akili-specs 2.1.0
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/.claude/commands/akili-archive.md +145 -0
- package/.claude/commands/akili-audit.md +97 -0
- package/.claude/commands/akili-constitution.md +413 -0
- package/.claude/commands/akili-execute.md +240 -0
- package/.claude/commands/akili-propose.md +167 -0
- package/.claude/commands/akili-seo.md +277 -0
- package/.claude/commands/akili-specify.md +320 -0
- package/.claude/commands/akili-test.md +141 -0
- package/.claude/commands/akili-validate.md +176 -0
- package/.claude/skills/angular-developer/SKILL.md +130 -0
- package/.claude/skills/angular-developer/references/angular-animations.md +160 -0
- package/.claude/skills/angular-developer/references/angular-aria.md +410 -0
- package/.claude/skills/angular-developer/references/cli.md +86 -0
- package/.claude/skills/angular-developer/references/component-harnesses.md +59 -0
- package/.claude/skills/angular-developer/references/component-styling.md +91 -0
- package/.claude/skills/angular-developer/references/components.md +117 -0
- package/.claude/skills/angular-developer/references/creating-services.md +97 -0
- package/.claude/skills/angular-developer/references/data-resolvers.md +69 -0
- package/.claude/skills/angular-developer/references/define-routes.md +67 -0
- package/.claude/skills/angular-developer/references/defining-providers.md +72 -0
- package/.claude/skills/angular-developer/references/di-fundamentals.md +120 -0
- package/.claude/skills/angular-developer/references/e2e-testing.md +66 -0
- package/.claude/skills/angular-developer/references/effects.md +83 -0
- package/.claude/skills/angular-developer/references/hierarchical-injectors.md +43 -0
- package/.claude/skills/angular-developer/references/host-elements.md +80 -0
- package/.claude/skills/angular-developer/references/injection-context.md +63 -0
- package/.claude/skills/angular-developer/references/inputs.md +101 -0
- package/.claude/skills/angular-developer/references/linked-signal.md +59 -0
- package/.claude/skills/angular-developer/references/loading-strategies.md +61 -0
- package/.claude/skills/angular-developer/references/mcp.md +106 -0
- package/.claude/skills/angular-developer/references/migrations.md +30 -0
- package/.claude/skills/angular-developer/references/navigate-to-routes.md +69 -0
- package/.claude/skills/angular-developer/references/outputs.md +86 -0
- package/.claude/skills/angular-developer/references/reactive-forms.md +122 -0
- package/.claude/skills/angular-developer/references/rendering-strategies.md +44 -0
- package/.claude/skills/angular-developer/references/resource.md +74 -0
- package/.claude/skills/angular-developer/references/route-animations.md +56 -0
- package/.claude/skills/angular-developer/references/route-guards.md +52 -0
- package/.claude/skills/angular-developer/references/router-lifecycle.md +45 -0
- package/.claude/skills/angular-developer/references/router-testing.md +87 -0
- package/.claude/skills/angular-developer/references/show-routes-with-outlets.md +68 -0
- package/.claude/skills/angular-developer/references/signal-forms.md +897 -0
- package/.claude/skills/angular-developer/references/signals-overview.md +94 -0
- package/.claude/skills/angular-developer/references/tailwind-css.md +69 -0
- package/.claude/skills/angular-developer/references/template-driven-forms.md +114 -0
- package/.claude/skills/angular-developer/references/testing-fundamentals.md +66 -0
- package/.claude/skills/api-design-principles/SKILL.md +528 -0
- package/.claude/skills/api-design-principles/assets/api-design-checklist.md +155 -0
- package/.claude/skills/api-design-principles/assets/rest-api-template.py +182 -0
- package/.claude/skills/api-design-principles/references/graphql-schema-design.md +583 -0
- package/.claude/skills/api-design-principles/references/rest-best-practices.md +408 -0
- package/.claude/skills/aws-serverless/SKILL.md +323 -0
- package/.claude/skills/brainstorming/SKILL.md +96 -0
- package/.claude/skills/error-handling-patterns/SKILL.md +641 -0
- package/.claude/skills/frontend-design/LICENSE.txt +177 -0
- package/.claude/skills/frontend-design/SKILL.md +272 -0
- package/.claude/skills/gsap-core/SKILL.md +254 -0
- package/.claude/skills/gsap-frameworks/SKILL.md +153 -0
- package/.claude/skills/gsap-performance/SKILL.md +79 -0
- package/.claude/skills/gsap-plugins/SKILL.md +426 -0
- package/.claude/skills/gsap-react/SKILL.md +136 -0
- package/.claude/skills/gsap-scrolltrigger/SKILL.md +296 -0
- package/.claude/skills/gsap-timeline/SKILL.md +107 -0
- package/.claude/skills/gsap-utils/SKILL.md +284 -0
- package/.claude/skills/judgment-day/SKILL.md +52 -0
- package/.claude/skills/nestjs-expert/SKILL.md +552 -0
- package/.claude/skills/product-manager-toolkit/SKILL.md +351 -0
- package/.claude/skills/product-manager-toolkit/references/prd_templates.md +317 -0
- package/.claude/skills/product-manager-toolkit/scripts/customer_interview_analyzer.py +441 -0
- package/.claude/skills/product-manager-toolkit/scripts/rice_prioritizer.py +296 -0
- package/.claude/skills/react-doctor/AGENTS.md +15 -0
- package/.claude/skills/react-doctor/SKILL.md +19 -0
- package/.claude/skills/seo-audit/SKILL.md +497 -0
- package/.claude/skills/seo-audit/evals/evals.json +136 -0
- package/.claude/skills/seo-audit/references/ai-writing-detection.md +200 -0
- package/.claude/skills/seo-audit/references/international-seo.md +230 -0
- package/.claude/skills/shadcn-ui/SKILL.md +1677 -0
- package/.claude/skills/shadcn-ui/references/learn.md +145 -0
- package/.claude/skills/shadcn-ui/references/official-ui-reference.md +1725 -0
- package/.claude/skills/shadcn-ui/references/reference.md +586 -0
- package/.claude/skills/shadcn-ui/references/ui-reference.md +1578 -0
- package/.claude/skills/stitch-design/README.md +50 -0
- package/.claude/skills/stitch-design/SKILL.md +84 -0
- package/.claude/skills/stitch-design/examples/DESIGN.md +22 -0
- package/.claude/skills/stitch-design/examples/enhanced-prompt.md +28 -0
- package/.claude/skills/stitch-design/references/design-mappings.md +45 -0
- package/.claude/skills/stitch-design/references/prompt-keywords.md +114 -0
- package/.claude/skills/stitch-design/references/tool-schemas.md +76 -0
- package/.claude/skills/stitch-design/workflows/edit-design.md +44 -0
- package/.claude/skills/stitch-design/workflows/generate-design-md.md +63 -0
- package/.claude/skills/stitch-design/workflows/text-to-design.md +47 -0
- package/.claude/skills/systematic-debugging/CREATION-LOG.md +119 -0
- package/.claude/skills/systematic-debugging/SKILL.md +296 -0
- package/.claude/skills/systematic-debugging/condition-based-waiting-example.ts +158 -0
- package/.claude/skills/systematic-debugging/condition-based-waiting.md +115 -0
- package/.claude/skills/systematic-debugging/defense-in-depth.md +122 -0
