wtf-p 0.1.0

package/write-the-f-paper/workflows/resume-paper.md

@@ -0,0 +1,274 @@
+<trigger>
+Use this workflow when:
+- Starting a new session on an existing paper
+- User says "continue", "what's next", "where were we", "resume"
+- Any writing operation when .planning/ already exists
+- User returns after time away from writing
+</trigger>
+
+<purpose>
+Instantly restore full project context and present clear status.
+Enables seamless session continuity for writing workflows.
+
+"Where were we?" should have an immediate, complete answer.
+</purpose>
+
+<process>
+
+<step name="detect_existing_project">
+Check if this is an existing writing project:
+
+```bash
+ls .planning/STATE.md 2>/dev/null && echo "Project exists"
+ls .planning/ROADMAP.md 2>/dev/null && echo "Roadmap exists"
+ls .planning/PROJECT.md 2>/dev/null && echo "Project file exists"
+```
+
+**If STATE.md exists:** Proceed to load_state
+**If only ROADMAP.md/PROJECT.md exist:** Offer to reconstruct STATE.md
+**If .planning/ doesn't exist:** This is a new project - route to /wtfp:new-paper
+</step>
+
+<step name="load_state">
+
+Read and parse STATE.md, then PROJECT.md:
+
+```bash
+cat .planning/STATE.md
+cat .planning/PROJECT.md
+```
+
+**From STATE.md extract:**
+
+- **Project Reference**: Core argument and current focus
+- **Current Position**: Section X of Y, Plan A of B, Status
+- **Word Count**: Current vs target
+- **Section Progress**: Which sections are done
+- **Argument Strength**: How solid is the thesis
+- **Open Questions**: Unresolved items
+- **Deferred**: Nice-to-haves logged for later
+- **Session Continuity**: Where we left off, any resume files
+
+**From PROJECT.md extract:**
+
+- **What This Is**: Document type, venue, deadline
+- **Core Argument**: The thesis
+- **Requirements**: What must be in the document
+- **Key Decisions**: Choices made about framing, scope
+
+</step>
+
+<step name="check_incomplete_work">
+Look for incomplete work that needs attention:
+
+```bash
+# Check for continue-here files (mid-plan resumption)
+ls .planning/sections/*/.continue-here*.md 2>/dev/null
+
+# Check for plans without summaries (incomplete writing)
+for plan in .planning/sections/*/*-PLAN.md; do
+  summary="${plan/PLAN/SUMMARY}"
+  [ ! -f "$summary" ] && echo "Incomplete: $plan"
+done 2>/dev/null
+```
+
+**If .continue-here file exists:**
+
+- This is a mid-plan resumption point
+- Read the file for specific resumption context
+- Flag: "Found mid-section checkpoint"
+
+**If PLAN without SUMMARY exists:**
+
+- Writing was started but not completed
+- Flag: "Found incomplete writing plan"
+</step>
+
+<step name="present_status">
+Present complete project status to user:
+
+```
+╔══════════════════════════════════════════════════════════════╗
+║  WRITING PROJECT STATUS                                       ║
+╠══════════════════════════════════════════════════════════════╣
+║  Document: [title from PROJECT.md]                            ║
+║  Venue: [target venue]                                        ║
+║                                                               ║
+║  Section: [X] of [Y] - [Section name]                        ║
+║  Plan:    [A] of [B] - [Status]                              ║
+║  Progress: [██████░░░░] XX%                                  ║
+║                                                               ║
+║  Words: [current] / [target]                                 ║
+║  Last activity: [date] - [what happened]                     ║
+╚══════════════════════════════════════════════════════════════╝
+
+[If incomplete work found:]
+⚠️  Incomplete work detected:
+    - [.continue-here file or incomplete plan]
+
+[If open questions exist:]
+❓ Open questions:
+    - [Question 1]
+    - [Question 2]
+
+[If argument strength is concerning:]
+📊 Argument status: [developing/weak]
+    - [Concern about thesis support]
+```
+
+</step>
+
+<step name="determine_next_action">
+Based on project state, determine the most logical next action:
+
+**If .continue-here file exists:**
+→ Primary: Resume from checkpoint
+→ Option: Start fresh on current plan
+
+**If incomplete plan (PLAN without SUMMARY):**
+→ Primary: Complete the incomplete plan
+→ Option: Abandon and move on
+
+**If section in progress, all plans complete:**
+→ Primary: Transition to next section
+→ Option: Review completed work
+
+**If section ready to plan:**
+Check if CONTEXT.md exists for this section:
+
+- If CONTEXT.md missing:
+  → Primary: Discuss section vision
+  → Secondary: Plan directly (skip context gathering)
+- If CONTEXT.md exists:
+  → Primary: Plan the section
+  → Option: Review roadmap
+
+**If section ready to write:**
+→ Primary: Execute next plan
+→ Option: Review the plan first
+</step>
+
+<step name="offer_options">
+Present contextual options based on project state:
+
+```
+What would you like to do?
