wtf-p 0.4.0 → 0.5.0

package/vendors/gemini/commands/wtfp/request-feature.toml

@@ -0,0 +1,155 @@
+description = "Request a new feature via GitHub issue"
+
+prompt = '''
+<objective>
+Help the user request a new feature for WTF-P by creating a well-formatted GitHub issue.
+</objective>
+
+<context>
+@~/.config/gemini/write-the-f-paper/references/github-contrib.md
+</context>
+
+<process>
+
+## Step 1: Verify GitHub CLI
+
+Check if `gh` is authenticated:
+
+```bash
+gh auth status 2>&1
+```
+
+If not authenticated, inform the user:
+> To create GitHub issues, you need to authenticate the GitHub CLI.
+> Run: `gh auth login`
+> Then try this command again.
+
+## Step 2: Understand the Feature Request
+
+Use interactive prompting to understand what the user wants:
+
+**Question 1: Feature Category**
+- Header: "Category"
+- Options:
+  - "New command" - A new /wtfp:* slash command
+  - "Workflow enhancement" - Improve existing writing workflow
+  - "Installation/CLI" - Improve npx wtf-p experience
+  - "Template/Format" - New venue template or output format
+  - "Integration" - Connect with other tools (Zotero, Overleaf, etc.)
+
+**Question 2: Complexity**
+- Header: "Scope"
+- Options:
+  - "Small tweak" - Minor change to existing behavior
+  - "New capability" - Add something that doesn't exist
+  - "Major feature" - Significant new functionality
+
+## Step 3: Gather Feature Details
+
+Based on category, ask targeted questions:
+
+**For new command:**
+- What should `/wtfp:new-command` do?
+- When would you use it in your writing workflow?
+- What inputs does it need? What outputs?
+
+**For workflow enhancement:**
+- Which workflow needs improvement?
+- What's missing or frustrating?
+- How should it work differently?
+
+**For templates/formats:**
+- Which venue or format?
+- Do you have example requirements?
+
+## Step 4: Explore Use Case
+
+Ask user:
+- What problem does this solve for you?
+- How often would you use this?
+- Have you tried any workarounds?
+
+## Step 5: Check for Duplicates
+
+Search existing issues:
+```bash
+gh issue list --repo akougkas/wtf-p --search "[KEYWORDS]" --limit 5
+```
+
+If similar issues exist, show them to the user and ask:
+- "These similar issues exist. Should we add to one of these, or create a new issue?"
+
+## Step 6: Draft the Feature Request
+
+Create a draft:
+
+```markdown
+## Feature Description
+[Clear description of the feature]
+
+## Use Case
+[Why this is needed, what problem it solves]
+
+## Proposed Solution
+[How it should work, with examples]
+
+### Example Usage
+```
+/wtfp:new-command
+> [Expected interaction]
+```
+
+## Alternatives Considered
+[Other approaches, if discussed]
+
+## Additional Context
+[Related features, prior art, mockups]
+```
+
+## Step 7: Offer Implementation Path
+
+Ask user:
+- Header: "Next Step"
+- Options:
+  - "Create issue only" - Submit as feature request for maintainers
+  - "I'll implement it" - Create issue + guide through PR process
+  - "Help me implement" - Claude assists with implementation
+
+If user wants to implement, transition to `/wtfp:contribute` workflow.
+
+## Step 8: Create the Issue
+
+If confirmed:
+
+```bash
+gh issue create \
+  --repo akougkas/wtf-p \
+  --title "feat: [SHORT_TITLE]" \
+  --body "$(cat <<'EOF'
+[FULL_BODY_HERE]
+EOF
+)" \
+  --label "enhancement"
+```
+
+## Step 9: Report Success
+
+Show the user:
+- Issue URL
+- Issue number
+- Encourage voting/commenting to show interest
+- If they want to implement: next steps
+
+</process>
+
+<tips>
+
+**Good feature requests include:**
+- Specific use case (not just "it would be nice")
+- Example of how it would work
+- Explanation of why existing features don't solve this
+
+**Signal boost:** Encourage users to share the issue link with others who might want the feature. More reactions = higher priority.
+
+</tips>
+'''