- package/.claude/skills/systematic-debugging/find-polluter.sh +63 -0
- package/.claude/skills/systematic-debugging/root-cause-tracing.md +169 -0
- package/.claude/skills/systematic-debugging/test-academic.md +14 -0
- package/.claude/skills/systematic-debugging/test-pressure-1.md +58 -0
- package/.claude/skills/systematic-debugging/test-pressure-2.md +68 -0
- package/.claude/skills/systematic-debugging/test-pressure-3.md +69 -0
- package/.claude/skills/tailwind-design-system/SKILL.md +874 -0
- package/.claude/skills/ui-ux-pro-max/SKILL.md +377 -0
- package/.claude/skills/ui-ux-pro-max/data/charts.csv +26 -0
- package/.claude/skills/ui-ux-pro-max/data/colors.csv +97 -0
- package/.claude/skills/ui-ux-pro-max/data/icons.csv +101 -0
- package/.claude/skills/ui-ux-pro-max/data/landing.csv +31 -0
- package/.claude/skills/ui-ux-pro-max/data/products.csv +97 -0
- package/.claude/skills/ui-ux-pro-max/data/react-performance.csv +45 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/astro.csv +54 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/flutter.csv +53 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/html-tailwind.csv +56 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/jetpack-compose.csv +53 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/nextjs.csv +53 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/nuxt-ui.csv +51 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/nuxtjs.csv +59 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/react-native.csv +52 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/react.csv +54 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/shadcn.csv +61 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/svelte.csv +54 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/swiftui.csv +51 -0
- package/.claude/skills/ui-ux-pro-max/data/stacks/vue.csv +50 -0
- package/.claude/skills/ui-ux-pro-max/data/styles.csv +68 -0
- package/.claude/skills/ui-ux-pro-max/data/typography.csv +58 -0
- package/.claude/skills/ui-ux-pro-max/data/ui-reasoning.csv +101 -0
- package/.claude/skills/ui-ux-pro-max/data/ux-guidelines.csv +100 -0
- package/.claude/skills/ui-ux-pro-max/data/web-interface.csv +31 -0
- package/.claude/skills/ui-ux-pro-max/scripts/core.py +253 -0
- package/.claude/skills/ui-ux-pro-max/scripts/design_system.py +1067 -0
- package/.claude/skills/ui-ux-pro-max/scripts/search.py +114 -0
- package/.claude/skills/vercel-react-best-practices/AGENTS.md +2934 -0
- package/.claude/skills/vercel-react-best-practices/SKILL.md +136 -0
- package/.claude/skills/vercel-react-best-practices/rules/advanced-event-handler-refs.md +55 -0
- package/.claude/skills/vercel-react-best-practices/rules/advanced-init-once.md +42 -0
- package/.claude/skills/vercel-react-best-practices/rules/advanced-use-latest.md +39 -0
- package/.claude/skills/vercel-react-best-practices/rules/async-api-routes.md +38 -0
- package/.claude/skills/vercel-react-best-practices/rules/async-defer-await.md +80 -0
- package/.claude/skills/vercel-react-best-practices/rules/async-dependencies.md +51 -0
- package/.claude/skills/vercel-react-best-practices/rules/async-parallel.md +28 -0
- package/.claude/skills/vercel-react-best-practices/rules/async-suspense-boundaries.md +99 -0
- package/.claude/skills/vercel-react-best-practices/rules/bundle-barrel-imports.md +59 -0
- package/.claude/skills/vercel-react-best-practices/rules/bundle-conditional.md +31 -0
- package/.claude/skills/vercel-react-best-practices/rules/bundle-defer-third-party.md +49 -0
- package/.claude/skills/vercel-react-best-practices/rules/bundle-dynamic-imports.md +35 -0
- package/.claude/skills/vercel-react-best-practices/rules/bundle-preload.md +50 -0
- package/.claude/skills/vercel-react-best-practices/rules/client-event-listeners.md +74 -0
- package/.claude/skills/vercel-react-best-practices/rules/client-localstorage-schema.md +71 -0
- package/.claude/skills/vercel-react-best-practices/rules/client-passive-event-listeners.md +48 -0
- package/.claude/skills/vercel-react-best-practices/rules/client-swr-dedup.md +56 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-batch-dom-css.md +107 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-cache-function-results.md +80 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-cache-property-access.md +28 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-cache-storage.md +70 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-combine-iterations.md +32 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-early-exit.md +50 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-hoist-regexp.md +45 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-index-maps.md +37 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-length-check-first.md +49 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-min-max-loop.md +82 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-set-map-lookups.md +24 -0
- package/.claude/skills/vercel-react-best-practices/rules/js-tosorted-immutable.md +57 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-activity.md +26 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-animate-svg-wrapper.md +47 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-conditional-render.md +40 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-content-visibility.md +38 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-hoist-jsx.md +46 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-hydration-no-flicker.md +82 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-hydration-suppress-warning.md +30 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-svg-precision.md +28 -0
- package/.claude/skills/vercel-react-best-practices/rules/rendering-usetransition-loading.md +75 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-defer-reads.md +39 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-dependencies.md +45 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-derived-state-no-effect.md +40 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-derived-state.md +29 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-functional-setstate.md +74 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-lazy-state-init.md +58 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-memo-with-default-value.md +38 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-memo.md +44 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-move-effect-to-event.md +45 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-simple-expression-in-memo.md +35 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-transitions.md +40 -0
- package/.claude/skills/vercel-react-best-practices/rules/rerender-use-ref-transient-values.md +73 -0
- package/.claude/skills/vercel-react-best-practices/rules/server-after-nonblocking.md +73 -0
