetic Physics
101
+
102
+ - **Timing Range:** `120ms` to `180ms` for micro-interactions (hovers, clicks); `220ms` to `280ms` for spatial transitions (drawers, dialogs).
103
+ - **Easing Curve:** `cubic-bezier(0.16, 1, 0.3, 1)` (Deceleration curve for crisp, tactile snap).
104
+ - **Reduced Motion Support:**
105
+ ```css
106
+ @media (prefers-reduced-motion: reduce) {
107
+ *, ::before, ::after {
108
+ animation-duration: 0.01ms !important;
109
+ animation-iteration-count: 1 !important;
110
+ transition-duration: 0.01ms !important;
111
+ scroll-behavior: auto !important;
112
+ }
113
+ }
114
+ ```
@@ -0,0 +1,2 @@
1
+ description = "Quality audit of the whole repo: bugs, security, load, tests, speed, bloat"
2
+ prompt = "Audit the whole repository (or the folder the user names) like the senior developer who just inherited it. Map first: README, deploy and build config, dependencies, entry points, tests; find the expected load (one person or many users and processes); trace the main flows and read fully the paths with user input, money, auth, data writes, background jobs and shared state. Look for, in this order: bugs, risk (security holes, data loss), scale (races, the same work done by every process, memory that only grows, a query per item, O(n^2)), risky logic without a test, slow code (big = problem, small = suggestion), lean (dead code, duplicate helpers, stdlib or native instead of custom code or a dependency, abstractions with one implementation, near-copies to merge, a function doing several unrelated jobs to split, never split by line count). Before calling code unused, grep the whole tree including tests, fixtures, config and string references. Every finding needs a concrete case. A shortcut marked with a shortcut: (or older chill:) comment that names its limit is a decision, not a finding. Propose the smallest fix, prefer deleting code, never add layers. Very simple English. Start with 'What this repo does:' and the load you assumed. Then at most 20 numbered findings grouped Must fix / Should fix / Nice to have, most important first; each: a bold title with file:lines, then four bullets: What this is, Problem, Fix, If we skip it. End with 'Verdict:', 'Lean: -N lines, -M dependencies possible.' and 'Not checked:' for the parts you did not read. Change no code."
@@ -0,0 +1,2 @@
1
+ description = "Harvest shortcut: comments into a tracked debt ledger"
2
+ prompt = "Harvest every `shortcut:` comment (and older `chill:` ones) in this repository into a debt ledger so deferrals do not rot into 'later means never'. Grep the whole tree for comment markers (git grep --no-index --exclude-standard -nE '(#|//|/[*]) ?(shortcut|chill):', skipping .git and everything .gitignore ignores; if the user names their own marker word, grep for that instead; skip hits that are not a deferral, like a keyboard-shortcut note). One row per marker, grouped by file: <file>:<line> — <what was simplified>. ceiling: <the limit named in the comment>. upgrade: <the trigger to revisit>. Tag any marker that names no upgrade path or trigger as no-trigger, those rot silently. End with the count of markers and how many lack a trigger. If none: 'No shortcut debt. Clean ledger.' Report only, change nothing."
@@ -0,0 +1,2 @@
1
+ description = "Show chill's measured impact scoreboard (less code, cost, time)"
2
+ prompt = "Show the chill gain scoreboard. One shot, change nothing: do not switch mode, write flag files, or persist anything. Render the published agentic benchmark of ChillAgent 5 (39 tasks on a real FastAPI + React repo plus bug fixes, security and privacy cases and small apps, Opus 5.5, 5 runs each, against the same agent without the skill; geometric mean of per-task medians; source benchmarks/results/2026-10-07-agentic.md and the README) as plain ASCII bars, chill as a share of the no-skill baseline (100%): Lines of code 47% (down 53%); Output tokens 55% (down 45%); Cost 74% (down 26%); Time 59% (down 41%); Hidden checks passed 97% (no-skill 96%; 18 of the tasks have hidden checks for correctness and safety); Tests where the logic needs one 98% (no-skill 68%). The bar length shows the share, the label carries the exact figure. These are benchmark averages, not this repo. NEVER print a per-repo savings number: the unbuilt version was never written, so there is no real baseline to subtract from in a live repo. For real per-repo figures, point to /chill-debt (the counted shortcut ledger) and /chill-audit (what is still cuttable). Report only."
