@jenga-ai/agent 1.0.0

package/skills/dooo/SKILL.md

@@ -0,0 +1,60 @@
+---
+name: dooo
+description: Parallel execution orchestrator. Calls /do to start implementations via sub-agents, then loops back to the board to identify and offer parallelisable tasks until the user selects "Done".
+keywords:
+  - dooo
+  - parallel
+  - batch
+  - multiple tasks
+  - orchestrate
+examples:
+  - "run all pending tasks in parallel"
+  - "execute multiple tasks at once"
+metadata:
+  prefered_agent: scrum-master
+---
+
+# Dooo — Parallel Execution Orchestrator
+
+## Instructions
+
+### 1. Invoke `/do`
+Call the `/do` skill to let the user select and start an implementation. `/do` will launch a background sub-agent to handle the implementation. Once the sub-agent is launched, `/do` returns control here.
+
+After `/do` hands back control, mark the story/task that was just started as **Running** in its board file (update the `status:` field in the YAML front-matter).
+
+### 2. Return to the board — identify parallelisable tasks
+
+Collect candidates from two sources:
+
+1. **Stories** — read all files from `project/board/stories/`.
+2. **Tasks derived from stories** — read all files from `project/board/tasks/`. A task is considered in-scope if its parent story (`story_id` in the task's front-matter) is listed in `project/todo.md`, even if the task itself is not directly listed there.
+
+A story or task is **eligible** to be presented as a parallel candidate if ALL of the following are true:
+- Its status is `Pending` (not `Running`, `In Progress`, `Passed`, etc.)
+- It has no unresolved dependencies (all blocking stories/tasks are at least `Running` or `Passed`)
+- It is directly listed in `project/todo.md`, **OR** its parent story is listed in `project/todo.md`
+
+### 3. Present choices to the user
+
+Build a numbered list of eligible story titles (use `ask_user` with `choices`). **Always append "Done" as the last option.**
+
+Example:
+```
+Which task would you like to start next?
+1. Create /spinoff skill (E02_S02)
+2. Training Skill Assets & Templates (E01_S06)
+3. Done
+```
+
+If there are **no eligible tasks** (all remaining todos are blocked or already running), skip straight to step 4.
+
+### 4. Branch on user selection
+
+- If the user selects **"Done"** — exit the loop and inform the user that no more implementations will be started in this session.
+- If the user selects a task — go back to step 1 (invoke `/do` for the selected task, then loop).
+
+### 5. Loop termination
+The loop ends when:
+- The user selects "Done", OR
+- There are no more eligible parallel tasks to offer

package/skills/error/SKILL.md

@@ -0,0 +1,29 @@
+---
+name: error
+description: Guided troubleshooting flow that gathers context about an error — where it occurs, what was attempted, what went wrong, and what was expected.
+keywords:
+  - error
+  - bug
+  - fix
+  - troubleshoot
+  - debug
+  - broken
+examples:
+  - "I'm getting an error"
+  - "help me fix this bug"
+metadata: 
+  prefered_agent: tester
+---
+
+# Error — Guided Troubleshooting
+
+## Instructions
+
+Ask the following questions to understand the background of the error:
+
+1. Where does the error occur?
+2. What are you trying to do?
+3. What went wrong?
+4. What was the expected outcome?
+
+Then use the answers to investigate and resolve the issue by creating a issue using the /todo skill.

package/skills/evaluate/SKILL.md

@@ -0,0 +1,45 @@
+---
+name: evaluate
+description: Analyzes example files against a target goal and produces a structured evaluation rapport.
+---
+
+# Evaluate
+
+## Input
+
+Expects a filled `eval_invokation_template.yml` with:
+- `goal`: the confirmed target goal
+- `paths`: list of example files from `/examplify` to analyze
+
+## Steps
+
+### 1. Read Input
+Parse the provided YAML file. If `goal` is empty or `paths` is empty/missing, 
+stop and ask the user to fill in the missing fields before proceeding.
+
+### 2. Read Example Files
+Load each file listed under `paths`. These are outputs from `/examplify` and 
+represent real observed behavior in the codebase.
+
+### 3. Analyze Against Goal
+For each example file, evaluate:
+- **Qualitative observations**: What is the current behavior? How does it relate 
+  to the goal?
+- **Gaps and issues**: What is missing, broken, or misaligned relative to the goal?
+- **Score**: How well does the current behavior satisfy the goal? 
+  Use a simple 1–5 scale with a one-line justification.
+
+### 4. Synthesize
+Across all examples, identify:
+- Recurring patterns or systemic issues
+- The most critical gaps blocking the goal
+- Any areas that are already well-aligned
+
+### 5. Write Rapport
+Copy `evaluation_rapport_template.md`. Derive the rapport filename from the goal in kebab-case:
+`<target-goal-in-kebab-case>-eval.md`
+
+Fill in the rapport based on the template structure and save to `project/rapports/analysis/` with this structure.
+
+### 6. Return
+Return the rapport filename to the caller (e.g. `/improve`).

