@mohammadhprp/system-prompt 0.11.2 → 0.12.0

package/framework/agents/researcher.md

@@ -6,7 +6,7 @@ permission:
   bash: deny
   read: allow
   edit: deny
-  write: allow
+  write: deny
   patch: deny
   grep: allow
   glob: allow

package/framework/mcps/github-mcp/README.md

@@ -48,4 +48,4 @@ Relevant skills in this repository:
 
 - [`code-review`](../../skills/code-review/SKILL.md): reviewing pull request diffs.
 - [`backend-best-practices`](../../skills/backend-best-practices/SKILL.md): backend best practices for testing, debugging, and security review.
-- [`pull-request`](../../skills/pull-request/SKILL.md): preparing and submitting pull requests.
+- [`pr`](../../commands/pr.md): preparing and submitting pull requests.

package/framework/mcps/github-mcp/configs/.env.example

@@ -1 +1 @@
-GITHUB_TOKEN=
+GITHUB_PERSONAL_ACCESS_TOKEN=

package/framework/plugins/ponytail/README.md

@@ -41,4 +41,4 @@ Relevant skills in this repository:
 
 - [`code-review`](../../skills/code-review/SKILL.md): review backend changes for correctness and maintainability, complementary to ponytail's over-engineering focus.
 - [`backend-best-practices`](../../skills/backend-best-practices/SKILL.md): backend best practices for refactoring and behavior-preserving cleanup.
-- [`pull-request`](../../skills/pull-request/SKILL.md): prepare small, reviewable changes aligned with ponytail's minimal-diff philosophy.
+- [`pr`](../../commands/pr.md): prepare small, reviewable changes aligned with ponytail's minimal-diff philosophy.

package/framework/plugins/ponytail/capabilities.md

@@ -90,7 +90,7 @@ Or in `~/.config/ponytail/config.json` (`%APPDATA%\ponytail\config.json` on Wind
 - Use `/ponytail-review` after a coding session to catch over-engineering the agent missed.
 - Mark intentional shortcuts with `ponytail:` comments naming the ceiling and upgrade path.
 - Review `/ponytail-debt` regularly to track deferred improvements.
-- Pair with `code-review` and `pull-request` skills for a complete quality workflow.
+- Pair with `code-review` and the `/pr` command for a complete quality workflow.
 
 ## Common Workflows
 

package/framework/references/standards/pull-requests.md

@@ -39,4 +39,4 @@ Define reusable backend engineering rules for pull request decisions across proj
 ## Related Skills
 
 - `skills/code-review/SKILL.md`
-- `skills/pull-request/SKILL.md`
+- `commands/pr.md`

package/framework/skills/README.md

@@ -31,11 +31,11 @@ This catalog is framework-agnostic: each skill defines when to activate, a step-
 | [security-best-practices](./security-best-practices/SKILL.md) | Perform language- and framework-specific security best-practice reviews and suggest improvements, with support for Python, JavaScript/TypeScript, and Go. | Explicit security reviews or reports, secure-by-default coding, or auditing existing code for major vulnerabilities. |
 | [sentry](./sentry/SKILL.md) | Inspect Sentry issues, summarize production errors, and pull health data via the Sentry API (read-only). | Checking production errors, summarizing recent crashes, or pulling a production error report. |
 | [show-me](./show-me/SKILL.md) | Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts. | Explaining logic, control flow, UI structure, file responsibility, or data flow with the smallest useful visual. |
-| [pull-request](./pull-request/SKILL.md) | Prepare small, reviewable changes with clear evidence, risk, deployment, and rollback notes. | Preparing PRs, writing descriptions, or planning safe deployments. |
 | [skill-creator](./skill-creator/SKILL.md) | Create new skills, modify and improve existing skills, and measure skill performance. | Designing new skills, optimizing existing skills, or running evals. |
 | [spec-driven-eval](./spec-driven-eval/SKILL.md) | Score how completely an implementation fulfills a PRD/spec, case by case, producing a single comparable final grade. | Benchmarking spec-driven implementations, grading acceptance criteria, or auditing implementation and test coverage against a spec. |
 | [technical-design-doc-creator](./technical-design-doc-creator/SKILL.md) | Create comprehensive Technical Design Documents (TDDs) with mandatory and optional sections through interactive discovery, in the user's language. | Writing a design doc, TDD, technical spec, or architecture document before implementing a significant change. |
 | [tlc-spec-driven](./tlc-spec-driven/SKILL.md) | Feature planning and implementation with adaptive phases, EARS testable requirements, atomic Conventional Commits, and independent verification. | Planning features, implementing with verification and atomic commits, or validating an implementation against a spec. |
+| [taste](./taste/SKILL.md) | Unified design-quality skill spanning anti-slop frontend design, image generation and image-to-code, brand kits, minimalist and industrial UI, redesigns, and Google Stitch design systems. | Landing pages, portfolios, redesigns, website/mobile/brand imagery, or any UI that must not look AI-generated. |
 | [web-design-guidelines](./web-design-guidelines/SKILL.md) | Review UI code for Web Interface Guidelines compliance — accessibility, focus, forms, animation, typography, and interaction patterns. | Reviewing UI, checking accessibility, auditing design or UX, or checking a site against best practices. |
 