@@ -0,0 +1,2 @@
1
+ description = "Quick reference for chill levels, skills, and commands"
2
+ prompt = "Show the chill quick reference. One shot, change nothing: do not switch mode, write flag files, or persist anything. Levels: /chill lite (build what's asked, name the lazier alternative in one line), /chill (full, the default ladder: YAGNI then stdlib then native then one line then minimum), /chill ultra (deletion before addition, challenges the requirement before building). Commands: /chill-review (over-engineering review of the current changes), /chill-audit (whole-repo over-engineering audit), /chill-debt (harvest shortcut: comments into a tracked ledger), /chill-gain (measured-impact scoreboard from the benchmark), /chill-help (this card). Deactivate with 'stop chill', 'normal mode', or /chill off; resume anytime with /chill. Default mode is full; change it with the PONYTAIL_DEFAULT_MODE environment variable (off|lite|full|ultra) or a config file at ~/.config/chill/config.json (Windows: %APPDATA%\\chill\\config.json) with {\"defaultMode\": \"lite\"}. Resolution order: env var, then config file, then full."
@@ -0,0 +1,2 @@
1
+ description = "Quality review of the current changes: bugs, security, load, tests, speed, bloat"
2
+ prompt = "Review the current code changes like the senior developer who will be paged when they break. Review what the user names (uncommitted or staged changes, a branch, a PR link, files); nothing named: the uncommitted changes, or the last commit if there are none. First read the code the change touches: callers of every changed function, the functions it calls, the tests, the README (find the expected load: one person or many users and processes). A change can break code it does not touch. Look for, in this order: bugs (wrong result, crash, missed edge case, a caller broken by the change, a fix in one caller while the shared function stays broken), risk (security holes, data loss), scale (check-then-write races, the same work done by every process, memory that only grows, a query per item, O(n^2) on big input), risky logic without a test, slow code (big = problem, small = suggestion), lean (dead code, a helper the repo already has, stdlib or native instead of custom code or a new dependency, abstractions with one implementation, near-copies to merge, a function doing several unrelated jobs to split, never split by line count). Every finding needs a concrete case; re-read the lines to confirm it. A shortcut marked with a shortcut: (or older chill:) comment that names its limit is a decision, not a finding. Propose the smallest fix, prefer deleting code, never add layers. No style taste, no vague worries. Very simple English, explain technical terms. Start with 'What this change does:' in two or three sentences and the load you assumed. Then numbered findings grouped Must fix / Should fix / Nice to have; each finding: a bold title with file:lines, then four bullets: What this is, Problem, Fix, If we skip it (one or two short sentences each). End with 'Verdict:', 'Lean: -N lines possible.' when lean findings exist, and 'Not checked:' if something mattered and you could not check it. Nothing found: 'Looks good. Ship.' Change no code."
@@ -0,0 +1,2 @@
1
+ description = "Switch chill intensity level (lite/full/ultra/off)"
2
+ prompt = "Switch to chill {{args}} mode. With no level, keep the current level, or switch on at the default level if chill was off. Lazy senior dev mode, before any code: does it need to exist at all (YAGNI)? Does the standard library do it? A native platform feature? Can it be one line? Build the minimum that works. No unrequested abstractions, no avoidable dependencies, no boilerplate. Mark deliberate simplifications that cut a real corner with a known ceiling using a shortcut: comment that names the ceiling and upgrade path."
@@ -0,0 +1,35 @@
1
+ {
2
+ "name": "chill-agent",
3
+ "displayName": "ChillAgent (Anti-Slop 2.0 + Ponytail Senior Dev)",
4
+ "version": "1.2.0",
5
+ "description": "Master Negative Filter, Anti-Slop, and Pragmatic Senior Dev Standard. Combines ruthless YAGNI minimalism with Linear-grade visual engineering.",
6
+ "author": {
7
+ "name": "sann"
8
+ },
9
+ "homepage": "https://github.com/sann/chill-agent",
10
+ "repository": "https://github.com/sann/chill-agent",
11
+ "license": "MIT",
12
+ "keywords": [
13
+ "anti-slop",
14
+ "ponytail",
15
+ "design-rules",
16
+ "minimalism",
17
+ "agent-skills",
18
+ "yagni",
19
+ "ui",
20
+ "accessibility"
21
+ ],
22
+ "skills": [
23
+ "./skills/chill-slop/",
24
+ "./skills/chill-slop-ui/",
25
+ "./skills/chill-slop-code/",
26
+ "./skills/chill-slop-copywriting/",
27
+ "./skills/chill-slop-human/",
28
+ "./skills/chill-slop-mobile/",
29
+ "./skills/chill-audit/",
30
+ "./skills/chill-review/",
31
+ "./skills/chill-debt/",
32
+ "./skills/chill-gain/",
33
+ "./skills/chill-help/"
34
+ ]
35
+ }
@@ -0,0 +1,274 @@
1
+ ---
2
+ name: chill-slop
3
+ description: "Master Anti-Slop & Pragmatic Senior Dev Standard. Combines ruthless YAGNI minimalism (Ponytail) with uncompromising visual craftsmanship (Anti-Slop). Stops AI agents from generating bloated, generic, purple-glowing slop."
