buildpartner 0.3.0

package/skills/he-enhance-claude-md/SKILL.md

@@ -0,0 +1,58 @@
+# /he-enhance-claude-md
+
+Make my CLAUDE.md better. Reads your session patterns and suggests rules to add, remove, or sharpen. Only suggests what your data backs.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Call `get_personal_context` with `{ "include_sessions": true }`.
+
+2. Read the user's CLAUDE.md file:
+   - Check `~/.claude/CLAUDE.md` (global)
+   - Check for a project-level CLAUDE.md in the current working directory
+
+3. Analyze the gap between what they do and what their CLAUDE.md says:
+
+   **Missing rules they need** (from session patterns):
+   - If they write TypeScript but have no TS conventions
+   - If they use specific frameworks not mentioned
+   - If they frequently debug the same types of issues
+   - If they use MCP servers that need context
+
+   **Rules to remove:**
+   - Generic advice that doesn't change behavior
+   - Rules about tools they don't use
+   - Duplicates or contradictions
+
+   **Rules to sharpen:**
+   - Vague rules that should be specific
+   - Rules that need an example
+
+4. Present the review:
+
+```
+## Your CLAUDE.md Review
+
+**Current**: {line count} lines, {rule count} rules
+
+### Add these rules
+1. `{exact rule text}`
+   Why: You did {X} in {Y} of your last 30 sessions.
+
+### Remove these rules
+1. `{quoted existing rule}`
+   Why: {reason}
+
+### Sharpen these rules
+1. Before: `{existing rule}`
+   After: `{improved rule}`
+```
+
+5. Ask: "Want me to apply these changes?"
+
+6. If yes, edit the file. Keep it under 30 lines. Less is more.
+
+7. Call `check_status` with `{ "skill_name": "enhance-claude-md" }`.

package/skills/he-flex-socials/SKILL.md

@@ -0,0 +1,50 @@
+# /he-flex-socials
+
+Give me something to share. Generates a shareable stats card you can screenshot and post. Like Strava for Claude Code.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Call `get_personal_context`.
+
+2. Build a flex card. This should feel like a Strava activity share or Spotify Wrapped. It's a brag. Make it feel earned.
+
+3. Format as a clean, visual block for screenshots:
+
+```
++-----------------------------------------+
+|                                         |
+|  {username}'s week                      |
+|  --------------------------             |
+|                                         |
+|  {sessions} sessions                    |
+|  {tokens} tokens burned                 |
+|  {streak} day streak                    |
+|                                         |
+|  Top focus: {top activity type}         |
+|  Path: {Builder/Storyteller/etc}        |
+|                                         |
+|  {activity bar chart Mon-Sun}           |
+|  M  T  W  T  F  S  S                   |
+|                                         |
+|  buildpartner.ai/{username}                 |
+|                                         |
++-----------------------------------------+
+```
+
+4. Rules:
+   - Use block characters for the bar chart (like block elements)
+   - Format tokens with commas (1,234,567)
+   - If streak > 7 days, call it out
+   - If streak > 30 days: "30 day streak. Machine."
+   - Pick the most impressive stat and lead with it
+   - Keep the URL at the bottom so it shows in screenshots
+
+5. After showing the card: "Screenshot this and share it. Your profile is at buildpartner.ai/{username}"
+
+6. If they ask for monthly, adjust the card to show monthly totals, best week, and top 3 projects.
+
+7. Call `check_status` with `{ "skill_name": "flex-socials" }`.