+
+[Primary action based on state - e.g.:]
+1. Resume from checkpoint
+   OR
+1. Write next plan (/wtfp:write-section .planning/sections/XX-name/02-02-PLAN.md)
+   OR
+1. Discuss Section 3 context (/wtfp:discuss-section 3)
+   OR
+1. Plan Section 3 (/wtfp:plan-section 3)
+
+[Secondary options:]
+2. Review current section status
+3. Check word count progress
+4. Review argument strength
+5. Something else
+```
+
+Wait for user selection.
+</step>
+
+<step name="route_to_workflow">
+Based on user selection, route to appropriate workflow:
+
+- **Write plan** → Show command for user to run after clearing:
+  ```
+  ---
+
+  ## Next Up
+
+  **{section}-{plan}: [Plan Name]** — [objective from PLAN.md]
+
+  `/wtfp:write-section [path]`
+
+  <sub>`/clear` first → fresh context window</sub>
+
+  ---
+  ```
+- **Plan section** → Show command for user to run after clearing:
+  ```
+  ---
+
+  ## Next Up
+
+  **Section [N]: [Name]** — [Goal from ROADMAP.md]
+
+  `/wtfp:plan-section [section-number]`
+
+  <sub>`/clear` first → fresh context window</sub>
+
+  ---
+
+  **Also available:**
+  - `/wtfp:discuss-section [N]` — gather context first
+  - `/wtfp:research-gap [topic]` — investigate literature
+
+  ---
+  ```
+- **Review section** → Read section content, present summary
+- **Check word count** → Calculate and display progress
+- **Review argument** → Read argument-map.md, assess thesis support
+- **Something else** → Ask what they need
+</step>
+
+<step name="update_session">
+Before proceeding to routed workflow, update session continuity:
+
+Update STATE.md:
+
+```markdown
+## Session Continuity
+
+Last session: [now]
+Stopped at: Session resumed, proceeding to [action]
+Resume file: [updated if applicable]
+```
+
+This ensures if session ends unexpectedly, next resume knows the state.
+</step>
+
+</process>
+
+<reconstruction>
+If STATE.md is missing but other artifacts exist:
+
+"STATE.md missing. Reconstructing from artifacts..."
+
+1. Read PROJECT.md → Extract thesis and document info
+2. Read ROADMAP.md → Determine sections, find current position
+3. Scan *-SUMMARY.md files → Extract decisions, word counts
+4. Check paper/ directory → Count actual words written
+5. Check for .continue-here files → Session continuity
+
+Reconstruct and write STATE.md, then proceed normally.
+</reconstruction>
+
+<quick_resume>
+For users who want minimal friction:
+
+If user says just "continue" or "go":
+
+- Load state silently
+- Determine primary action
+- Execute immediately without presenting options
+
+"Continuing from [state]... [action]"
+
+This enables "just keep writing" workflow.