- package/.claude/skills/vercel-react-best-practices/rules/server-auth-actions.md +96 -0
- package/.claude/skills/vercel-react-best-practices/rules/server-cache-lru.md +41 -0
- package/.claude/skills/vercel-react-best-practices/rules/server-cache-react.md +76 -0
- package/.claude/skills/vercel-react-best-practices/rules/server-dedup-props.md +65 -0
- package/.claude/skills/vercel-react-best-practices/rules/server-parallel-fetching.md +83 -0
- package/.claude/skills/vercel-react-best-practices/rules/server-serialization.md +38 -0
- package/.claude/templates/implementer.md +36 -0
- package/.claude/templates/leader.md +77 -0
- package/.claude/templates/reviewer.md +53 -0
- package/.mcp.json.example +12 -0
- package/CHANGELOG.md +243 -0
- package/LICENSE +21 -0
- package/README.md +795 -0
- package/assets/jc-fox-mark.svg +10 -0
- package/assets/jc-methodology-badge.png +0 -0
- package/bin/akili.js +574 -0
- package/docs/README.md +48 -0
- package/docs/cli.md +187 -0
- package/docs/commands/README.md +43 -0
- package/docs/commands/akili-archive.md +65 -0
- package/docs/commands/akili-constitution.md +91 -0
- package/docs/commands/akili-execute.md +93 -0
- package/docs/commands/akili-propose.md +65 -0
- package/docs/commands/akili-seo.md +75 -0
- package/docs/commands/akili-specify.md +69 -0
- package/docs/commands/akili-test.md +65 -0
- package/docs/commands/akili-validate.md +64 -0
- package/docs/flow.md +255 -0
- package/docs/model-routing.md +133 -0
- package/docs/openspec-comparison.md +42 -0
- package/docs/plans/2026-05-26-multi-agent-sdd-orchestration-design.md +105 -0
- package/docs/release-checklist.md +91 -0
- package/docs/skills/README.md +42 -0
- package/docs/skills/angular-developer.md +23 -0
- package/docs/skills/api-design-principles.md +22 -0
- package/docs/skills/aws-serverless.md +22 -0
- package/docs/skills/brainstorming.md +21 -0
- package/docs/skills/error-handling-patterns.md +22 -0
- package/docs/skills/frontend-design.md +23 -0
- package/docs/skills/gsap-core.md +21 -0
- package/docs/skills/gsap-frameworks.md +20 -0
- package/docs/skills/gsap-performance.md +21 -0
- package/docs/skills/gsap-plugins.md +20 -0
- package/docs/skills/gsap-react.md +22 -0
- package/docs/skills/gsap-scrolltrigger.md +21 -0
- package/docs/skills/gsap-timeline.md +20 -0
- package/docs/skills/gsap-utils.md +21 -0
- package/docs/skills/nestjs-expert.md +23 -0
- package/docs/skills/product-manager-toolkit.md +22 -0
- package/docs/skills/react-doctor.md +27 -0
- package/docs/skills/seo-audit.md +27 -0
- package/docs/skills/shadcn-ui.md +22 -0
- package/docs/skills/stitch-design.md +21 -0
- package/docs/skills/systematic-debugging.md +27 -0
- package/docs/skills/tailwind-design-system.md +23 -0
- package/docs/skills/ui-ux-pro-max.md +25 -0
- package/docs/skills/vercel-react-best-practices.md +22 -0
- package/package.json +50 -0
- package/scripts/gsc_verify.py +162 -0
- package/scripts/parse_tests.js +112 -0
package/docs/cli.md
ADDED
|
@@ -0,0 +1,187 @@
|
|
|
1
|
+
# CLI Reference
|
|
2
|
+
|
|
3
|
+
The `akili` CLI installs the AKILI command prompts, skills, and helper resources into Claude Code, OpenCode, Google Antigravity, or multiple tools.
|
|
4
|
+
|
|
5
|
+
## Install
|
|
6
|
+
|
|
7
|
+
### Interactive Mode (Recommended)
|
|
8
|
+
|
|
9
|
+
Run the CLI without arguments or use the `init` command to launch an interactive wizard. It will guide you through selecting the target tools and choosing between global or local installation:
|
|
10
|
+
|
|
11
|
+
```bash
|
|
12
|
+
pnpm dlx akili-specs
|
|
13
|
+
# or
|
|
14
|
+
akili init
|
|
15
|
+
```
|
|
16
|
+
|
|
17
|
+
### Manual Installation
|
|
18
|
+
|
|
19
|
+
Run directly from npm:
|
|
20
|
+
|
|
21
|
+
```bash
|
|
22
|
+
pnpm dlx akili-specs install --tool claude
|
|
23
|
+
pnpm dlx akili-specs install --tool opencode
|
|
24
|
+
pnpm dlx akili-specs install --tool antigravity
|
|
25
|
+
pnpm dlx akili-specs install --tool both
|
|
26
|
+
pnpm dlx akili-specs install --tool all
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
Claude is the default target:
|
|
30
|
+
|
|
31
|
+
```bash
|
|
32
|
+
pnpm dlx akili-specs install
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
Use a persistent global install if preferred:
|
|
36
|
+
|
|
37
|
+
```bash
|
|
38
|
+
pnpm add -g akili-specs
|
|
39
|
+
akili install --tool all
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
To install directly into the local project workspace instead of globally, use the `--local` flag:
|
|
43
|
+
|
|
44
|
+
```bash
|
|
45
|
+
akili install --tool both --local
|
|
46
|
+
```
|
|
47
|
+
|
|
48
|
+
## Commands
|
|
49
|
+
|
|
50
|
+
| Command | Purpose |
|
|
51
|
+
|---|---|
|
|
52
|
+
| `akili init` | Interactive setup wizard for installation |
|
|
53
|
+
| `akili install` | Install commands, skills, and helper resources |
|
|
54
|
+
| `akili update` | Reinstall packaged commands, skills, and helper resources |
|
|
55
|
+
| `akili list` | List packaged commands, skills, and helper resources |
|
|
56
|
+
| `akili doctor` | Check whether expected files are installed |
|
|
57
|
+
| `akili help` | Show help |
|
|
58
|
+
|
|
59
|
+
## Options
|
|
60
|
+
|
|
61
|
+
| Option | Applies To | Purpose |
|
|
62
|
+
|---|---|---|
|
|
63
|
+
| `--tool claude` | install, update, doctor | Target Claude Code config |
|
|
64
|
+
| `--tool opencode` | install, update, doctor | Target OpenCode config |
|
|
65
|
+
| `--tool antigravity` | install, update, doctor | Target Google Antigravity config |
|
|
66
|
+
| `--tool both` | install, update, doctor | Target Claude and OpenCode |
|
|
67
|
+
| `--tool all` | install, update, doctor | Target Claude, OpenCode, and Antigravity |
|
|
68
|
+
| `--target <path>` | single-tool install/update/doctor | Override the selected tool target directory |
|
|
69
|
+
| `--claude-target <path>` | multiple tools | Override Claude target directory |
|
|
70
|
+
| `--opencode-target <path>` | multiple tools | Override OpenCode target directory |
|
|
71
|
+
| `--antigravity-target <path>` | multiple tools | Override Antigravity target directory |
|
|
72
|
+
| `--local`, `-l` | install, update, doctor | Target the current project directory (e.g., `./.claude`) instead of the global home directory |
|
|
73
|
+
| `--force` | install, update | Overwrite existing files |
|
|
74
|
+
| `--dry-run` | install, update | Show planned writes without writing files |
|
|
75
|
+
| `--commands-only` | install, update, doctor | Only install or check commands |
|
|
76
|
+
| `--skills-only` | install, update, doctor | Only install or check skills |
|
|
77
|
+
| `--fix` | doctor | Automatically repair and copy missing files |
|
|
78
|
+
|
|
79
|
+
`--commands-only` and `--skills-only` are mutually exclusive.