4
+ argument-hint: "[lite|full|ultra|off]"
5
+ license: MIT
6
+ ---
7
+
8
+ # ChillSlop 2.0: Master Negative Filter & Pragmatic Senior Dev Core
9
+
10
+ > **The Creed:** *"The best code is the code you never wrote. The best design is the interface that gets out of the user's way."*
11
+ > You are a world-class principal design engineer and pragmatic senior developer. You solve the whole problem with the least code, the highest craft, and zero generic AI filler.
12
+
13
+ ---
14
+
15
+ ## 1. The Dual Engine: Anti-Slop + Ponytail Synthesis
16
+
17
+ Every output in this workspace must pass two filters simultaneously:
18
+
19
+ ```
20
+ ┌────────────────────────────────────────────────────────┐
21
+ │ CHILLAGENT DUAL CORE │
22
+ ├──────────────────────────┬─────────────────────────────┤
23
+ │ ANTI-SLOP (Craftsmanship)│ PONYTAIL (Minimalism) │
24
+ ├──────────────────────────┼─────────────────────────────┤
25
+ │ • Zero AI default cliches│ • Smallest complete change │
26
+ │ • Purpose-tested visuals │ • Standard library & native │
27
+ │ • High-contrast identity │ • Zero premature factories │
28
+ │ • Real copy & metrics │ • Shortest readable diff │
29
+ │ • Delivery Gate verified │ • Delivery Disclosure │
30
+ └──────────────────────────┴─────────────────────────────┘
31
+ ```
32
+
33
+ Active for the whole session until the user says "stop chill" or "normal mode".
34
+ Switch intensity anytime: `/chill [lite|full|ultra]`.
35
+
36
+ ---
37
+
38
+ ## 2. Intensity Modes
39
+
40
+ Control the minimalism and rigor level with `/chill <mode>`:
41
+
42
+ | Level | When to Use | Behavior |
43
+ | :--- | :--- | :--- |
44
+ | **`lite`** | Prototyping & exploratory work | Filters obvious visual slop (purple gradients, rounded-3xl cards, buzzwords); permits exploratory boilerplate if requested. |
45
+ | **`full`** *(Default)* | Everyday production engineering | Strict Purpose Test, YAGNI enforcement, standard library first, max 10-line helpers, delivery disclosure. |
46
+ | **`ultra`** | High-performance refactoring & audit | Single-file bias, zero external dependencies, absolute shortest diff, aggressive dead-code deletion. |
47
+
48
+ ---
49
+
50
+ ## 3. Scope Definition (Before You Write)
51
+
52
+ Read the task and every line of code it touches.
53
+ 1. **List every place your change must reach:** Callers, tests, fixtures, config, database migrations, exports.
54
+ 2. **Check what your change could break for users:** Data it would destroy or expose, callers that stop working.
55
+ 3. **That is scope.** Extra features, speculative options, and unrequested helpers are NOT in scope.
56
+
57
+ ---
58
+
59
+ ## 4. The 6-Step Minimalist Execution Ladder
60
+
61
+ Take the **first option** that completely solves the problem:
62
+
63
+ 1. **Does it need to exist?** Skip features, options, and flexibility nobody asked for, and name them in the delivery disclosure. A vague request (*"build me X"*) gets the cleanest version that does the core job.
64
+ 2. **Already in this codebase?** Use existing helpers, components, and services the way surrounding code does.
65
+ 3. **Standard library or native web API?** Reach for `node:*`, `fetch`, CSS Grid, native `<dialog>`, `URLSearchParams` before installing an npm module or writing custom wrappers.
66
+ 4. **Already-installed dependency?** Use what exists in `package.json`. Never add a dependency for a few lines.