+</quick_resume>
+
+<success_criteria>
+Resume is complete when:
+
+- [ ] STATE.md loaded (or reconstructed)
+- [ ] Incomplete work detected and flagged
+- [ ] Clear status presented to user
+- [ ] Contextual next actions offered
+- [ ] User knows exactly where project stands
+- [ ] Session continuity updated
+</success_criteria>

package/write-the-f-paper/workflows/resume-paper.wcn.md

@@ -0,0 +1,93 @@
+<trigger>
+Use this workflow when:
+- Starting a new session on an existing paper
+- User says "continue", "what's next", "where were we", "resume"
+- Any writing operation when .planning/ already exists
+- User returns after time away from writing
+</trigger>
+
+<purpose>
+Instantly restore full project context and present clear status.
+Enables seamless session continuity for writing workflows.
+
+"Where were we?" should have an immediate, complete answer.
+</purpose>
+
+<process>
+
+[step:detect_existing_project]
+RUN: ls .planning/STATE.md 2>/dev/null && echo "Project exists"
+IF STATE.md_exists → Proceed to load_state
+IF only_ROADMAP.md/PROJECT.md_exist → Offer to reconstruct STATE.md
+IF .planning/_doesnt_exist → This is a new project - route to /wtfp:new-paper
+[/step]
+
+[step:load_state]
+RUN: cat .planning/STATE.md
+[/step]
+
+[step:check_incomplete_work]
+IF .continue-here_file_exists → - This is a mid-plan resumption point
+IF PLAN_without_SUMMARY_exists → - Writing was started but not completed
+[/step]
+
+[step:present_status]
+[/step]
+
+[step:determine_next_action]
+IF .continue-here_file_exists → → Primary: Resume from checkpoint
+IF incomplete_plan_(PLAN_without_SUMMARY) → → Primary: Complete the incomplete plan
+IF section_in_progress,_all_plans_complete → → Primary: Transition to next section
+IF section_ready_to_plan → Check if CONTEXT.md exists for this section:
+IF section_ready_to_write → → Primary: Execute next plan
+[/step]
+
+[step:offer_options]
+[/step]
+
+[step:route_to_workflow]
+[/step]
+
+[step:update_session]
+[/step]
+
+</process>
+
+<reconstruction>
+If STATE.md is missing but other artifacts exist:
+
+"STATE.md missing. Reconstructing from artifacts..."
+
+1. Read PROJECT.md → Extract thesis and document info
+2. Read ROADMAP.md → Determine sections, find current position
+3. Scan *-SUMMARY.md files → Extract decisions, word counts
+4. Check paper/ directory → Count actual words written
+5. Check for .continue-here files → Session continuity
+
+Reconstruct and write STATE.md, then proceed normally.
+</reconstruction>
+
+<quick_resume>
+For users who want minimal friction:
+
+If user says just "continue" or "go":
+
+- Load state silently
+- Determine primary action
+- Execute immediately without presenting options
+
+"Continuing from [state]... [action]"
+
+This enables "just keep writing" workflow.
+</quick_resume>
+
+<success_criteria>
+Resume is complete when:
+
+- [ ] STATE.md loaded (or reconstructed)
+- [ ] Incomplete work detected and flagged
+- [ ] Clear status presented to user
+- [ ] Contextual next actions offered
+- [ ] User knows exactly where project stands
+- [ ] Session continuity updated
+</success_criteria>

package/write-the-f-paper/workflows/review-section.md

@@ -0,0 +1,329 @@
+<purpose>
+Run three-layer verification on written sections. Extract deliverables from SUMMARY.md,
+generate verification checklist, guide user through each check, log issues.
+
+The USER performs judgment-based verification — Claude runs mechanical checks,
+identifies potential issues, and guides the verification process.