package/vendors/gemini/commands/wtfp/research-gap.toml

@@ -0,0 +1,214 @@
+description = "Research literature and domain knowledge for a section"
+
+prompt = '''
+<execution_context>
+@~/.config/gemini/write-the-f-paper/references/research-pitfalls.md
+</execution_context>
+
+<objective>
+Perform comprehensive literature/domain research for a specific section.
+
+**Orchestrator role:** Validate project, scope research with user, resolve model profile, spawn research-synthesizer agent, present results.
+
+Creates RESEARCH.md with "how experts write this" knowledge, key citations, gaps, and positioning.
+</objective>
+
+<context>
+Section: {{args}} (section number or name)
+</context>
+
+<process>
+
+## 1. Validate Environment and Resolve Model Profile
+
+```bash
+[ ! -f .planning/PROJECT.md ] && echo "ERROR: No project. Run /wtfp:new-paper" && exit 1
+[ ! -f .planning/ROADMAP.md ] && echo "ERROR: No roadmap. Run /wtfp:create-outline" && exit 1
+```
+
+```bash
+MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
+```
+
+| Agent | quality | balanced | budget |
+|-------|---------|----------|--------|
+| research-synthesizer | opus | sonnet | haiku |
+
+## 1b. Parse Depth Flag
+
+Parse --depth from {{args}}:
+
+```bash
+# Extract depth from arguments (--depth=quick, --depth=standard, or --depth=deep)
+DEPTH_ARG=$(echo "{{args}}" | grep -oE '\-\-depth=(quick|standard|deep)' | cut -d= -f2)
+
+# If no --depth flag, read default from config
+if [ -z "$DEPTH_ARG" ]; then
+  DEPTH=$(cat .planning/config.json 2>/dev/null | grep -o '"depth"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "standard")
+else
+  DEPTH="$DEPTH_ARG"
+fi
+```
+
+**Depth mapping:**
+
+| Depth | Behavior |
+|-------|----------|
+| quick | Quick verbal summary - no RESEARCH.md created, no git commit |
+| standard | Standard research (current behavior) - 10-20 sources, RESEARCH.md created |
+| deep | Exhaustive literature review - 20-50 papers, all categories mandatory |
+
+## 2. Define Research Scope
+
+Use interactive prompting:
+- header: "Research Focus"
+- question: "What specifically do you need to understand for this section?"
+- options:
+  - "Key citations" — Who are the must-cite authors/papers?
+  - "Methodology" — How do others approach this method?
+  - "State of field" — What's the current consensus/debate?
+  - "Positioning" — How to differentiate from existing work?
+
+## 3. Read Context Files
+
+```bash
+PROJECT_CONTENT=$(cat .planning/PROJECT.md)
+ROADMAP_CONTENT=$(cat .planning/ROADMAP.md)
+ARGMAP_CONTENT=$(cat .planning/structure/argument-map.md 2>/dev/null)
+LITERATURE_CONTENT=$(cat .planning/sources/literature.md 2>/dev/null)
+BIB_INDEX=$(node ~/.config/gemini/bin/bib-index.js index references.bib 2>/dev/null || echo "No references.bib")
+
+SECTION_DIR=$(ls -d .planning/sections/${SECTION}-* 2>/dev/null | head -1)
+CONTEXT_CONTENT=$(cat "${SECTION_DIR}"/*-CONTEXT.md 2>/dev/null)
+```
+
+## 3b. Quick Depth: Verbal Summary Only
+
+**If DEPTH is "quick":**
+
+Skip agent spawn entirely. Orchestrator provides direct verbal synthesis.
+
+Read available context (PROJECT.md, argument-map, existing literature, CONTEXT_CONTENT) and synthesize a verbal summary directly to user:
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► QUICK RESEARCH SYNTHESIS
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Based on available context for Section {X}:
+
+[Synthesize key points from PROJECT, argument-map, and any existing literature.md]
+
+Key areas:
+- [Area 1]: [Brief synthesis]
+- [Area 2]: [Brief synthesis]
+
+Suggested citations to consider:
+- [If any mentioned in existing sources]
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+**Note:** Quick research -- no RESEARCH.md written. Run with `--depth=standard` for persistent research.
+```
+
+No RESEARCH.md created. No git commit. Present summary and offer next steps, then exit workflow.
+
+**If DEPTH is "standard" or "deep":** Continue to Step 4.
+
+## 4. Spawn wtfp-research-synthesizer Agent (standard/deep)
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► RESEARCHING SECTION {X} (depth: {DEPTH})
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+```
+Task(
+  prompt="First, read ~/.config/gemini/agents/wtfp/research-synthesizer.md for your role and instructions.\n\n" + filled_research_prompt,
+  subagent_type="general-purpose",
+  model="{researcher_model}",
+  description="Research Section {X}"
+)
+```
+
+Research prompt includes: `<research_scope>` with user-selected scope, `<project_context>` with PROJECT + ROADMAP + argument-map, `<existing_literature>` with bib index and literature.md, `<user_decisions>` with CONTEXT_CONTENT, `<output>` with target RESEARCH.md path, `<depth>` with current depth setting.
+
+**Depth-specific instructions in prompt:**
+
+**If DEPTH is "standard":**
+Add `<depth_instruction>Target 10-20 relevant sources across categories. Focus on most impactful papers for each category.</depth_instruction>`
+
+**If DEPTH is "deep":**
+Add `<depth_instruction>Perform exhaustive literature review. Target 20-50 papers across all categories. Include systematic field mapping: major research groups, funding bodies, key venues, citation networks. Map the intellectual lineage of the field. Identify ALL competing approaches, not just the main ones. Document methodology variations comprehensively. All 5 categories (foundational, recent, competing, gap, methods) are REQUIRED, not optional.</depth_instruction>`
+
+**Source priority hierarchy (all depths):**
+Add `<source_priority>Source priority: Context7 MCP first (if available), official sources/databases second (Google Scholar, PubMed, IEEE, ACL, arXiv), WebSearch last.</source_priority>`
+
+## 5. Handle Researcher Return
+
+**`## RESEARCH COMPLETE`:** Present findings summary.
+
+**`## RESEARCH BLOCKED`:** Show blocker, offer alternatives.
+
+## 6. Present Results
+
+</process>
+
+<offer_next>
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► RESEARCH COMPLETE ✓
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Depth: {DEPTH}
+Citations found: {N}
+Confidence: {level}
+
+───────────────────────────────────────────
+
+## ▶ Next Up
+
+**Plan section** — create writing plan with research context
+
+`/wtfp:plan-section {section}`
+
+<sub>`/clear` first → fresh context window</sub>
+
+───────────────────────────────────────────
+
+</offer_next>
+
+<offer_next_quick>
+
+**For quick depth only (no RESEARCH.md written):**
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► QUICK RESEARCH COMPLETE
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Quick research -- no RESEARCH.md written. Run with `--depth=standard` for persistent research.
+
+───────────────────────────────────────────
+
+## ▶ Next Up
+
+**Plan section** — proceed without literature doc
+
+`/wtfp:plan-section {section}`
+
+**Or deepen research:**
+
+`/wtfp:research-gap {section} --depth=standard`
+
+───────────────────────────────────────────
+
+</offer_next_quick>
+
+<success_criteria>
+- [ ] Research scope defined with user
+- [ ] Research-synthesizer spawned with full context
+- [ ] RESEARCH.md created with key citations and gaps
+- [ ] User knows next steps
+</success_criteria>
+'''