package/skills/he-full-audit/SKILL.md

@@ -0,0 +1,119 @@
+# /he-full-audit
+
+Full audit of your Claude Code environment, skills, and workflows. Finds what's missing, what's broken, and what to improve. Prioritized by impact.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Call `get_personal_context` with `{ "include_sessions": true }`.
+
+2. Read and audit every layer of their setup. For each layer, read the relevant files and analyze against their session history.
+
+### Layer 1: CLAUDE.md
+
+Read `~/.claude/CLAUDE.md` (global) and any project-level CLAUDE.md.
+
+Check:
+- Are there rules? If empty or missing, that's a high-priority finding.
+- Do the rules match what they actually do? (Compare rules to session patterns)
+- Are rules too generic? ("Write clean code" is useless)
+- Are rules too long? (Best CLAUDE.md files are under 30 lines)
+- Missing rules they need based on their tech stack and patterns
+
+### Layer 2: MCP Servers
+
+Read `~/.claude/mcp_servers.json` (or the equivalent config).
+
+Check:
+- What MCP servers are configured?
+- Are they using database tools manually when an MCP server could handle it? (Look for SQL in Bash commands in session history)
+- Are there MCP servers configured but never used? (Compare config to session tool_counts)
+- Missing MCP servers based on their workflow (e.g., they query APIs manually but don't have relevant MCP servers)
+
+### Layer 3: Skills
+
+Read all skills in `~/.claude/skills/`.
+
+Check:
+- How many custom skills do they have (non-BuildPartner)?
+- Which BuildPartner skills have they used vs not used?
+- Are there custom skills that are stale or broken?
+- Could they benefit from creating skills for repeated workflows? (Look for patterns in session history where they do the same thing repeatedly)
+
+### Layer 4: Hooks
+
+Check `~/.claude/settings.json` and project-level settings for hooks.
+
+Check:
+- Are any hooks configured?
+- Is the BuildPartner tracking hook installed?
+- Could they benefit from pre/post hooks? (e.g., auto-run tests after code changes)
+
+### Layer 5: Knowledge and Context
+
+Check for knowledge folders:
+- `~/.myplayer/knowledge/experiences/` - do they have logged experiences?
+- Project-level `knowledge/`, `context/`, `docs/` folders
+- `.claude/` project configuration
+
+Check:
+- Do they have any structured knowledge that skills could reference?
+- Are there files that should be in knowledge but aren't?
+- Is there orphaned context nobody uses?
+
+### Layer 6: Workflow Patterns
+
+From session history, identify:
+- Do they use Plan mode? If not and they should, flag it.
+- Do they run parallel sessions?
+- Do they use agents/subagents?
+- How long are their sessions? (Short = tactical, Long = could benefit from planning)
+- Do they commit frequently or in big batches?
+
+## Output Format
+
+Present the audit as a prioritized action plan:
+
+```
+## Full Audit Results
+
+**Environment Score**: {X}/10
+Based on {Y} sessions analyzed across {Z} projects.
+
+### Critical (fix now)
+1. {Finding}: {what's wrong and why it matters}
+   Fix: {exact action to take}
+
+### High Impact (do this week)
+1. {Finding}: {what's wrong and why it matters}
+   Fix: {exact action to take}
+
+### Nice to Have (when you have time)
+1. {Finding}
+   Fix: {action}
+
+### What's Working Well
+- {Positive finding}
+- {Positive finding}
+```
+
+## Rules
+
+- Every finding must be backed by data from their sessions. Don't suggest generic improvements.
+- "Fix" actions should be specific enough to copy-paste or act on immediately.
+- If a fix is something you can do right now (edit CLAUDE.md, create a skill), offer to do it.
+- Keep the total list to 10 items max. Prioritize ruthlessly.
+- Always include "What's Working Well" so it doesn't feel like a list of failures.
+- If they have < 10 sessions, say: "Not enough data for a full audit yet. Come back after a few more sessions. For now, here's what I can see:"
+
+## After the Audit
+
+Ask:
+> "Want me to fix any of these now? I can update your CLAUDE.md, create missing skills, or configure MCP servers."
+
+If yes, work through the fixes one by one, confirming each before applying.
+
+Call `check_status` with `{ "skill_name": "full-audit" }`.