 ## How Skills Are Organized

package/framework/skills/diagram-design/SKILL.md

@@ -192,7 +192,7 @@ Universal building blocks. Type-specialized primitives (lifeline, activation bar
 
 - Editorial callouts → [primitive-annotation.md](references/primitive-annotation.md)
 - Hand-drawn variant → [primitive-sketchy.md](references/primitive-sketchy.md)
-- Icon set (laptop, server, DB, K8s, Docker, AWS, …) → [primitive-icons.md](references/primitive-icons.md). Browse the gallery at [`assets/icons.html`](../assets/icons.html).
+- Icon set (laptop, server, DB, K8s, Docker, AWS, …) → [primitive-icons.md](references/primitive-icons.md). Browse the gallery at [`assets/icons.html`](assets/icons.html).
 - Terminal / CLI-window variant → [primitive-terminal.md](references/primitive-terminal.md)
 
 ### Background

package/framework/skills/taste/SKILL.md

@@ -0,0 +1,47 @@
+---
+name: taste
+description: One skill for the full taste spectrum. Covers anti-slop frontend design (landing pages, portfolios, redesigns, premium and minimalist UI, GSAP motion), image generation and image-to-code direction (web, mobile, brand kits), full-output enforcement, and Google Stitch design systems. Read the brief, pick the matching reference below, and follow it end to end. Do not auto-apply every reference at once.
+---
+
+# TASTE — Unified Design Quality Skill
+
+You are an elite frontend design engineer and art director. This skill bundles every taste discipline into one entry point. Each reference below is a complete playbook for one domain.
+
+## How to use
+
+1. **Read the brief first.** Do not fire all references at once.
+2. **Route to the matching reference** using the table below.
+3. **Follow that reference end to end** — its directives override generic defaults.
+4. When a task spans domains (e.g. redesign an existing site that also needs new imagery), apply the relevant references in sequence and reconcile conflicting rules by task priority.
+
+## Reference library
+
+| When the task is… | Use |
+|---|---|
+| Anti-slop frontend for landing pages, portfolios, redesigns (current default) | [design-taste-frontend.md](references/design-taste-frontend.md) |
+| Exact backward-compatible v1 taste behavior (original baseline) | [design-taste-frontend-v1.md](references/design-taste-frontend-v1.md) |
+| Awwwards-level design engineering with GSAP motion, randomization, bento grids | [gpt-taste.md](references/gpt-taste.md) |
+| High-end agency visual design — fonts, spacing, shadows, motion choreography | [high-end-visual-design.md](references/high-end-visual-design.md) |
+| Premium utilitarian minimalism — warm monochrome, editorial type, flat bento | [minimalist-ui.md](references/minimalist-ui.md) |
+| Industrial brutalism / tactical telemetry UI — Swiss print, CRT terminals | [industrial-brutalist-ui.md](references/industrial-brutalist-ui.md) |
+| Upgrading an existing project to premium quality (audit-first, no rewrites) | [redesign-existing-projects.md](references/redesign-existing-projects.md) |
+| Completeness of output — no truncation, no placeholders, no skipped sections | [full-output-enforcement.md](references/full-output-enforcement.md) |
+| Generating website section reference images, then implementing them | [image-to-code.md](references/image-to-code.md) |
+| Generating website design-reference images (one image per section) | [imagegen-frontend-web.md](references/imagegen-frontend-web.md) |
+| Generating mobile app screen concepts and flows (images only) | [imagegen-frontend-mobile.md](references/imagegen-frontend-mobile.md) |
+| Generating premium brand-kit / identity-system boards (images only) | [brandkit.md](references/brandkit.md) |
+| Generating a semantic DESIGN.md for Google Stitch | [stitch-design-taste.md](references/stitch-design-taste.md) |
+| Reference DESIGN.md output produced by the Stitch skill | [stitch-design-taste-design.md](references/stitch-design-taste-design.md) |
+
+## Cross-cutting rules
+
+Every reference shares these baseline principles; specific rules in a reference override these:
+
+- Never output the same layout or aesthetic twice in a row.
+- Reject the LLM defaults: Inter, Lucide/Feather icons, purple-blue AI gradients, three equal feature cards, centered hero over dark mesh, generic glassmorphism, `h-screen` (use `min-h-[100dvh]`).
+- Animate only `transform` and `opacity`. No layout-triggering properties.
+- No emojis in code, markup, text content, or alt text.
+- No pure black (`#000000`) — use off-black, charcoal, or zinc-950.
+- Prefer distinctive type (Geist, Outfit, Cabinet Grotesk, Satoshi, Fraunces, Instrument Serif) over generic fonts.
+- Verify dependency availability before importing third-party libraries.
+- Generate the `<design_plan>` / design-read step before writing any code where the reference requires it.