+</purpose>
+
+<three_layers>
+Academic writing verification has three distinct layers:
+
+**1. Citation Check (Mechanical)** - Claude can run this
+- All claims have citations where needed
+- Citations formatted correctly for style
+- All cited works appear in bibliography
+- No broken references or [CITE:] placeholders
+- Page numbers where required by style
+
+**2. Argument Coherence (Logical)** - Claude identifies, user verifies
+- Claims follow from evidence
+- No logical contradictions
+- Thesis supported throughout
+- Counterarguments addressed
+- Flow between paragraphs
+
+**3. Rubric Check (Requirements)** - Both verify
+- Required sections present
+- Word/page limits met
+- Formatting requirements met
+- All required elements included
+- Submission checklist complete
+</three_layers>
+
+<process>
+
+<step name="identify">
+**Determine what to verify:**
+
+If $ARGUMENTS provided:
+- Parse as section number (e.g., "4") or plan number (e.g., "04-02")
+- Find corresponding SUMMARY.md file(s)
+
+If no arguments:
+- Find most recently modified SUMMARY.md
+
+```bash
+find .planning/sections -name "*SUMMARY.md" -type f -exec ls -lt {} + | head -5
+```
+
+Read the SUMMARY.md to understand what was written.
+</step>
+
+<step name="extract">
+**Extract verifiable elements from SUMMARY.md:**
+
+Parse for:
+1. **Claims made** - Statements that need citations
+2. **Citations used** - References added
+3. **Word count** - Against target
+4. **Section goal** - Was it accomplished?
+
+Focus on VERIFIABLE outcomes:
+
+Examples:
+- "Introduction establishes research gap" → Check: gap clearly stated
+- "Three prior approaches cited" → Check: verify three relevant citations
+- "Methods section ~500 words" → Check: actual word count
+</step>
+
+<step name="layer_1_citation_check">
+**Run Citation Check (Mechanical):**
+
+Claude performs these checks directly:
+
+```
+## Layer 1: Citation Check
+
+Scanning [section/file] for citation issues...
+
+### All Claims Have Citations
+- [ ] [Claim 1] - citation: [present/missing]
+- [ ] [Claim 2] - citation: [present/missing]
+[List all factual claims and their citation status]
+
+### Citation Format
+Style: [detected/specified style - APA, IEEE, etc.]
+- [ ] Author-year format consistent
+- [ ] Et al. used correctly
+- [ ] Punctuation correct
+
+### Bibliography Match
+- [ ] All in-text citations appear in references
+- [ ] No orphan references (in bibliography but not cited)
+- [ ] All [CITE:] placeholders resolved
+
+### Issues Found
+[List any mechanical citation issues]
+```
+
+**If issues found:**
+Present for resolution before continuing.
+</step>
+
+<step name="layer_2_coherence_check">
+**Prepare Argument Coherence Check (Logical):**
+
+Claude identifies potential issues, user verifies:
+
+```
+## Layer 2: Argument Coherence
+
+### Thesis Support
+Central claim: [from argument-map.md]
+
+This section should support it by: [expected contribution]
+
+**Check:** Does the section actually advance the thesis?
+
+### Logical Flow
+Reading the section for argument structure...
+
+Paragraph flow:
+1. [Para 1 purpose] → [Para 2 purpose] → [Para 3 purpose]
+
+**Potential gaps identified:**
+- [Gap 1]: Between [X] and [Y], transition unclear
+- [Gap 2]: Claim [Z] not fully supported
+
+### Contradiction Check
+Cross-referencing with prior sections...
+
+**Potential contradictions:**
+- [None found / List any inconsistencies]
+
+### Counterargument Coverage
+For claims that might face objection:
+- [Claim]: [Counterargument addressed? Y/N]
+```
+
+Use AskUserQuestion for each potential issue:
+- header: "[Issue type]"
+- question: "[Describe the potential issue] - Is this actually a problem?"