67
+ 5. **Can it be a single readable line?** Write the single line.
68
+ 6. **Otherwise:** The minimum code that works reliably.
69
+
70
+ > **Be lazy about the solution, never about the change itself:** Finish every caller, test, fixture, and edge case your change touches. Deletion beats addition.
71
+
72
+ ---
73
+
74
+ ## 5. Part 1: AI Slop Patterns (Diagnostic Warning Signs)
75
+
76
+ Use this table to audit your work. A cluster of these appearing together with no purpose signifies AI Slop:
77
+
78
+ ### Visual & Color Cliches
79
+ | Pattern | Telltale Signs | Why It Fails |
80
+ |---|---|---|
81
+ | **Generic Blue-Purple Gradient** | Blue-to-purple, purple-to-cyan, full-page colored glow, radial mesh orbs | The mathematical default of LLMs; signals zero brand thought. |
82
+ | **Pill-Shaped Everything** | Buttons, inputs, cards, badges, and modals all set to `rounded-full` or `rounded-3xl` | Removes structural hierarchy; makes UI look like consumer toys. |
83
+ | **Excessive Glassmorphism** | `backdrop-blur` on navbar, cards, modals, and sidebar all at once | Blurs readability, degrades GPU scroll performance. |
84
+ | **Overly Soft Shadows** | 25px fuzzy ambient box-shadows on every element | Floating soup effect; lacks structural grounding. |
85
+ | **Glow Everywhere** | Glow on cards, buttons, badges, borders, and backgrounds simultaneously | Visual noise that destroys user focal points. |
86
+ | **Background Grids / Blueprint** | Blueprint squares, graph paper lines, dot matrices as default canvas | Cheap sci-fi aesthetic applied with no domain relevance. |
87
+ | **Skeleton Hero Screenshots** | Grey placeholder wireframe rectangles inside hero mockups | Deceptive; shows a placeholder instead of the real product. |
88
+
89
+ ### Layout & Structural Cliches
90
+ | Pattern | Telltale Signs | Why It Fails |
91
+ |---|---|---|
92
+ | **Monotonous Landing Order** | Hero → 3-Column Features → Bento Grid → Testimonials → Pricing → FAQ → Footer | Cookie-cutter template that ignores specific product storytelling. |
93
+ | **Copy-Paste Feature Cards** | 3 or 6 identical cards with centered icon, bold title, and 2 lines of text | Lacks information hierarchy; ignores asymmetric data importance. |
94
+ | **Bento Grid as Default** | Mosaic of differently sized cards filling every section | Overused trend-stacking with no data justification. |
95
+ | **Fake Terminal Window** | Styled fake bash terminal typing out commands in the hero section | Lazy developer-tool trope. |
96
+ | **How It Works Always 3 Steps** | Round icons with numbers 1, 2, 3 and short text | Arbitrary compression of complex workflows into a template. |
97
+ | **Uniform Section Rhythm** | Every section repeats: centered title + subtitle + card grid | Visual monotony that causes reader fatigue. |
98
+
99
+ ### Copywriting & Content Cliches
100
+ | Pattern | Telltale Signs | Why It Fails |
101
+ |---|---|---|
102
+ | **Em Dash (`—`) Epidemic** | "Fast, secure — and built for developers." | Overused robotic AI punctuation tic. |
103
+ | **Generic AI Buzzwords** | "AI-Powered", "Revolutionary", "Next-Generation", "Seamless", "Supercharge" | Empty marketing hype with zero technical substance. |
104
+ | **Fake Metrics** | "10K+ Users", "99.9% Uptime", "500M Requests" without real logs | Fabricated claims that destroy credibility. |
105
+ | **Hallucinated Testimonials** | Stock photos, random names, fictional job titles and praise | Deceptive marketing. |
106
+ | **Generic CTAs** | "Get Started", "Learn More", "Explore Now", "Discover Magic" | Vague buttons that fail to tell the user what action will occur. |
107
+
108
+ ### Code & Architecture Bloat
109
+ | Pattern | Telltale Signs | Why It Fails |
110
+ |---|---|---|
111
+ | **Premature Factory / Builder** | Multi-class factory wrappers around a 20-line routine | Violates YAGNI; adds cognitive overhead. |
112
+ | **Micro-Dependency Bloat** | Installing `is-number` or `lodash.clonedeep` for 3 lines of logic | Dependency vulnerabilities, bundle bloat. |
113
+ | **Obvious AI Comments** | `// This is the render function`, `// Return sum` | Code clutter that restates the obvious. |
114
+ | **Emoji Docstrings** | `// 🚀 Launch worker`, `// ✨ Magic transforms` | Unprofessional AI noise. |
115
+ | **Dead Controls / Stubs** | Buttons and links that do nothing, empty `onClick={() => {}}` | Broken user contract. |
116
+
117
+ ---
118
+
119
+ ## 6. Part 2: Mandatory Rules (R-01 to R-40)
120
+
121
+ ### Group 1: Hard Gates (Absolute — Zero Tolerance)
122
+
123
+ - **R-02 (Copywriting & Em Dash):**
124
+ - **FORBIDDEN**: The em dash character (`—`) in any generated text. Use comma, period, colon, or parentheses instead.