package/framework/skills/taste/examples.md

@@ -0,0 +1,73 @@
+# Taste Skill — Example Outputs
+
+Realistic examples of how the `taste` skill routes a brief to the right reference and enforces its standards.
+
+## Example 1: Landing Page (routes to `design-taste-frontend`)
+
+**User:** "Build a landing page for a developer analytics platform. Clean, premium, not AI-sloppy."
+
+**Design read:** B2B SaaS landing for technical buyers, with a Linear-style minimalist language, leaning toward Tailwind utilities + Geist + restrained motion.
+
+**What the agent does (following `design-taste-frontend.md`):**
+
+1. Sets the dials from the read: VARIANCE 5, MOTION 4, DENSITY 3.
+2. States the design read in one line before writing any code.
+3. Chooses a non-default hero: centered over a wide headline with two high-contrast CTAs and a full-bleed background image with a dark radial wash — not a narrow 6-line text wall.
+4. Bans Inter and Lucide; uses Geist + Phosphor. No AI-purple gradient, no three equal feature cards — uses an asymmetric bento with `grid-flow-dense`.
+5. Applies `min-h-[100dvh]` (never `h-screen`), animates only `transform`/`opacity`, generous `py-32 md:py-48` section spacing.
+
+**Result:** A distinctive, premium landing that does not read as a template.
+
+## Example 2: Brand Kit (routes to `brandkit`)
+
+**User:** "Generate a brand-kit board for 'Aster', a security platform for cloud-native startups."
+
+**What the agent does (following `brandkit.md`):**
+
+1. Infers brand strategy first: category security, audience CTOs/security engineers, core metaphor "vigilance + protection".
+2. Picks the Dark Security / Threat Intelligence visual mode: black/navy canvas, shield forms, radar lines, red/blue alert chips.
+3. Chooses a `3 × 3` layout with strong gutters and sparse typography: logo cover, logo construction grid, browser mockup, tagline, color system, typography, physical application, image direction, system detail.
+4. Designs one strong mark — an eye formed by crossing shield shapes — repeated consistently across panels. No generic lightning bolts, no fake luxury crests.
+5. Writes a short, specific tagline ("Your network. Our watch."), one URL, and minimal labels. No lorem ipsum, no dense body copy.
+
+**Result:** A premium, presentation-ready identity-system board that feels like a serious studio deck.
+
+## Example 3: Mobile App Screens (routes to `imagegen-frontend-mobile`)
+
+**User:** "Show me the onboarding flow for a habit-tracking app — three screens."
+
+**What the agent does (following `imagegen-frontend-mobile.md`):**
+
+1. Generates three separate app-native screens (welcome, permissions, home) inside a subtle premium phone mockup with a visible frame.
+2. Keeps hierarchy clean and text comfortably readable — no tiny fake labels, no dense dashboards.
+3. Uses one controlled palette with textured surfaces and image-led composition.
+4. Keeps the three screens visually consistent (shared color, type scale, iconography).
+5. Produces images only — no code.
+
+**Result:** Three cohesive, premium, app-native concepts a designer can hand to an engineer.
+
+## Example 4: Redesign (routes to `redesign-existing-projects`)
+
+**User:** "The dashboard we built last month looks generic. Make it premium without breaking it."
+
+**What the agent does (following `redesign-existing-projects.md`):**
+
+1. **Scan** — identifies the stack (React + Tailwind v4) and current patterns.
+2. **Diagnose** — audits: Inter everywhere, three equal card columns, pure black background, purple-blue gradient hero, no hover/active states, no loading or empty states, generic Lucide icons.
+3. **Fix in priority order** — font swap first (Geist), then palette cleanup (off-black + one desaturated accent), then hover/active states, layout, and finally component and icon swaps.
+4. Works with the existing stack — no framework migration, no rewrites. Tests after each change.
+
+**Result:** The same app, elevated — no broken functionality, no templated look.
+
+## Example 5: Full Output (routes to `full-output-enforcement`)
+
+**User:** "Write the complete `auth.ts` service — every function, no shortcuts."
+
+**What the agent does (following `full-output-enforcement.md`):**
+
+1. Counts the deliverables (all auth functions + exports) and locks the scope.
+2. Emits the full file — no `// rest of code`, no `// TODO`, no `...` placeholders, no "the rest follows the same pattern."
+3. If the response approaches the token limit, stops at a clean breakpoint and marks it: `[PAUSED — 2 of 4 complete. Send "continue" to resume from: token refresh]`.
+4. Cross-checks output against the original request before finalizing.
+
+**Result:** A complete, runnable file with zero placeholder patterns.