|
|
80
|
+
|
|
81
|
+
## Install Targets
|
|
82
|
+
|
|
83
|
+
Default targets:
|
|
84
|
+
|
|
85
|
+
```text
|
|
86
|
+
Claude: ~/.claude
|
|
87
|
+
OpenCode: ~/.config/opencode
|
|
88
|
+
Antigravity: ~/.gemini
|
|
89
|
+
```
|
|
90
|
+
|
|
91
|
+
Claude install layout:
|
|
92
|
+
|
|
93
|
+
```text
|
|
94
|
+
~/.claude/commands/
|
|
95
|
+
~/.claude/skills/
|
|
96
|
+
~/.claude/akili/scripts/
|
|
97
|
+
~/.claude/akili/templates/ (leader.md, implementer.md, reviewer.md — used by /akili-constitution to scaffold project .agents/)
|
|
98
|
+
~/.claude/akili/.mcp.json.example
|
|
99
|
+
```
|
|
100
|
+
|
|
101
|
+
OpenCode install layout:
|
|
102
|
+
|
|
103
|
+
```text
|
|
104
|
+
~/.config/opencode/commands/
|
|
105
|
+
~/.config/opencode/skills/
|
|
106
|
+
~/.config/opencode/akili/scripts/
|
|
107
|
+
~/.config/opencode/akili/templates/
|
|
108
|
+
~/.config/opencode/akili/.mcp.json.example
|
|
109
|
+
```
|
|
110
|
+
|
|
111
|
+
Antigravity install layout:
|
|
112
|
+
|
|
113
|
+
```text
|
|
114
|
+
~/.gemini/antigravity/global_workflows/ (custom commands mapped as global workflows)
|
|
115
|
+
~/.gemini/config/skills/ (skills mapped as global skills)
|
|
116
|
+
~/.gemini/config/akili/scripts/ (scripts mapped as config resources)
|
|
117
|
+
~/.gemini/config/akili/templates/ (multi-agent harness templates: leader, implementer, reviewer)
|
|
118
|
+
~/.gemini/config/akili/.mcp.json.example
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
Restart Claude Code, OpenCode, or Google Antigravity after install/update so running sessions load new commands and skills.
|
|
122
|
+
|
|
123
|
+
## Safety Rules
|
|
124
|
+
|
|
125
|
+
- Existing files are skipped by default.
|
|
126
|
+
- Use `--force` to overwrite old installed files.
|
|
127
|
+
- Use `--dry-run` before changing custom targets.
|
|
128
|
+
- `update` is intentionally the same safe copy behavior as `install` unless `--force` is provided.
|
|
129
|
+
|
|
130
|
+
## Examples
|
|
131
|
+
|
|
132
|
+
Preview a three-tool install:
|
|
133
|
+
|
|
134
|
+
```bash
|
|
135
|
+
akili install --tool all --dry-run
|
|
136
|
+
```
|
|
137
|
+
|
|
138
|
+
Install Claude commands into a local project folder:
|
|
139
|
+
|
|
140
|
+
```bash
|
|
141
|
+
akili install --tool claude --target ./.claude
|
|
142
|
+
```
|
|
143
|
+
|
|
144
|
+
Install both tools into custom directories:
|
|
145
|
+
|
|
146
|
+
```bash
|
|
147
|
+
akili install --tool both --claude-target ./.claude --opencode-target ./.opencode
|
|
148
|
+
```
|
|
149
|
+
|
|
150
|
+
Update Antigravity skills only:
|
|
151
|
+
|
|
152
|
+
```bash
|
|
153
|
+
akili update --tool antigravity --skills-only --force
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
Check all installs:
|
|
157
|
+
|
|
158
|
+
```bash
|
|
159
|
+
akili doctor --tool all
|
|
160
|
+
```
|
|
161
|
+
|
|
162
|
+
## Packaged Resources
|
|
163
|
+
|
|
164
|
+
The CLI installs helper resources under the target `akili/` directory:
|
|
165
|
+
|
|
166
|
+
| Resource | Purpose |
|
|
167
|
+
|---|---|
|
|
168
|
+
| `scripts/gsc_verify.py` | Google Site Verification helper used by `/akili-seo` |
|
|
169
|
+
| `scripts/parse_tests.js` | Jest/Vitest JSON test-output parser used by `/akili-test` to generate the requirement-to-test matrix |
|
|
170
|
+
| `templates/leader.md` | Default Leader (Orchestrator) persona for the multi-agent harness — copied into project `.agents/` by `/akili-constitution` |
|
|
171
|
+
| `templates/implementer.md` | Default Implementer persona for the multi-agent harness |
|
|
172
|
+
| `templates/reviewer.md` | Default Reviewer persona for the multi-agent harness |
|
|
173
|
+
| `.mcp.json.example` | Example MCP config for the Google Search Console MCP server |
|
|
174
|
+
|
|
175
|
+
## Troubleshooting
|
|
176
|
+
|
|
177
|
+
If commands do not appear in your AI tool:
|
|
178
|
+
|
|
179
|
+
- Run `akili doctor --tool <claude|opencode|antigravity|both|all>`.
|
|
180
|
+
- Restart Claude Code, OpenCode, or Google Antigravity.
|
|
181
|
+
- Confirm the target directory is the one your tool reads.
|
|
182
|
+
- Re-run with `--force` if older files should be replaced.
|
|
183
|
+
|
|
184
|
+
If helper resources are missing:
|
|
185
|
+
|
|
186
|
+
- Run `akili doctor --tool <target>` without `--commands-only` or `--skills-only`.
|
|
187
|
+
- Re-run `akili install --tool <target> --force`.
|
|
@@ -0,0 +1,43 @@
|
|
|
1
|
+
# Command Reference
|
|
2
|
+
|
|
3
|
+
AKILI commands are installed as slash-command prompts for Claude Code and OpenCode. The installable source files live in `.claude/commands/`.
|
|
4
|
+
|
|
5
|
+
## Command Map
|
|
6
|
+
|
|
7
|
+
| Command | Use When | Main Output |
|
|
8
|
+
|---|---|---|
|
|
9
|
+
| [`/akili-constitution`](akili-constitution.md) | Starting a repo or repairing weak project context | Project baseline docs, `CLAUDE.md`, `AGENTS.md`, general spec templates, and the `.agents/` multi-agent harness |
|
|
10
|
+
| [`/akili-propose <change-name-or-spec-path>`](akili-propose.md) | Aligning on intent before full specification | `proposal.md` under `docs/specs/<spec-path>/` |
|
|
11
|
+
| [`/akili-specify <spec-path>`](akili-specify.md) | Planning one bounded change before code | `requirements.md`, `design.md`, `tasks.md` |
|
|
12
|
+
| [`/akili-execute <spec-path>`](akili-execute.md) | Implementing approved tasks via the Leader → Implementer → Reviewer harness | Code/docs changes, updated `tasks.md`, `execution.md` with full PASS/FAIL audit trail |
|
|
13
|
+
| [`/akili-test <spec-path>`](akili-test.md) | Proving behavior with test evidence | `test-report.md` |
|
|
14
|
+
| [`/akili-validate <spec-path>`](akili-validate.md) | Auditing conformance before completion | `validation-report.md` |
|
|
15
|
+
| [`/akili-archive <spec-path>`](akili-archive.md) | Closing completed work after validation | Archived spec folder with `archive-summary.md` |
|
|
16
|
+
| [`/akili-seo <site-domain>`](akili-seo.md) | Setting up GSC ownership and SEO audit evidence | `seo-setup-report.md`, `seo-audit-report.md` |
|
|
17
|
+
|
|
18
|
+
## Normal Sequence
|
|
19
|
+
|
|
20
|
+
```text
|
|
21
|
+
/akili-constitution
|
|
22
|
+
/akili-propose <change-name-or-spec-path>
|
|
23
|
+
/akili-specify <spec-path>
|
|
24
|
+
/akili-execute <spec-path>
|
|
25
|
+
/akili-test <spec-path>
|
|
26
|
+
/akili-validate <spec-path>
|
|
27
|
+
/akili-archive <spec-path>
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
You can skip `/akili-propose` for very small, obvious work. You should not skip validation before archiving unless the user explicitly accepts the risk.
