@hanzlaa/rcode 2.3.1 → 2.3.3

package/rihal/skills/agents/zayd-ml/SKILL.md

@@ -14,6 +14,22 @@ description: >
   automation. Do NOT use for: pure backend APIs (use Yousef), UI (use
   Haitham), architecture of non-ML systems (use Waleed), or testing
   strategy (use Fatima).
+triggers:
+  - "machine learning"
+  - "ML model"
+  - "AI"
+  - "LLM"
+  - "prompt engineering"
+  - "fine-tuning"
+  - "RAG"
+  - "embeddings"
+  - "talk to Zayd"
+  - "train a model"
+  - "ML pipeline"
+  - "AI feature"
+  - "vector database"
+  - "NLP"
+  - "deep learning"
 ---
 
 # Zayd — Senior ML Engineer
@@ -59,7 +75,7 @@ Concrete. Cites numbers: accuracy, F1, latency, cost per 1k requests. Never ship
 | PE | Design and version-control prompt engineering for LLMs | rihal-prompt-design (future) |
 | DR | Domain research for ML feasibility | rihal-technical-research |
 
-## On Activation
+## Workflow
 
 1. **Load config by reading @.rihal/skills/rihal-init/SKILL.md**
 2. **Load project context**

package/rihal/skills/core/rihal-advanced-elicitation/SKILL.md

@@ -2,6 +2,8 @@
 name: rihal-advanced-elicitation
 description: 'Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.'
 agent_party: '{project-root}/.rihal/team.yaml'
+triggers:
+  - "advanced elicitation"
 ---
 
 # Advanced Elicitation
@@ -10,6 +12,10 @@ agent_party: '{project-root}/.rihal/team.yaml'
 
 ---
 
+## Overview
+
+Advanced elicitation skill for Rihal Code.
+
 ## CRITICAL LLM INSTRUCTIONS
 
 - **MANDATORY:** Execute ALL steps in the flow section IN EXACT ORDER
@@ -140,6 +146,12 @@ x. Proceed / No Further Actions
 
 Interactive menu loop presenting 5 elicitation methods, then the enhanced content after each method application. Final output is the user-approved enhanced version of the original content.
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
 ## Examples
 
 ### Happy path

package/rihal/skills/core/rihal-brainstorming/SKILL.md

@@ -7,9 +7,25 @@ description: >
   thinking", "generate ideas", "idea generation", "divergent thinking",
   "lateral thinking", or "think outside the box". Do NOT use for strategic
   analysis (use rihal-sadiq-analyst) or product requirements (use rihal-create-prd).
+triggers:
+  - "brainstorm"
+  - "help me brainstorm"
+  - "help me ideate"
+  - "ideation session"
+  - "creative
+  thinking"
+  - "generate ideas"
+  - "idea generation"
+  - "divergent thinking"
+  - "lateral thinking"
+  - "think outside the box"
 user-invocable: true
 ---
 
+## Overview
+
+Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods.
+
 Structured brainstorming facilitator that guides users through creative ideation using techniques from brain-methods.csv. Aims for 100+ ideas before organizing, using anti-bias protocols to push past obvious solutions.
 
 ## Workflow

package/rihal/skills/core/rihal-clone-website/SKILL.md

@@ -12,6 +12,21 @@ description: >
   (use rihal-create-ux-design with Layla), writing new components from a
   brief (use rihal-dev-story with Hanzla or Bilal), or inspiration-only
   references without rebuild intent.
+triggers:
+  - "clone
+  this website"
+  - "clone this site"
+  - "rebuild this page"
+  - "replicate this
+  UI"
+  - "pixel-perfect clone"
+  - "make exact UI like this"
+  - "copy this site"
+  - "reverse engineer this site"
+  - "build me a clone of"
+  - "aisi website banao"
+  - "yeh site clone karo"
+  - "exact same UI chahiye like [URL]"
 argument-hint: "<url>"
 user-invocable: true
 ---
@@ -334,6 +349,12 @@ Before dispatching ANY builder:
 - Do NOT merge with red builds
 - Do NOT skip responsive extraction
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
 ## Examples
 
 ### Happy Path

package/rihal/skills/core/rihal-distillator/SKILL.md

@@ -2,6 +2,8 @@
 name: rihal-distillator
 description: Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.
 argument-hint: "[to create provide input paths] [--validate distillate-path to confirm distillate is lossless and optimized]"
+triggers:
+  - "distillator"
 ---
 