package/vendors/gemini/commands/wtfp/resume-writing.toml

@@ -0,0 +1,136 @@
+description = "Resume writing from a previous session"
+
+prompt = '''
+<objective>
+Resume work from a previous session with full context restoration.
+
+Reads STATE.md and any .continue-here.md files to restore context.
+
+Shows current position, recent progress, and offers appropriate next actions.
+</objective>
+
+<process>
+
+<step name="verify">
+**Verify project exists:**
+
+```bash
+[ ! -f .planning/STATE.md ] && echo "ERROR: No project state found. Run /wtfp:new-paper first" && exit 1
+```
+
+</step>
+
+<step name="load">
+**Load project context:**
+
+- Read STATE.md for current position and session info
+- Read PROJECT.md for paper vision
+- Read ROADMAP.md for section structure
+- Check for .continue-here.md files in section directories
+</step>
+
+<step name="check_handoff">
+**Check for handoff file:**
+
+```bash
+find .planning/sections -name ".continue-here.md" 2>/dev/null | head -1
+```
+
+If handoff file exists:
+- Read it for detailed resumption context
+- Extract: current task, remaining work, next action, blockers
+</step>
+
+<step name="present">
+**Present resumption context:**
+
+**If handoff file exists:**
+
+```
+# Resuming: [Paper Title]
+
+## Where You Left Off
+Section [N]: [Name]
+Task [X] of [Y]: [task description]
+Status: [in_progress/blocked]
+
+## Completed in Last Session
+- [Task 1]: [done]
+- [Task 2]: [done]
+
+## Remaining Work
+- [Current task]: [in progress]
+- [Next tasks]: [pending]
+
+## Context Notes
+[Notes from .continue-here.md]
+
+## Blockers (if any)
+[Any blockers noted]
+
+---
+
+## ▶ Next Action
+
+[From .continue-here.md next_action]
+
+`/wtfp:[appropriate-command]`
+
+<sub>`/clear` first if context window is full</sub>
+
+---
+```
+
+**If no handoff file:**
+
+```
+# Resuming: [Paper Title]
+
+## Current Position
+Section [N] of [total]: [Name]
+Plan [X] of [section-total]: [status]
+Words: [current] / [target]
+
+## Recent Progress
+[From STATE.md or recent SUMMARY files]
+
+---
+
+## ▶ Next Up
+
+[Based on STATE.md current position]
+
+`/wtfp:[appropriate-command]`
+
+---
+
+For full status: `/wtfp:progress`
+
+---
+```
+
+</step>
+
+<step name="cleanup">
+**Clean up handoff file after resume:**
+
+If user proceeds with next action, the handoff file should be removed:
+
+```bash
+rm .planning/sections/XX-name/.continue-here.md
+git add .planning/sections/XX-name/
+git commit -m "docs: resume [section name] from handoff"
+```
+
+</step>
+
+</process>
+
+<success_criteria>
+- [ ] STATE.md read for current position
+- [ ] Handoff file detected if exists
+- [ ] Full context presented
+- [ ] Clear next action provided
+- [ ] Routes to appropriate command
+</success_criteria>
+'''