|
|
31
|
+
|
|
32
|
+
## Source Files
|
|
33
|
+
|
|
34
|
+
| Command | Source |
|
|
35
|
+
|---|---|
|
|
36
|
+
| `/akili-constitution` | `.claude/commands/akili-constitution.md` |
|
|
37
|
+
| `/akili-propose` | `.claude/commands/akili-propose.md` |
|
|
38
|
+
| `/akili-specify` | `.claude/commands/akili-specify.md` |
|
|
39
|
+
| `/akili-execute` | `.claude/commands/akili-execute.md` |
|
|
40
|
+
| `/akili-test` | `.claude/commands/akili-test.md` |
|
|
41
|
+
| `/akili-validate` | `.claude/commands/akili-validate.md` |
|
|
42
|
+
| `/akili-archive` | `.claude/commands/akili-archive.md` |
|
|
43
|
+
| `/akili-seo` | `.claude/commands/akili-seo.md` |
|
|
@@ -0,0 +1,65 @@
|
|
|
1
|
+
# `/akili-archive`
|
|
2
|
+
|
|
3
|
+
Move a completed spec into historical archive after implementation, testing, and validation.
|
|
4
|
+
|
|
5
|
+
## Usage
|
|
6
|
+
|
|
7
|
+
```text
|
|
8
|
+
/akili-archive <spec-path>
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
Examples:
|
|
12
|
+
|
|
13
|
+
```text
|
|
14
|
+
/akili-archive changes/add-remember-me
|
|
15
|
+
/akili-archive bugfix/login-redirect
|
|
16
|
+
/akili-archive enhancements/renewals
|
|
17
|
+
```
|
|
18
|
+
|
|
19
|
+
## Use When
|
|
20
|
+
|
|
21
|
+
- The spec is complete.
|
|
22
|
+
- Required tasks are `[x]`, or incomplete work is explicitly accepted as follow-up.
|
|
23
|
+
- Test and validation evidence exist or their absence is explicitly accepted.
|
|
24
|
+
- No unresolved FAIL findings remain.
|
|
25
|
+
|
|
26
|
+
## Output
|
|
27
|
+
|
|
28
|
+
Moves:
|
|
29
|
+
|
|
30
|
+
```text
|
|
31
|
+
docs/specs/<spec-path>/
|
|
32
|
+
```
|
|
33
|
+
|
|
34
|
+
to:
|
|
35
|
+
|
|
36
|
+
```text
|
|
37
|
+
docs/specs/archive/YYYY-MM-DD-<safe-name>/
|
|
38
|
+
```
|
|
39
|
+
|
|
40
|
+
`<safe-name>` replaces `/` with `--`.
|
|
41
|
+
|
|
42
|
+
## Archive Summary
|
|
43
|
+
|
|
44
|
+
Before moving, the command creates or updates:
|
|
45
|
+
|
|
46
|
+
```text
|
|
47
|
+
docs/specs/<spec-path>/archive-summary.md
|
|
48
|
+
```
|
|
49
|
+
|
|
50
|
+
The summary captures delivered requirements, files changed, test evidence, validation summary, accepted warnings, follow-ups, and historical notes.
|
|
51
|
+
|
|
52
|
+
## Constitution & Graph Sync
|
|
53
|
+
|
|
54
|
+
Before moving the folder, the command consumes the `## Constitution Impact` notes recorded in `execution.md` during `/akili-execute`:
|
|
55
|
+
|
|
56
|
+
- creates or updates child `CLAUDE.md`/`AGENTS.md` guides for new or reshaped modules (thin, module-specific, never duplicating root rules)
|
|
57
|
+
- adds or refreshes the child entries in the parent guides' `## Module Guides` index
|
|
58
|
+
- updates root-guide statements the change made stale
|
|
59
|
+
- recommends a CodeGraph re-index when `.codegraph/` exists
|
|
60
|
+
|
|
61
|
+
## Guardrails
|
|
62
|
+
|
|
63
|
+
- Do not delete completed specs.
|
|
64
|
+
- Do not overwrite an existing archive folder.
|
|
65
|
+
- If archive readiness is unclear, ask whether to validate first, proceed with accepted risk, or keep the spec active.
|
|
@@ -0,0 +1,91 @@
|
|
|
1
|
+
# `/akili-constitution`
|
|
2
|
+
|
|
3
|
+
Establish or strengthen the project-wide AKILI foundation and scaffold the multi-agent harness.
|
|
4
|
+
|
|
5
|
+
## Usage
|
|
6
|
+
|
|
7
|
+
```text
|
|
8
|
+
/akili-constitution
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
## Use When
|
|
12
|
+
|
|
13
|
+
- Starting a new repository.
|
|
14
|
+
- Existing project docs are missing, stale, or inconsistent.
|
|
15
|
+
- A major product pivot changed the project's baseline assumptions.
|
|
16
|
+
- Agents need stable `CLAUDE.md` and `AGENTS.md` guidance.
|
|
17
|
+
- The project does not yet have a `.agents/` directory powering `/akili-execute`.
|
|
18
|
+
|
|
19
|
+
## Behavior
|
|
20
|
+
|
|
21
|
+
The command classifies the repository into one of three modes and adjusts its behavior accordingly.
|
|
22
|
+
|
|
23
|
+
| Mode | Meaning | Constitution Behavior | `.agents/` Behavior |
|
|
24
|
+
|---|---|---|---|
|
|
25
|
+
| Brand-new (Seed Setup) | No code, no AKILI-SPECS docs | Draft baseline from user intent, chosen stack, assumptions, open questions | Copy default Leader / Implementer / Reviewer personas verbatim |
|
|
26
|
+
| Legacy (Discovery Setup) | Real code exists, no AKILI-SPECS baseline | Inspect repository reality (CodeGraph preferred) before drafting; synthesize from evidence | Copy defaults then customize with detected stack, design tokens, lint and test commands |
|
|
27
|
+
| Active AKILI-SPECS (Safe Update) | AKILI-SPECS baseline already present, custom `.agents/` may exist | Upgrade weak sections, fill missing files non-destructively | Never overwrite existing personas — only append minimal upgrade blocks |
|
|
28
|
+
|
|
29
|
+
For Legacy and Active-AKILI-SPECS modes, if `.codegraph/` exists CodeGraph is used for semantic exploration; if it is missing and the CLI is available, the agent asks before initializing it.