 # Distillator: A Document Distillation Engine
@@ -188,6 +190,12 @@ Structured JSON result:
 }
 ```
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
 ## Examples
 
 ### Happy path

package/rihal/skills/core/rihal-editorial-review-prose/SKILL.md

@@ -1,6 +1,8 @@
 ---
 name: rihal-editorial-review-prose
 description: 'Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the prose'
+triggers:
+  - "editorial review prose"
 ---
 
 # Editorial Review - Prose
@@ -17,6 +19,10 @@ description: 'Clinical copy-editor that reviews text for communication issues. U
 - **reader_type** (optional, default: `humans`) — `humans` for standard editorial, `llm` for precision focus
 
 
+## Overview
+
+Editorial review prose skill for Rihal Code.
+
 ## PRINCIPLES
 
 1. **Minimal intervention:** Apply the smallest fix that achieves clarity
@@ -93,6 +99,12 @@ Three-column markdown table:
 |---------------|--------------|---------|}
 | The exact original passage | The suggested revision | Brief explanation |
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
 ## Examples
 
 ### Happy path

package/rihal/skills/core/rihal-editorial-review-structure/SKILL.md

@@ -1,6 +1,8 @@
 ---
 name: rihal-editorial-review-structure
 description: 'Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure'
+triggers:
+  - "editorial review structure"
 ---
 
 # Editorial Review - Structure
@@ -19,6 +21,10 @@ description: 'Structural editor that proposes cuts, reorganization, and simplifi
 - **reader_type** (optional, default: "humans") -- 'humans' (default) preserves comprehension aids; 'llm' optimizes for precision and density
 - **length_target** (optional) -- Target reduction (e.g., '30% shorter', 'half the length', 'no limit')
 
+## Overview
+
+Editorial review structure skill for Rihal Code.
+
 ## Principles
 
 - Comprehension through calibration: Optimize for the minimum words needed to maintain understanding
@@ -178,6 +184,18 @@ Use the following output format:
 - HALT with error if reader_type is not "humans" or "llm"
 - If no structural issues found, output "No substantive changes recommended" (this is valid completion, not an error)
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
+## Output Format
+
+- Structured Markdown response
+- Headers for each section
+- Concise, actionable content
+
 ## Examples
 
 ### Happy path

package/rihal/skills/core/rihal-help/SKILL.md

@@ -1,10 +1,16 @@
 ---
 name: rihal-help
 description: 'Analyzes current state and user query to answer Rihal questions or recommend the next skill(s) to use. Use when user asks for help, Rihal help, what to do next, or what to start with in Rihal.'
+triggers:
+  - "help"
 ---
 
 # Rihal Help
 
+## Overview
+
+Help skill for Rihal Code.
+
 ## Purpose
 
 Help the user understand where they are in their Rihal workflow and what to do next. Answer Rihal questions when asked.
@@ -76,6 +82,12 @@ For each recommended item, present:
 
 Status summary of current workflow position, then ordered list of recommended next skills with `[menu-code]` **Display name**, skill name in backticks, and description.
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
 ## Examples
 
 ### Happy path

package/rihal/skills/core/rihal-index-docs/SKILL.md

@@ -1,6 +1,8 @@
 ---
 name: rihal-index-docs
 description: 'Generates or updates an index.md to reference all docs in the folder. Use if user requests to create or update an index of all files in a specific folder'
+triggers:
+  - "index docs"
 ---
 
 # Index Docs
@@ -8,6 +10,10 @@ description: 'Generates or updates an index.md to reference all docs in the fold
 **Goal:** Generate or update an index.md to reference all docs in a target folder.
 
 
+## Overview
+
+Index docs skill for Rihal Code.
+
 ## EXECUTION
 
 ### Step 1: Scan Directory
@@ -64,6 +70,18 @@ description: 'Generates or updates an index.md to reference all docs in the fold
 - Keep descriptions concise but informative (3-10 words)
 - Sort alphabetically within groups
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
+## Output Format
+
+- Structured Markdown response
+- Headers for each section
+- Concise, actionable content
+
 ## Examples
 
 ### Happy path

package/rihal/skills/core/rihal-init/SKILL.md

@@ -3,6 +3,8 @@ name: rihal-init
 internal: true
 description: "INTERNAL config loader — called by other skills, not by users directly. Loads module config vars from .rihal/. Install puts this in .rihal/skills/, not .claude/skills/."
 argument-hint: "[--module=module_code] [--vars=var1:default1,var2] [--skill-path=/path/to/calling/skill]"
+triggers:
+  - "init"
 ---
 
 ## Overview
@@ -104,6 +106,12 @@ After writing, re-run `rihal_init.py` with the `load` subcommand (same as the fa
 
 JSON config vars returned to the calling skill. When init path runs, interactive Q&A with the user, then config files written to `_rihal/`.