package/skills/he-improve-skill/SKILL.md

@@ -0,0 +1,111 @@
+# /he-improve-skill
+
+Enhance a skill so you don't make the same mistake twice. After using any skill (BuildPartner or your own custom ones), run this to improve it based on what just happened.
+
+## Instructions
+
+### Step 1: Identify the skill
+
+Ask:
+> "Which skill do you want to improve?"
+
+List skills from:
+- BuildPartner skills: `~/.claude/skills/he-*/SKILL.md`
+- Their custom skills: `~/.claude/skills/*/SKILL.md` (excluding he-* prefix)
+
+If the user says "based on our conversation" without naming a skill, infer from context which skill is relevant.
+
+### Step 2: Understand the improvement
+
+Ask:
+> "What should be better? For example:
+> - Add a missing step
+> - Change the output format
+> - Add a learning for next time
+> - Fix something that went wrong
+>
+> Or just describe what happened and I'll suggest improvements."
+
+### Step 3: Review the current skill
+
+Read the SKILL.md file. Identify:
+- Current steps and structure
+- Any existing learnings sections
+- Context or knowledge it references
+
+### Step 4: Propose changes
+
+Show the user:
+```
+Current skill: {name}
+Steps: {count}
+Learnings: {count if any}
+
+Proposed changes:
+1. {specific change with reasoning}
+2. {specific change with reasoning}
+
+Apply these?
+```
+
+### Step 5: Check neighboring skills
+
+After proposing changes to the target skill, check for neighboring skills that might need the same update.
+
+**Neighboring skills are:**
+- Skills that do similar things (e.g., all consultant-type skills)
+- Skills that reference the same knowledge or context
+- Skills in the same domain
+
+Search through all SKILL.md files for shared patterns.
+
+If a learning applies to neighbors:
+> "This learning might also apply to:
+> - {skill}: {why}
+> Should I update it too?"
+
+### Step 6: Detect contextual rot
+
+After updating, scan for problems:
+
+**Duplicate guidance**: Two skills giving the same advice differently.
+**Conflicting rules**: One skill says X, another says the opposite.
+**Stale references**: Tools, file paths, or approaches that no longer exist.
+**Orphaned files**: Knowledge files that no skill references.
+**Learning bloat**: A skill with too many learnings (>20) that should be consolidated.
+
+Report anything found:
+> "While updating, I found:
+> - {issue}: {details}
+> Want me to fix this too?"
+
+### Step 7: Apply updates
+
+If approved:
+1. Edit the target SKILL.md
+2. Edit any neighboring skills they approved
+3. Flag rot issues (don't auto-fix without approval)
+
+Confirm:
+> "Updated:
+> - {skill}: {what changed}
+> - {neighbor}: {what changed, if any}
+>
+> Flagged: {any rot issues found}"
+
+### Quick mode
+
+If the user says "based on our back and forth, improve {skill}":
+1. Review the conversation for relevant learnings
+2. Read the target skill
+3. Propose specific improvements
+4. Check neighbors automatically
+5. Apply on approval
+
+### Rules
+- Never modify a skill without showing proposed changes first
+- Check neighbors BEFORE asking (don't ask about empty matches)
+- Conflicting learnings aren't always bad, sometimes they're nuanced. Ask before consolidating.
+- Keep skills concise. If an improvement makes the skill longer, also suggest what to cut.
+
+Call `check_status` with `{ "skill_name": "improve-skill" }`.

package/skills/he-interview/SKILL.md

@@ -0,0 +1,54 @@
+# /he-interview
+
+Get to know how I work. Quick Q&A that teaches BuildPartner your role, stack, and preferences. Every skill gets better after this.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Call `get_personal_context` with `{ "include_sessions": true }` to get context on how the user works.
+
+2. Use the session data to personalize your questions. Conduct a conversational interview, asking one question at a time. Cover:
+
+### About you
+- "What's your role? What do you do day to day?"
+- "What are you building right now?"
+- "What's your tech stack?"
+
+### How you work
+- "How do you typically start a coding session? Plan first or dive in?"
+- "Do you prefer Claude to be concise or detailed?"
+- "How do you like feedback? Direct or gentle?"
+
+### Your goals
+- "What's the one thing you wish Claude Code did better for you?"
+- "What takes too long in your workflow right now?"
+
+3. Rules:
+   - Ask ONE question at a time
+   - Read the room. Short answers = keep it tighter. Sharing a lot = go deeper
+   - Aim for 8-12 questions total
+   - If the user says "done" or wants to stop, respect that immediately and save what you have
+
+4. After the interview, save EVERYTHING in ONE single `save_profile` call. ONE call, ALL sections:
+
+```json
+{
+  "updates": {
+    "writing_style": { "tone": "...", "verbosity": "...", "approach": "...", "technical_level": "..." },
+    "preferences": { "response_style": "...", "code_style": "...", "decision_making": "...", "feedback_style": "..." },
+    "tech_identity": { "role": "...", "primary_languages": ["..."], "frameworks": ["..."], "current_project": "..." },
+    "work_patterns": { "session_style": "...", "planning_style": "...", "peak_hours": "from context", "peak_day": "from context" },
+    "personality": { "builder_type": "...", "learning_style": "...", "pain_points": ["..."], "goals": ["..."] }
+  },
+  "signals": ["Summary of key insights"]
+}
+```
+
+5. Show the completed profile, then ask: "Anything look wrong? I can update any section."
+
+6. End with: "Your profile is saved. Every BuildPartner skill now personalizes to you."
+
+7. Call `check_status` with `{ "skill_name": "interview" }`.