package/skills/evaluate/assets/evaluation_invokation_template.yml

@@ -0,0 +1,3 @@
+goal: ""  # The confirmed target goal (e.g. "improve checkout performance")
+paths:    # One or more paths to example files produced by /examplify
+  - ""

package/skills/evaluate/assets/evaluation_rapport_template.md

@@ -0,0 +1,24 @@
+# Evaluation Rapport: <target-goal-in-kebab-case>
+
+## Goal
+<!-- The confirmed target goal -->
+
+## References
+<!-- Comma-separated list of example files analyzed -->
+
+## Observations
+<!-- Qualitative prose per example file, grouped by file -->
+### `<file-name>`
+<!-- What does this example reveal about current behavior? -->
+
+## Gaps & Issues
+<!-- Bulleted list, most critical first -->
+- 
+
+## Score
+<!-- 1–5 with one-line justification -->
+**Score**: /5
+**Justification**: 
+
+## Summary
+<!-- 2–3 sentences synthesizing the most important findings -->

package/skills/examplify/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: examplify
+description: Explains concepts, features, use cases, and patterns based on provided context — a description, scenario, code snippet, or file. Use when the user wants to understand what something is, how it works, when to use it, or wants a concrete example.
+keywords:
+  - examplify
+  - explain
+  - example
+  - how does
+  - understand
+examples:
+  - "explain how this works"
+  - "give me an example of X"
+---
+
+# Concept Explainer
+
+## Instructions
+
+If the context is unclear or too broad, ask one focused clarifying question before proceeding. Otherwise, infer and proceed.
+
+Explain the concept by covering:
+
+1. **What it is** — a plain-language definition
+2. **Why it exists** — the problem it solves
+3. **How it works** — core mechanics
+4. **When to use it** — and when not to
+5. **Example(s)** — grounded in the user's context; show a before/after when relevant
+
+After delivering the explanation, save a copy to:
+`project/documentation/examples/<concept_and_context>.md`
+
+Derive the filename from the concept + context (lowercased, hyphenated). Tell the user where the file was saved.
+
+## Follow-up
+
+If further discussion reveals new information about the topic — a new use case, correction, or better example — ask the user:
+
+> "That adds something new to what we covered — want me to update the saved file?"
+1. Yes
+2. No
+
+If yes, append the new content under an `## Additional Notes` section. Do not overwrite the original.

package/skills/help/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: help
+description: List all available skills with a short description of what each one does. Also use this skill when the user wants to know what commands or skills are available in the project.
+keywords:
+  - help
+  - skills
+  - commands
+  - what can you do
+  - list skills
+examples:
+  - "what skills are available?"
+  - "show me all commands"
+---
+
+# Help — List Available Skills
+
+## Instructions
+
+List all available skills (from the current skill list) with a short description of what each one does. Format the output as a table with columns for the slash command and its description.
+
+## MCP Tool (Dynamic Discovery)
+
+An MCP server ships inside the `jenga-agent` package at `mcp/help/` that dynamically discovers skills at runtime.
+
+To install and run (from a consumer project that has `jenga-agent` installed):
+```bash
+cd node_modules/jenga-agent/mcp/help && npm install
+node index.js
+```
+
+Or wire it as an MCP server in `.claude/settings.json` — `jenga attach` does this automatically for the router; the help server can be added the same way, pointing `args` at `node_modules/jenga-agent/mcp/help/index.js`.
+
+The `help` tool accepts an optional `path` argument (defaults to `cwd`) and:
+1. Looks for a `.claude/skills` directory at that path, falling back to `.agents/skills`.
+2. If found, returns a list of all folder names inside it.
+3. If neither exists, returns a clear message listing the paths it checked.

package/skills/improve/SKILL.md

@@ -0,0 +1,55 @@
+---
+name: improve
+description: A skill for analyzing a codebase and producing a structured improvement plan toward a defined goal.
+---
+
+# Improve
+
+## Instructions
+
+Before doing anything, check the attached description for an explicit or implicit goal.
+
+- **Explicit goal**: clearly stated (e.g. "improve login performance")
+- **Implicit goal**: inferable from context (e.g. "the checkout flow feels slow" → goal: improve checkout performance)
+
+If no goal can be determined, ask:
+> "What's the outcome you're trying to achieve with this improvement?"
+
+Do not proceed until a goal is confirmed.
+
+---
+
+## Steps
+
+### 1. Search the Codebase
+Search for files and flows relevant to the target goal. Look for:
+- Entry points, handlers, or controllers related to the feature
+- Shared utilities or services it depends on
+- Recent changes in the area (if git history is accessible)
+
+### 2. Check Project Documentation
+Look in `project/documentation/` for `.md` files that offer insight into:
+- Architecture decisions
+- Known limitations
+- Intended behavior of the relevant area
+
+### 3. Evaluate Insight Sufficiency
+Assess whether you have enough context to evaluate current behavior against the goal.
+
+- If yes: proceed to step 5.
+- If no: proceed to step 4.
+
+### 4. Run `/examplify`
+Invoke the `/examplify` skill. Specify clearly what you want it to find out — e.g. which code paths are exercised, what inputs/outputs look like, or what edge cases exist.
+
+### 5. Run `/evaluate`
+Copy `.agents/skills/evaluate/assets/evaluation_invokation_template.yml` and fill in:
+- `paths`: path(s) to the relevant example files
+- `goal`: the confirmed target goal
+
+This generates `<target-goal-in-kebab-case>-eval.md` inside `project/rapports/analysis/`.
+
+### 6. Invoke `/todo`
+Call `/todo` with the following message:
+
+"invoke /brainstorm <path-to-evaluation-rapport>".

package/skills/index/scripts/board-index

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+python3 "$(dirname "$0")/board_index.py" "$@"