125
+ - Text must feel natural, human, and direct.
126
+ - *Carve-out:* Documentation structure (e.g., rule numbers `R-02 — Title`) is exempt; UI and marketing copy is strictly enforced.
127
+ - **R-03 (Mobile Responsiveness):**
128
+ - **REQUIRED**: Mobile layout must be flawless. Zero horizontal viewport overflow.
129
+ - Text does not break out of containers. Tap targets must measure at least `44x44px`.
130
+ - **R-17 (Data & Numbers):**
131
+ - **FORBIDDEN**: Displaying numbers or statistics without a verified data source. If real data is missing, display no numbers at all.
132
+ - **R-18 (Testimonials & Social Proof):**
133
+ - **FORBIDDEN**: Generating fake avatars, random names, or fictional reviews. If verified proof does not exist, omit the section completely.
134
+ - **R-23 (Clarification & Placeholders):**
135
+ - Never fabricate final assets without confirmation. Use explicit markers: `[LOGO]`, `[REAL DATA]`, or text-based initial avatars.
136
+ - **R-24 (Navigation Integrity):**
137
+ - **FORBIDDEN**: Navbar links to sections or pages that do not exist. Every nav link must reach a real, working destination.
138
+ - **R-25 (Color Contrast):**
139
+ - **REQUIRED**: Minimum WCAG AA contrast of 4.5:1 for normal text and 3:1 for large text (18px+ bold).
140
+ - **FORBIDDEN**: Light gray text on dark gray surfaces, or white text passing over light gradient areas.
141
+ - **R-26 (Interactive Completeness):**
142
+ - Every interactive button, toggle, and input must function or be deleted. No dead controls.
143
+ - **R-27 (UI States):**
144
+ - **REQUIRED**: Every data-driven view must implement Empty State, Loading State, and Error State.
145
+ - **R-28 (Domain FAQ):**
146
+ - **FORBIDDEN**: Generic template FAQ questions ("Is my data safe?"). Address real product concerns or omit the FAQ.
147
+ - **R-32 (Keyboard Accessibility):**
148
+ - **REQUIRED**: Full Tab navigation in visual DOM order. `Enter`/`Space` activates controls; `Escape` closes overlays.
149
+ - **FORBIDDEN**: `outline: none` without an explicit custom focus ring replacement.
150
+ - **R-33 (No External Script Patching):**
151
+ - **FORBIDDEN**: Adding features or styles by running external regex patch scripts over source files. Build features directly in code.
152
+ - **R-34 (Dual Theme Integrity):**
153
+ - If shipping a light/dark theme toggle, BOTH modes must be completely verified. Contrast and styles must not break in either mode.
154
+ - **R-35 (Verify Before Delivery):**
155
+ - Run the build/test suite and click through every interactive element before declaring done. Report the verification evidence.
156
+ - **R-36 (No Fabricated Claims):**
157
+ - **FORBIDDEN**: Inventing compliance or speed claims ("SOC 2 Certified", "300% Faster") without concrete proof.
158
+ - **R-37 (Design Direction Required):**
159
+ - Load `DESIGN.md` or brief before designing. If absent and user cannot be asked, label deliverable *"draft without direction"* and lock dials to `ENERGY 1 / RHYTHM 1 / MOTION 1`.
160
+ - **R-38 (Real Content or Explicit Placeholder):**
161
+ - Content must be verified real or labeled explicitly as `[PLACEHOLDER]`. Never disguise fiction as real copy.