|
|
30
|
+
|
|
31
|
+
## Outputs
|
|
32
|
+
|
|
33
|
+
Creates or enhances:
|
|
34
|
+
|
|
35
|
+
- `docs/prd.md`
|
|
36
|
+
- `docs/ux-ui/design.md`
|
|
37
|
+
- `docs/trd/trd.md`
|
|
38
|
+
- `docs/specs/general-setup/requirements.md`
|
|
39
|
+
- `docs/specs/general-setup/design.md`
|
|
40
|
+
- `docs/specs/general-setup/task.md`
|
|
41
|
+
- `CLAUDE.md`
|
|
42
|
+
- `AGENTS.md`
|
|
43
|
+
- `.agents/leader.md`
|
|
44
|
+
- `.agents/implementer.md`
|
|
45
|
+
- `.agents/reviewer.md`
|
|
46
|
+
|
|
47
|
+
Projects created before the TRD naming may still have `docs/system-design/design.md` (UX/UI blueprint) and `docs/detailed-design/detailed-design.md` (technical blueprint). The constitution treats those as the existing UX/UI Design document and TRD, and in Active-AKILI-SPECS mode offers to migrate them to `docs/ux-ui/design.md` and `docs/trd/trd.md`.
|
|
48
|
+
|
|
49
|
+
The root guides also carry a `## Module Guides` index: modules whose conventions diverge from the root get a thin child `CLAUDE.md`/`AGENTS.md`, and every child guide must be referenced from that index. `/akili-execute` records new-module impact notes and `/akili-archive` syncs the guides and recommends a CodeGraph re-index.
|
|
50
|
+
|
|
51
|
+
## Multi-Agent Harness Scaffolding
|
|
52
|
+
|
|
53
|
+
`.agents/` is the source of truth for the multi-agent loop that `/akili-execute` runs (Leader → Implementer → Reviewer). The constitution seeds it from the packaged defaults shipped by the installer:
|
|
54
|
+
|
|
55
|
+
- Claude Code: `~/.claude/akili/templates/{leader,implementer,reviewer}.md`
|
|
56
|
+
- OpenCode: `~/.config/opencode/akili/templates/{leader,implementer,reviewer}.md`
|
|
57
|
+
- Antigravity: `~/.gemini/config/akili/templates/{leader,implementer,reviewer}.md`
|
|
58
|
+
|
|
59
|
+
If packaged templates are not available, the constitution drafts equivalent personas inline using the structure documented in `/akili-execute` (rework loop, PASS/FAIL output contract, AKILI commit standard, Pivot Protocol).
|
|
60
|
+
|
|
61
|
+
The `.agents/` directory is tool-agnostic: pure Markdown + YAML frontmatter, resolved relative to the active workspace, and used by Claude Code, OpenCode, and Google Antigravity (`invoke_subagent`).
|
|
62
|
+
|
|
63
|
+
## Model Routing Scaffolding
|
|
64
|
+
|
|
65
|
+
Step 7C adds or upgrades a `## Model Routing` section in the project's root `AGENTS.md` and `CLAUDE.md`: a capability-tier registry that maps each AKILI-SPECS phase to a model **per tool** (Claude Code and OpenCode). It is guidance only — no `model:` frontmatter is added and the installer is unchanged. The registry enforces **author ≠ auditor** (the Reviewer runs on a different model than the Implementer) and, in Active-AKILI-SPECS mode, is non-destructive: an existing customized registry is preserved and only gaps are filled. See [Model Routing](../model-routing.md) for the tiers and the default registry.
|
|
66
|
+
|
|
67
|
+
- `product-manager-toolkit`
|
|
68
|
+
- `ui-ux-pro-max`
|
|
69
|
+
- `frontend-design`
|
|
70
|
+
- `stitch-design`
|
|
71
|
+
- `nestjs-expert`
|
|
72
|
+
- `api-design-principles`
|
|
73
|
+
- `error-handling-patterns`
|
|
74
|
+
- `aws-serverless`
|
|
75
|
+
- `shadcn-ui`
|
|
76
|
+
- `tailwind-design-system`
|
|
77
|
+
- `vercel-react-best-practices`
|
|
78
|
+
|
|
79
|
+
## Next Step
|
|
80
|
+
|
|
81
|
+
After approving the baseline and confirming `.agents/` is in place, start a change:
|
|
82
|
+
|
|
83
|
+
```text
|
|
84
|
+
/akili-propose <change-name-or-spec-path>
|
|
85
|
+
```
|
|
86
|
+
|
|
87
|
+
For a small, obvious change, you may start with:
|
|
88
|
+
|
|
89
|
+
```text
|
|
90
|
+
/akili-specify <spec-path>
|
|
91
|
+
```
|
|
@@ -0,0 +1,93 @@
|
|
|
1
|
+
# `/akili-execute`
|
|
2
|
+
|
|
3
|
+
Implement the next eligible task from an approved spec path using the AKILI **Leader → Implementer → Reviewer** multi-agent harness.
|
|
4
|
+
|
|
5
|
+
## Usage
|
|
6
|
+
|
|
7
|
+
```text
|
|
8
|
+
/akili-execute <spec-path>
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
## Use When
|
|
12
|
+
|
|
13
|
+
- `requirements.md`, `design.md`, and `tasks.md` are approved.
|
|
14
|
+
- `.agents/` is in place (scaffolded by `/akili-constitution`).
|
|
15
|
+
- You want incremental, audited execution instead of broad untracked implementation.
|
|
16
|
+
- A previous task is marked `[~]` and should be resumed.
|
|
17
|
+
|
|
18
|
+
## Inputs
|
|
19
|
+
|
|
20
|
+
Reads:
|
|
21
|
+
|
|
22
|
+
- `docs/specs/<spec-path>/requirements.md`
|
|
23
|
+
- `docs/specs/<spec-path>/design.md`
|
|
24
|
+
- `docs/specs/<spec-path>/tasks.md`
|
|
25
|
+
- `docs/specs/<spec-path>/execution.md` when present
|
|
26
|
+
- Constitution docs (`docs/prd.md`, `docs/ux-ui/design.md`, `docs/trd/trd.md`)
|
|
27
|
+
- `CLAUDE.md` and `AGENTS.md`
|
|
28
|
+
- `.agents/leader.md`, `.agents/implementer.md`, `.agents/reviewer.md`
|
|
29
|
+
|
|
30
|
+
## Behavior
|
|
31
|
+
|
|
32
|
+
`/akili-execute` runs each task through a bounded rework loop. The caller acts as the **Leader** and delegates to two subordinate roles:
|
|
33
|
+
|
|
34
|
+
| Role | File | Responsibilities |
|
|
35
|
+
|---|---|---|
|
|
36
|
+
| Leader | `.agents/leader.md` | Picks the next task, delegates, enforces the loop, updates `tasks.md` and `execution.md`, commits |
|
|
37
|
+
| Implementer | `.agents/implementer.md` | Writes code strictly within task scope, applies design tokens, runs verification before reporting |
|
|
38
|
+
| Reviewer | `.agents/reviewer.md` | Read-only diff audit; emits `STATUS: PASS` or `STATUS: FAIL` with structured findings |
|
|
39
|
+
|
|
40
|
+
### Per-task loop
|
|
41
|
+
|
|
42
|
+
```text
|
|
43
|
+
1. Leader selects the next [ ] or [~] task whose dependencies are complete
|
|
44
|
+
2. Spawn Implementer with task scope, design context, and prior FAIL feedback (if rework)
|
|
45
|
+
3. Implementer writes code and runs the verification command
|
|
46
|
+
4. Leader extracts git diff
|
|
47
|
+
5. Spawn Reviewer with diff + relevant spec slices
|
|
48
|
+
6. Reviewer returns STATUS: PASS or STATUS: FAIL
|
|
49
|
+
|
|
50
|
+
if PASS → update tasks.md to [x], append execution.md, commit, advance to next task
|
|
51
|
+
if FAIL → log issues; if attempts < 3, respawn Implementer with the unchanged Reviewer report
|
|
52
|
+
if 3 consecutive FAILs → HALT, mark task [~], present full audit trail
|
|
53
|
+
```
|
|
54
|
+
|
|
55
|
+
On PASS, if the task created a new module/package or moved a module boundary, the Leader also appends a `## Constitution Impact: <Task ID>` block to `execution.md` (child guide needed, parent `## Module Guides` index entry, pending CodeGraph re-index). `/akili-archive` consumes these notes during Constitution & Graph Sync.