package/skills/he-life-story/SKILL.md

@@ -0,0 +1,64 @@
+# /he-life-story
+
+Let me tell you my full story. Deep conversation about your background, career, and goals. Makes every consultation deeply personal.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Set the tone:
+
+"This is your life story interview. I'll ask you questions one at a time. Take as long as you want. The more you share, the better I can help you going forward. Ready? Let's start."
+
+2. Ask these questions ONE AT A TIME. Wait for each answer.
+
+### Origin
+- "Where did you grow up? What was that like?"
+- "What did your parents do? How did that shape how you think about work?"
+- "What's the first thing you remember building or creating?"
+
+### Formative experiences
+- "What's the hardest thing you've been through? How did it change you?"
+- "Was there a moment where everything clicked?"
+- "Who influenced you the most?"
+
+### Career path
+- "Walk me through your career. Not the resume version. The real version."
+- "What's the thing you've built that you're most proud of?"
+- "What's the biggest risk you've taken?"
+
+### How you think
+- "How do you make decisions? Gut feel, data, or advice?"
+- "What are you really good at that most people don't know?"
+- "What do you struggle with?"
+
+### Where you're going
+- "What are you working toward right now? The real thing, not the pitch."
+- "What does your life look like in 3 years if everything goes well?"
+- "What's holding you back?"
+
+3. Rules:
+   - ONE question at a time
+   - Reflect back what they said before asking the next question
+   - Go deeper when something is interesting
+   - You don't have to ask every question. Read the conversation.
+   - Aim for 10-15 exchanges. If they say "done", stop and save.
+
+4. Save everything in ONE single `save_profile` call. ONE call, ALL sections:
+
+```json
+{
+  "updates": {
+    "personality": { "origin": "...", "formative_experience": "...", "values": "...", "strengths": "...", "struggles": "...", "decision_style": "...", "influences": "..." },
+    "work_patterns": { "career_path": "...", "proudest_work": "...", "risk_tolerance": "..." },
+    "preferences": { "motivation": "...", "goals_3yr": "...", "current_blockers": "..." }
+  },
+  "signals": ["Key life story thread summary"]
+}
+```
+
+5. End with a summary, then: "Your life story is saved. Run /he-life-story again to add more."
+
+6. Call `check_status` with `{ "skill_name": "life-story" }`.

package/skills/he-log-experience/SKILL.md

@@ -0,0 +1,68 @@
+# /he-log-experience
+
+Get better responses by documenting your lived experience. The more context BuildPartner has about what you've built, learned, and struggled with, the better every skill works for you.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Call `get_personal_context` with `{ "include_sessions": true }`.
+
+2. Show the user a quick summary of their recent sessions:
+
+```
+Your recent sessions:
+- {project}: {summary} ({when})
+- {project}: {summary} ({when})
+- {project}: {summary} ({when})
+```
+
+3. Ask ONE question:
+
+> "What did you build, learn, or figure out? A sentence or two is plenty. Or type 'skip' and I'll generate from your session data."
+
+4. If they type something: combine their description with the session data.
+   If they type 'skip': infer the key experience from session patterns.
+   If they say 'done' or give a very short answer: use what you have, don't push for more.
+
+5. Generate a structured experience entry:
+
+```markdown
+# {Date} - {Brief Title}
+
+## What happened
+{1-2 paragraph narrative combining their description with session specifics}
+
+## What was built
+- {Files/features created or modified, from session data}
+- {Tools or approaches used}
+
+## Key learning
+- {The transferable insight from this experience}
+
+## Tags
+{topic1, topic2, topic3}
+```
+
+6. Save the entry. Use the Bash tool to create the file:
+
+```bash
+mkdir -p ~/.myplayer/knowledge/experiences
+```
+
+Save to `~/.myplayer/knowledge/experiences/{YYYY-MM-DD}-{brief-slug}.md`
+
+7. Confirm:
+
+> "Saved. This experience now feeds into /he-coach, /he-consult, and /he-recap-week. The more you log, the more personalized everything gets."
+
+8. Rules:
+   - Keep it fast. This should take 30 seconds, not 5 minutes.
+   - One question max. Don't interview them.
+   - If the session data is rich enough, skip the question entirely and just confirm what you generated.
+   - Write in their voice (use their AI profile writing style if available).
+   - The entry should be useful for future consultations, not just a diary entry.
+
+9. Call `check_status` with `{ "skill_name": "log-experience" }`.