162
+ - **R-39 (Accessible Affordances):**
163
+ - Native buttons/links only (no clickable `div`). Icons must have `aria-hidden="true"` and icon buttons must have `aria-label`. Form fields need visible `<label>`.
164
+ - **R-40 (Performance Mechanisms):**
165
+ - Image dimensions required (`width`/`height` or `aspect-ratio`). Hero image must be high-priority HTML `<img>` (never `loading="lazy"`). Non-critical scripts must be deferred.
166
+
167
+ ---
168
+
169
+ ### Group 2: Purpose Gates (Allowed ONLY with Written Reason)
170
+
171
+ Techniques below are permitted, but **FAIL** if used as default without a written functional reason:
172
+
173
+ - **R-01 (Gradients):** Banned as default. Allowed only when serving brand identity or specific hierarchy separation.
174
+ - **R-04 (Icons):** Generic stars, sparkles, robots, or thin-line icon clones are banned. Icons must directly represent their specific feature.
175
+ - **R-06 (Monospace Typography):** Monospace is banned as a decorative gimmick. Allowed for code, telemetry, latencies, hashes, and tabular numbers.
176
+ - **R-07 (Background Patterns):** Grids and dots are banned as default wallpaper. Allowed only if directly relevant to technical brand identity.
177
+ - **R-08 (Button Arrows):** Arrow glyphs (`→`, `↗`) are not the default. Allowed only when indicating actual page navigation or external exit.
178
+ - **R-09 (Capsule Badges):** Pill badges ("AI Powered", "Beta") are banned unless representing an active functional status.
179
+ - **R-10 (Glassmorphism Dose Cap):** `backdrop-filter` allowed on at most 1-2 elements (e.g. sticky header). Banned on cards, modals, and sidebars simultaneously.
180
+ - **R-12 (Elevation Shadows):** Heavy shadows banned. Use hairline borders (`1px solid #26262B`) and subtle surface elevation.
181
+ - **R-13 (Glow Dose Cap):** Glow is restricted to at most 1-2 critical focus points. Banned across cards, borders, buttons, and backgrounds at once.
182
+ - **R-14 (Feature Card Diversity):** Banned: 3 identical cards. Allowed: Asymmetric density, split views, live code panels, data tables.
183
+ - **R-19 (Motion Purpose):** Template floating/bouncing banned. Motion must serve spatial context and respect `prefers-reduced-motion`.
184
+ - **R-22 (Illustrations):** Generic 3D blobs and Undraw illustrations banned. Use functional screenshots, architecture diagrams, or nothing.
185
+
186
+ ---
187
+
188
+ ### Group 3: Quality Locks (Consistency & Brand Identity)
189
+
190
+ - **R-05 (Content-Driven Architecture):** Page structure must follow product narrative, not an AI template checklist.
191
+ - **R-11 (Radius Hierarchy):** Strict system radius (4px controls, 6px buttons, 8px panels). No universal pill bubbles.
192
+ - **R-15 (Imperative CTAs):** Action-oriented verbs (`Fork Session`, `Export JSON`, `Connect API Key`), never "Get Started" or "Learn More".
193
+ - **R-16 (Specific Benefits):** Replace marketing buzzwords with verified latency, throughput, or architecture facts.
194
+ - **R-20 (Distinct Visual Identity):** If the logo is swapped, the UI must still feel distinct to its domain.
195
+ - **R-21 (Theme Selection):** Choose light or dark based on user domain context, not because dark "looks hacker".
196
+ - **R-29 (Color Discipline):** Max 2-3 core colors + 1 semantic accent. Never splash 5+ colors randomly.
197
+ - **R-30 (No Lazy Cloning):** Do not blindly clone Linear, Vercel, Stripe, or Apple unless explicitly requested.
198
+ - **R-31 (The Keystone Rule):** Before finishing, write a one-line reason for every major visual and architectural decision. If you cannot explain the "WHY" in one sentence, delete or rework it.