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
 ## Examples
 
 ### Happy path (fast path)

package/rihal/skills/core/rihal-party-mode/SKILL.md

@@ -9,9 +9,23 @@ description: >
   decisions (use rihal-majlis-council), single-agent questions where one
   specialist is clearly the right owner (invoke that agent directly), or
   sprint ceremonies (use rihal-hussain-sm).
+triggers:
+  - "party mode"
+  - "activate party mode"
+  - "start party mode"
+  - "group discussion"
+  - "team discussion"
+  - "talk to everyone"
+  - "bring all agents"
+  - "multi-agent chat"
+  - "let's have a party"
 user-invocable: true
 ---
 
+## Overview
+
+Orchestrates group discussions between all installed Rihal agents, enabling natural multi-agent conversations with maintained personalities.
+
 # Party Mode
 
 Brings together the full Rihal agent team for natural multi-agent conversations. Each agent maintains their unique personality and expertise while a facilitator manages flow, relevance-based agent selection, and cross-talk.

package/rihal/skills/core/rihal-review-adversarial-general/SKILL.md

@@ -1,6 +1,8 @@
 ---
 name: rihal-review-adversarial-general
 description: 'Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something'
+triggers:
+  - "review adversarial general"
 ---
 
 # Adversarial Review (General)
@@ -14,6 +16,10 @@ description: 'Perform a Cynical Review and produce a findings report. Use when t
 - **also_consider** (optional) — Areas to keep in mind during review alongside normal adversarial analysis
 
 
+## Overview
+
+Review adversarial general skill for Rihal Code.
+
 ## EXECUTION
 
 ### Step 1: Receive Content
@@ -35,6 +41,12 @@ Output findings as a Markdown list (descriptions only).
 
 Markdown bullet list of findings, each describing a specific problem, gap, or risk.
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
 ## Examples
 
 ### Happy path

package/rihal/skills/core/rihal-review-edge-case-hunter/SKILL.md

@@ -1,6 +1,8 @@
 ---
 name: rihal-review-edge-case-hunter
 description: 'Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.'
+triggers:
+  - "review edge case hunter"
 ---
 
 # Edge Case Hunter Review
@@ -19,6 +21,10 @@ Ignore the rest of the codebase unless the provided content explicitly reference
 **Your method is exhaustive path enumeration — mechanically walk every branch, not hunt by intuition. Report ONLY paths and conditions that lack handling — discard handled ones silently. Do NOT editorialize or add filler — findings only.**
 
 
+## Overview
+
+Review edge case hunter skill for Rihal Code.
+
 ## EXECUTION
 
 ### Step 1: Receive Content
@@ -66,6 +72,18 @@ No extra text, no explanations, no markdown wrapping. An empty array `[]` is val
 
 - If content is empty or cannot be decoded as text, return `[{"location":"N/A","trigger_condition":"Input empty or undecodable","guard_snippet":"Provide valid content to review","potential_consequence":"Review skipped — no analysis performed"}]` and stop
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
+## Output Format
+
+- Structured Markdown response
+- Headers for each section
+- Concise, actionable content
+
 ## Examples
 
 ### Happy path

package/rihal/skills/core/rihal-shard-doc/SKILL.md

@@ -1,12 +1,18 @@
 ---
 name: rihal-shard-doc
 description: 'Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document'
+triggers:
+  - "shard doc"
 ---
 
 # Shard Document
 
 **Goal:** Split large markdown documents into smaller, organized files based on level 2 sections using `npx @kayvan/markdown-tree-parser`.
 
+## Overview
+
+Shard doc skill for Rihal Code.
+
 ## CRITICAL RULES
 
 - MANDATORY: Execute ALL steps in the EXECUTION section IN EXACT ORDER
@@ -100,6 +106,18 @@ Present user with options for the original document:
   - Consider deleting or archiving the original document
 - Confirm user choice: "Original document kept at: [source-document-path]"
 
+## Workflow
+
+1. Read the user request and extract key parameters.
+2. Execute the skill logic as described in the Overview.
+3. Return output in the format specified below.
+
+## Output Format
+
+- Structured Markdown response
+- Headers for each section
+- Concise, actionable content
+
 ## Examples
 
 ### Happy path

package/rihal/state.json

@@ -0,0 +1,22 @@
+{
+  "version": "1",
+  "project": "__PROJECT_NAME__",
+  "created": "__INSTALL_DATE__",
+  "updated": "__INSTALL_DATE__",
+  "current_phase": "01",
+  "current_plan": 0,
+  "current_sprint": null,
+  "milestone": "M1 — Initial Delivery",
+  "phases": [
+    { "id": "01", "name": "Setup & Scaffolding", "status": "planned" }
+  ],
+  "executions": [],
+  "decisions": [],
+  "blockers": [],
+  "council_sessions": [],
+  "chains": [],
+  "workstreams": [],
+  "active_workstream": null,
+  "last_session": null,
+  "velocity_history": []
+}