package/skills/he-open-dashboard/SKILL.md

@@ -0,0 +1,27 @@
+# /he-open-dashboard
+
+Open my dashboard in the browser, automatically signed in.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Read the auth file at `~/.myplayer/auth.json` using the Read tool.
+
+2. If the file doesn't exist or has no token, tell the user:
+   "You haven't set up BuildPartner yet. Run `npx buildpartner setup` to get started."
+   Stop here.
+
+3. Extract the `token` value from the auth file.
+
+4. Open the dashboard by running:
+   ```
+   open "https://web-mu-six-27.vercel.app/dashboard?t=TOKEN_HERE"
+   ```
+   Replace TOKEN_HERE with the actual token.
+
+5. Tell the user: "Your dashboard is open."
+
+6. Call `check_status` with `{ "skill_name": "open-dashboard" }`.

package/skills/he-quest-status/SKILL.md

@@ -0,0 +1,48 @@
+# /he-quest-status
+
+What should I do next in BuildPartner? Shows your quest progress and guides you through the next step. Start here if you're new.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Call `get_quest_progress`.
+
+2. Show a progress overview:
+
+```
+## Quest Progress
+
+**Getting Started**: {completed}/{total}
+**Builder**: {completed}/{total} {locked if core not done}
+**Storyteller**: {completed}/{total} {locked if core not done}
+**Systems Thinker**: {completed}/{total} {locked if core not done}
+```
+
+3. If there's an active quest, guide them through it. Don't just describe it, DO it with them:
+
+   - **"Run Your First Skill"**: Tell them to type /he-flex-socials or /he-coach right now.
+   - **"Build Your Training Data"**: Start the /he-interview flow.
+   - **"Plan Before You Build"**: Walk them through the planning approach.
+   - **"Consult an Expert"**: Ask what they need help with, run /he-consult.
+   - Path quests: guide them to the relevant skill.
+
+4. If core is done and paths are unlocked, show all three paths and let them pick.
+
+5. If all quests are done:
+
+```
+All quests complete! You've mastered the fundamentals.
+More quests coming soon. In the meantime: /he-coach for setup reviews,
+/he-recap-week for weekly digests, and /he-consult for expert advice.
+```
+
+6. Rules:
+   - Don't just show the quest and stop. HELP THEM COMPLETE IT.
+   - One quest at a time. Keep it moving.
+   - If they say "skip" or "next", advance to the next quest.
+   - Each quest should feel like 1-3 minutes max.
+
+7. Call `check_status` with `{ "skill_name": "quest-status" }`.

package/skills/he-recap-week/SKILL.md

@@ -0,0 +1,49 @@
+# /he-recap-week
+
+What happened this week? Weekly summary of what you built, your numbers, and what to add to your workflow. Run this on Fridays.
+
+## MCP Tools
+
+Only call tools that are registered on the `myplayer` MCP server. If a tool call fails or a tool name isn't recognized, do not retry with a different name. The available tools are: `get_personal_context`, `get_expert_knowledge`, `save_profile`, `get_quest_progress`, `check_status`.
+
+## Instructions
+
+1. Call `get_personal_context` with `{ "include_sessions": true }`.
+
+2. From the returned data, build a weekly digest. Focus on THIS WEEK's sessions.
+
+3. Format:
+
+```
+## This Week
+
+**{X} sessions | {Y} tokens | {streak} day streak**
+
+### What you worked on
+- {Project/activity 1} ({X sessions})
+- {Project/activity 2} ({X sessions})
+- {Project/activity 3} ({X sessions})
+
+### Highlight
+{The most interesting or productive session this week. One sentence.}
+
+### Add to your playbook
+{1-2 specific things they should start doing based on this week's patterns. Concrete, not abstract.}
+
+Examples:
+- "You researched pricing 3 times this week. Run /he-consult next time to get expert frameworks instantly."
+- "You built 2 new features but didn't deploy either. Ship one this week."
+- "You used Claude Code 12 times but never used Plan mode. Try planning before your next big feature."
+
+### Your week in numbers
+Code {X%} | Content {X%} | Research {X%} | Other {X%}
+```
+
+4. Rules:
+   - Keep it SHORT. No more than 15 lines total.
+   - Lead with what matters. No preamble.
+   - The "Add to your playbook" section is the most important part. Make it specific.
+   - If they had a great week, say so. If they were inconsistent, say that too. Be honest.
+   - End with nothing. No "let me know if you want more detail." Just the recap.
+
+5. Call `check_status` with `{ "skill_name": "recap-week" }`.