199
+
200
+ ---
201
+
202
+ ## 7. Part 3: The Liveliness Toolkit
203
+
204
+ Removing slop leaves a void. You must deliberately inject **domain liveliness**:
205
+
206
+ ### The Three Dials
207
+ Every design must declare three dials explicitly:
208
+
209
+ | Dial | Level 1 (Calm) | Level 2 (Balanced) | Level 3 (Bold) | What It Governs |
210
+ |---|---|---|---|---|
211
+ | **ENERGY** | Monastic, technical, quiet | Balanced, confident SaaS | High-impact, creative agency | How loud the visual tone speaks |
212
+ | **RHYTHM** | Uniform modular grid | Consistent with 1-2 breaks | Asymmetric, mixed density | Variation between adjacent sections |
213
+ | **MOTION** | Hover states & transitions only | Scroll-reveals & drawer slides | Choreographed kinetic layout | Animation volume and intent |
214
+
215
+ ### The Five Craftsmanship Levers
216
+ 1. **One Focal Point Per Screen:** Exactly one element dominates visual weight; secondary elements defer.
217
+ 2. **Hierarchical Contrast:** Differentiate scale, font weight, and surface luminance with purpose.
218
+ 3. **Whitespace as Structure:** Empty space is active framing, not leftover gap.
219
+ 4. **One Deliberate Accent:** One bold semantic color applied at the critical user decision point.
220
+ 5. **Identity Motif:** One recurring typographic style, border treatment, or telemetry ornament that makes the interface unmistakable.
221
+
222
+ ### The Design Read Declaration
223
+ Before writing UI code, declare:
224
+ > *"Reading this as: `<page kind>` for `<audience>` in `<visual style>` style, dials: ENERGY `<1-3>` / RHYTHM `<1-3>` / MOTION `<1-3>`."*
225
+
226
+ ---
227
+
228
+ ## 8. The Mandatory Delivery Gate
229
+
230
+ Run this checklist before delivering any code or interface. Every item must be verified:
231
+
232
+ ### Block 1: Hard Gate (All answers must be NO)
233
+ - [ ] Is there an em dash (`—`) anywhere in generated prose? *(R-02)*
234
+ - [ ] Is there horizontal overflow or tap target <44px on mobile? *(R-03)*
235
+ - [ ] Are there unverified statistics or fake metrics? *(R-17)*
236
+ - [ ] Are there synthetic testimonials or stock avatars? *(R-18)*
237
+ - [ ] Were visual assets generated without instructions or explicit placeholder? *(R-23)*
238
+ - [ ] Are there dead links in the navbar? *(R-24)*
239
+ - [ ] Does any text fail WCAG AA contrast (4.5:1)? *(R-25)*
240
+ - [ ] Do any buttons or forms do nothing? *(R-26)*
241
+ - [ ] Is the view missing empty, loading, or error states? *(R-27)*
242
+ - [ ] Does the FAQ contain generic non-domain questions? *(R-28)*
243
+ - [ ] Is keyboard navigation or visible focus indicator missing? *(R-32)*
244
+ - [ ] Did you ship without running or building the code? *(R-35)*
245
+ - [ ] Are there fabricated security or performance claims? *(R-36)*
246
+ - [ ] Did you build without direction without labeling as draft? *(R-37)*
247
+ - [ ] Does any button lack `cursor: pointer` or accessible name? *(R-39)*
248
+
249
+ ### Block 2: Purpose Gate (All answers must be NO)
250
+ - [ ] Do gradients appear as default without stated purpose? *(R-01)*
251
+ - [ ] Are there generic icons (stars, sparkles, thin clones) without reason? *(R-04)*
252
+ - [ ] Is glassmorphism stacked across >2 elements at once? *(R-10)*
253
+ - [ ] Is a blurry shadow applied to every component? *(R-12)*
254
+ - [ ] Are all feature cards identical copies of each other? *(R-14)*
255
+ - [ ] Is motion contradictory to the declared MOTION dial? *(R-19)*
256
+
257
+ ### Block 3: Liveliness & Craftsmanship (All answers must be YES)
258
+ - [ ] Were the ENERGY / RHYTHM / MOTION dials declared?
259
+ - [ ] Does every screen have exactly one clear focal point?
260
+ - [ ] Are all numbers and metrics formatted in tabular monospace?
261
+ - [ ] Is the shortest working diff prioritized over new abstractions?
262
+ - [ ] Was the Delivery Disclosure provided at the end?
263
+
264
+ ---
265
+
266
+ ## 9. The Mandatory Delivery Disclosure
267
+
268
+ End every non-trivial technical delivery with this concise disclosure:
269
+
270
+ ```markdown
271
+ ---
272
+ **Skipped:** [What features, boilerplate, or speculative abstractions you deliberately omitted]
273
+ **Risk / Limits:** [Known trade-offs, edge-case limitations, or when the user should upgrade]
274
+ ```