|
|
56
|
+
|
|
57
|
+
### Reviewer output contract
|
|
58
|
+
|
|
59
|
+
On `FAIL`, every finding lists three fields so the Implementer has actionable instructions on the next loop iteration:
|
|
60
|
+
|
|
61
|
+
- **Discovered Issue** — what is incorrect or missing.
|
|
62
|
+
- **Violated Rule** — the specific spec document and section that the diff contradicts.
|
|
63
|
+
- **Remediation Suggestion** — what the next Implementer attempt must change.
|
|
64
|
+
|
|
65
|
+
## Outputs
|
|
66
|
+
|
|
67
|
+
- Focused code or documentation changes (only after Reviewer PASS).
|
|
68
|
+
- Updated `tasks.md` with `[x]`, `[~]`, or `[ ]` status.
|
|
69
|
+
- Updated `execution.md` with files changed, requirements covered, decisions, every Implementer attempt, every Reviewer verdict, verification evidence, and final status (PASS / HALT / pivot).
|
|
70
|
+
- Commit prefixed with `[SPEC:<spec-path>]`.
|
|
71
|
+
|
|
72
|
+
## Guardrails
|
|
73
|
+
|
|
74
|
+
- **Maximum retries.** Hard ceiling of 3 rework attempts per task. After 3 consecutive FAILs the loop HALTS and presents the audit trail.
|
|
75
|
+
- **Structured feedback.** The Reviewer's FAIL report is passed back unchanged to the next Implementer — no paraphrasing.
|
|
76
|
+
- **No scope creep.** The Implementer keeps changes minimal and within task scope; broad refactors require user approval.
|
|
77
|
+
- **No completion without PASS.** A task is never marked `[x]` until the Reviewer PASSes.
|
|
78
|
+
- **Pivot Protocol takes precedence.** If discovery proves the spec itself is wrong, the loop stops immediately and a `## Pivot Record` is opened in `execution.md` for user sign-off — rework retries are not consumed on a broken spec.
|
|
79
|
+
|
|
80
|
+
## Cross-tool support
|
|
81
|
+
|
|
82
|
+
The `.agents/` directory is pure Markdown + YAML frontmatter and is resolved relative to the active workspace.
|
|
83
|
+
|
|
84
|
+
- **Claude Code / OpenCode:** Leader delegates by spawning focused subagent or sub-prompt contexts seeded with the persona file plus task/diff context.
|
|
85
|
+
- **Google Antigravity:** Leader calls `invoke_subagent` using prompts read from `.agents/`.
|
|
86
|
+
|
|
87
|
+
## Next Step
|
|
88
|
+
|
|
89
|
+
Continue executing tasks until implementation is complete, then run:
|
|
90
|
+
|
|
91
|
+
```text
|
|
92
|
+
/akili-test <spec-path>
|
|
93
|
+
```
|
|
@@ -0,0 +1,65 @@
|
|
|
1
|
+
# `/akili-propose`
|
|
2
|
+
|
|
3
|
+
Create a lightweight, reviewable proposal before full specification.
|
|
4
|
+
|
|
5
|
+
## Usage
|
|
6
|
+
|
|
7
|
+
```text
|
|
8
|
+
/akili-propose <change-name-or-spec-path>
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
Examples:
|
|
12
|
+
|
|
13
|
+
```text
|
|
14
|
+
/akili-propose add-remember-me
|
|
15
|
+
/akili-propose bugfix/login-redirect
|
|
16
|
+
/akili-propose enhancements/renewals
|
|
17
|
+
```
|
|
18
|
+
|
|
19
|
+
## Path Rules
|
|
20
|
+
|
|
21
|
+
| Input | Spec Path | Proposal Path |
|
|
22
|
+
|---|---|---|
|
|
23
|
+
| `add-remember-me` | `changes/add-remember-me` | `docs/specs/changes/add-remember-me/proposal.md` |
|
|
24
|
+
| `bugfix/login-redirect` | `bugfix/login-redirect` | `docs/specs/bugfix/login-redirect/proposal.md` |
|
|
25
|
+
|
|
26
|
+
Bare names default to `changes/<name>`. Paths containing `/` are used as provided under `docs/specs/`.
|
|
27
|
+
|
|
28
|
+
## Use When
|
|
29
|
+
|
|
30
|
+
- The change needs stakeholder review before detailed specs.
|
|
31
|
+
- Scope, non-goals, risks, or affected systems are uncertain.
|
|
32
|
+
- Multiple implementation approaches are possible.
|
|
33
|
+
- Existing behavior may need added, modified, or removed requirements.
|
|
34
|
+
|
|
35
|
+
## Output
|
|
36
|
+
|
|
37
|
+
Creates or updates:
|
|
38
|
+
|
|
39
|
+
```text
|
|
40
|
+
docs/specs/<spec-path>/proposal.md
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
## Proposal Sections
|
|
44
|
+
|
|
45
|
+
- Document Control
|
|
46
|
+
- Intent
|
|
47
|
+
- Problem / Current Behavior
|
|
48
|
+
- Proposed Outcome
|
|
49
|
+
- Scope
|
|
50
|
+
- Non-Goals
|
|
51
|
+
- Affected Users, Systems, And Specs
|
|
52
|
+
- Requirement Delta Preview
|
|
53
|
+
- Approach Options
|
|
54
|
+
- Recommended Approach
|
|
55
|
+
- Risks, Dependencies, And Open Questions
|
|
56
|
+
- Success Criteria
|
|
57
|
+
- Next Step
|
|
58
|
+
|
|
59
|
+
## Next Step
|
|
60
|
+
|
|
61
|
+
After approval:
|
|
62
|
+
|
|
63
|
+
```text
|
|
64
|
+
/akili-specify <spec-path>
|
|
65
|
+
```
|
|
@@ -0,0 +1,75 @@
|
|
|
1
|
+
# `/akili-seo`
|
|
2
|
+
|
|
3
|
+
Provision Google Search Console ownership for a domain, run a technical SEO audit, and write reports under a spec path.