package/vendors/gemini/commands/wtfp/review-section.toml

@@ -0,0 +1,121 @@
+description = "Review section for citations, coherence, and requirements"
+
+prompt = '''
+<execution_context>
+@~/.config/gemini/write-the-f-paper/workflows/review-section.md
+</execution_context>
+
+<objective>
+User acceptance testing of written sections with configurable reviewer personas.
+
+**Orchestrator role:** Validate section exists, select persona, resolve model profile, spawn section-reviewer agent, present results.
+
+Runs 3-layer verification:
+1. Citation Check (Mechanical)
+2. Argument Coherence (Logical)
+3. Rubric Check (Requirements)
+</objective>
+
+<context>
+Section: {{args}} (section number or path)
+</context>
+
+<process>
+
+## 1. Validate Environment and Resolve Model Profile
+
+```bash
+ls paper/*.md 2>/dev/null || echo "No content in paper/ directory"
+ls .planning/ 2>/dev/null
+```
+
+**Resolve model profile:**
+```bash
+MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
+```
+
+| Agent | quality | balanced | budget |
+|-------|---------|----------|--------|
+| section-reviewer | opus | sonnet | haiku |
+
+## 2. Select Reviewer Persona
+
+Use interactive prompting:
+- header: "Reviewer"
+- question: "What type of review do you want?"
+- options:
+  - "Friendly Mentor" — Balanced, constructive, actionable (Recommended)
+  - "Reviewer #2 (Hostile)" — Nitpicky, assumes worst, finds every flaw
+  - "Area Chair (Big Picture)" — Strategic focus on contribution and impact
+  - "Camera-Ready Editor" — Formatting, style, polish, consistency
+
+## 3. Read Context Files
+
+```bash
+SECTION_CONTENT=$(cat paper/*.md 2>/dev/null)
+PROJECT_CONTENT=$(cat .planning/PROJECT.md)
+ARGMAP_CONTENT=$(cat .planning/structure/argument-map.md 2>/dev/null)
+OUTLINE_CONTENT=$(cat .planning/structure/outline.md 2>/dev/null)
+SUMMARY_CONTENT=$(cat .planning/sections/*/SUMMARY.md 2>/dev/null | head -200)
+
+SECTION_DIR=$(ls -d .planning/sections/${SECTION}-* 2>/dev/null | head -1)
+CONTEXT_CONTENT=$(cat "${SECTION_DIR}"/*-CONTEXT.md 2>/dev/null)
+```
+
+## 4. Spawn wtfp-section-reviewer Agent
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► REVIEWING SECTION
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+```
+Task(
+  prompt="First, read ~/.config/gemini/agents/wtfp/section-reviewer.md for your role and instructions.\n\n" + filled_review_prompt,
+  subagent_type="general-purpose",
+  model="{reviewer_model}",
+  description="Review Section {X}"
+)
+```
+
+Review prompt includes: `<section_content>` with written text, `<review_persona>` with selected persona, `<project_context>` with PROJECT + argument-map + outline, `<user_decisions>` with CONTEXT_CONTENT.
+
+## 5. Handle Reviewer Return
+
+**`## REVIEW COMPLETE`:** Present results, route to next action.
+
+## 6. Present Results
+
+</process>
+
+<offer_next>
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► REVIEW COMPLETE
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+[If issues found:]
+**Plan revisions** — address identified issues
+
+`/wtfp:plan-revision XX-YY`
+
+[If no issues:]
+**Continue** — move to next section
+
+`/wtfp:plan-section [next]`
+
+<sub>`/clear` first → fresh context window</sub>
+
+───────────────────────────────────────────
+
+</offer_next>
+
+<success_criteria>
+- [ ] Reviewer persona selected
+- [ ] Section-reviewer spawned with full context
+- [ ] All 3 verification layers executed
+- [ ] Issues documented in ISSUES.md
+- [ ] Clear next steps provided
+</success_criteria>
+'''