|
|
4
|
+
|
|
5
|
+
## Usage
|
|
6
|
+
|
|
7
|
+
```text
|
|
8
|
+
/akili-seo <site-domain>
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
Examples:
|
|
12
|
+
|
|
13
|
+
```text
|
|
14
|
+
/akili-seo example.com
|
|
15
|
+
/akili-seo seo/example.com
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
## Path Rules
|
|
19
|
+
|
|
20
|
+
Bare domains default to:
|
|
21
|
+
|
|
22
|
+
```text
|
|
23
|
+
docs/specs/seo/<domain>/
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
Paths containing `/` are treated as explicit spec paths under `docs/specs/`.
|
|
27
|
+
|
|
28
|
+
## Prerequisites
|
|
29
|
+
|
|
30
|
+
- Google Cloud service account JSON key stored outside the repo.
|
|
31
|
+
- Site Verification API enabled.
|
|
32
|
+
- Search Console API enabled.
|
|
33
|
+
- DNS provider access for the target domain.
|
|
34
|
+
- `gsc` MCP configured from `.mcp.json.example`.
|
|
35
|
+
- Python dependencies for the bundled verification helper: `google-auth` and `google-api-python-client`.
|
|
36
|
+
|
|
37
|
+
The Web Search Indexing API is not required for generic sites. Google only honors it for `JobPosting` and `BroadcastEvent` schemas.
|
|
38
|
+
|
|
39
|
+
## Outputs
|
|
40
|
+
|
|
41
|
+
Creates or updates:
|
|
42
|
+
|
|
43
|
+
```text
|
|
44
|
+
docs/specs/<spec-path>/seo-setup-report.md
|
|
45
|
+
docs/specs/<spec-path>/seo-audit-report.md
|
|
46
|
+
```
|
|
47
|
+
|
|
48
|
+
## Audit Areas
|
|
49
|
+
|
|
50
|
+
- DNS TXT verification and property ownership
|
|
51
|
+
- Search Console property visibility
|
|
52
|
+
- sitemap submission and sitemap URL inventory
|
|
53
|
+
- URL inspection and index coverage
|
|
54
|
+
- structured data warnings and errors
|
|
55
|
+
- search analytics by query, page, country, and device
|
|
56
|
+
- server-rendered content checks with Googlebot user agent
|
|
57
|
+
- internal linking quick check
|
|
58
|
+
- on-page audit (titles, metas, headings, canonicals, hreflang) via the `seo-audit` skill
|
|
59
|
+
- prioritized remediation plan
|
|
60
|
+
- implementation prompt for high-severity fixes
|
|
61
|
+
|
|
62
|
+
## Skills
|
|
63
|
+
|
|
64
|
+
The audit phase loads the packaged [`seo-audit`](../skills/seo-audit.md) skill: findings follow its Issue / Impact / Evidence / Fix / Priority format and are weighted by its priority order (crawlability → technical → on-page → content → authority). `systematic-debugging` applies when index data is inconsistent with site reality.
|
|
65
|
+
|
|
66
|
+
## Helper Resources
|
|
67
|
+
|
|
68
|
+
| Resource | Purpose |
|
|
69
|
+
|---|---|
|
|
70
|
+
| `scripts/gsc_verify.py` | Calls Site Verification API for token and verify operations |
|
|
71
|
+
| `.mcp.json.example` | Reference MCP config for `@mikusnuz/gsc-mcp` |
|
|
72
|
+
|
|
73
|
+
## When To Run
|
|
74
|
+
|
|
75
|
+
Run after deployment, after major content changes, after schema changes, or when Search Console ownership needs to be provisioned for a service account.
|
|
@@ -0,0 +1,69 @@
|
|
|
1
|
+
# `/akili-specify`
|
|
2
|
+
|
|
3
|
+
Generate the requirements, design, and task plan for one bounded feature, bugfix, enhancement, or module.
|
|
4
|
+
|
|
5
|
+
## Usage
|
|
6
|
+
|
|
7
|
+
```text
|
|
8
|
+
/akili-specify <spec-path>
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
Examples:
|
|
12
|
+
|
|
13
|
+
```text
|
|
14
|
+
/akili-specify loan
|
|
15
|
+
/akili-specify enhancements/renewals
|
|
16
|
+
/akili-specify admin/user-management
|
|
17
|
+
```
|
|
18
|
+
|
|
19
|
+
## Use When
|
|
20
|
+
|
|
21
|
+
- A proposal has been approved and needs full specification.
|
|
22
|
+
- A small change is clear enough to specify directly.
|
|
23
|
+
- A feature needs behavior, design, task, and verification traceability before coding.
|
|
24
|
+
|
|
25
|
+
## Inputs
|
|
26
|
+
|
|
27
|
+
Reads context from:
|
|
28
|
+
|
|
29
|
+
- `docs/specs/<spec-path>/proposal.md` when present
|
|
30
|
+
- `docs/specs/general-setup/`
|
|
31
|
+
- `docs/prd.md`
|
|
32
|
+
- `docs/ux-ui/design.md`
|
|
33
|
+
- `docs/trd/trd.md`
|
|
34
|
+
- related specs under `docs/specs/`
|
|
35
|
+
- root and package-level agent guidance files
|
|
36
|
+
|
|
37
|
+
## Outputs
|
|
38
|
+
|
|
39
|
+
Creates or updates:
|
|
40
|
+
|
|
41
|
+
```text
|
|
42
|
+
docs/specs/<spec-path>/requirements.md
|
|
43
|
+
docs/specs/<spec-path>/design.md
|
|
44
|
+
docs/specs/<spec-path>/tasks.md
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
## Documentation Depth
|
|
48
|
+
|
|
49
|
+
| Depth | Use For |
|
|
50
|
+
|---|---|
|
|
51
|
+
| Lite | Small bugfixes, copy updates, narrow UI tweaks |
|
|
52
|
+
| Standard | Normal features and enhancements |
|
|
53
|
+
| Full | Risky, cross-cutting, API, data, auth, migration, or high-impact work |
|
|
54
|
+
|
|
55
|
+
## Key Rules
|
|
56
|
+
|
|
57
|
+
- Requirements describe observable behavior, not implementation details.
|
|
58
|
+
- Key requirements include Given/When/Then scenarios.
|
|
59
|
+
- Design extends the current architecture instead of replacing it.
|
|
60
|
+
- Tasks reference requirements, design sections, dependencies, done criteria, verification, and relevant skills.
|
|
61
|
+
- The user approves requirements, design, and tasks before implementation begins.
|
|
62
|
+
|
|
63
|
+
## Next Step
|
|
64
|
+
|
|
65
|
+
After approval:
|
|
66
|
+
|
|
67
|
+
```text
|
|
68
|
+
/akili-execute <spec-path>
|
|
69
|
+
```
|