+- options:
+  - "Not an issue" — The logic is sound
+  - "Minor issue" — Note but don't block
+  - "Major issue" — Needs fixing
+  - "Let me look" — I need to review the text
+</step>
+
+<step name="layer_3_rubric_check">
+**Run Rubric Check (Requirements):**
+
+```
+## Layer 3: Rubric Check
+
+### Required Elements
+[Based on document type and venue requirements]
+
+- [ ] [Required element 1]: [present/missing]
+- [ ] [Required element 2]: [present/missing]
+[Check all required elements for this section type]
+
+### Word Count
+Target: [from ROADMAP.md]
+Actual: [count from written content]
+Status: [within range / over / under by X%]
+
+### Formatting
+- [ ] Heading levels correct
+- [ ] Figure/table formatting (if applicable)
+- [ ] Reference style consistent
+
+### Section-Specific Requirements
+[Based on section type - e.g., for Methods:]
+- [ ] Participants/setting described
+- [ ] Procedure clear
+- [ ] Measures defined
+- [ ] Analysis approach stated
+```
+</step>
+
+<step name="collect_issues">
+**Collect and categorize all issues:**
+
+For each issue identified across three layers:
+
+```
+### Issue Summary
+
+**Layer 1 (Citation) Issues:**
+- [Issue]: [Severity] - [Brief description]
+
+**Layer 2 (Coherence) Issues:**
+- [Issue]: [Severity] - [Brief description]
+
+**Layer 3 (Rubric) Issues:**
+- [Issue]: [Severity] - [Brief description]
+```
+
+Severity levels:
+- **Critical** — Must fix before submission (factual error, missing required element)
+- **Major** — Should fix (logical gap, weak support)
+- **Minor** — Consider fixing (polish, enhancement)
+- **Note** — Awareness item (not blocking)
+</step>
+
+<step name="log_issues">
+**Log issues to section file if found:**
+
+If any Critical or Major issues:
+
+Create `.planning/sections/XX-name/{section}-ISSUES.md`:
+
+```markdown
+# Section [X] Verification Issues
+
+## Summary
+- Critical: [N]
+- Major: [N]
+- Minor: [N]
+
+## Critical Issues
+
+### CRIT-001: [Brief description]
+**Layer:** [Citation/Coherence/Rubric]
+**Location:** [paragraph/claim/element]
+**Issue:** [Full description]
+**Fix needed:** [What needs to change]
+
+## Major Issues
+
+### MAJ-001: [Brief description]
+[Same format]
+
+## Minor Issues
+[List briefly]
+
+## Verification Date
+[Date of this review]
+```
+</step>
+
+<step name="summarize">
+**Present verification summary:**
+
+```
+# Verification Results: [Section Name]
+
+## Layer Scores
+- Citation Check: [PASS/ISSUES - N issues]
+- Coherence Check: [PASS/ISSUES - N issues]
+- Rubric Check: [PASS/ISSUES - N issues]
+
+## Overall Status
+
+[Based on issues found:]
+- ALL PASS: "Section verified. Ready to proceed."
+- MINOR ONLY: "Section solid with minor polish opportunities."
+- MAJOR ISSUES: "Section needs revisions before proceeding."
+- CRITICAL: "Critical issues found - must address before continuing."
+
+## Issues by Priority
+
+[If issues exist:]
+**Must Fix:**
+- [Critical issue 1]
+- [Major issue 1]
+
+**Should Fix:**
+- [Major issue 2]
+- [Minor issue 1]
+
+**Consider:**
+- [Minor issues]
+
+## Next Steps
+[Based on verdict:]
+- If clean: Proceed to next section
+- If issues: /wtfp:plan-revision to address
+```
+</step>
+
+<step name="offer_next">
+**Offer next actions based on results:**
+
+Use AskUserQuestion:
+- header: "Next"
+- question: "What would you like to do?"
+- options (based on results):
+
+If all passed:
+- "Continue to next section" — Proceed with confidence
+- "Verify more" — Run additional checks
+- "Done" — Finish verification session
+
+If issues found:
+- "Plan revision" — Create plan to fix issues (/wtfp:plan-revision)
+- "Fix now" — Address issues immediately
+- "Log and continue" — Issues logged, proceed anyway
+- "Done" — Finish verification session
+</step>
+
+</process>
+
+<verification_by_section_type>
+**Different sections emphasize different checks:**
+
+| Section | Citation Heavy | Coherence Heavy | Rubric Heavy |
+|---------|---------------|-----------------|--------------|
+| Abstract | Low | Medium | High (word limit) |
+| Introduction | High (gap) | High (argument) | Medium |
+| Related Work | Very High | High (synthesis) | Medium |
+| Methods | Low | Medium | High (completeness) |
+| Results | Low (own data) | Medium | High (all findings) |
+| Discussion | High (context) | Very High | Medium |
+
+Adjust verification emphasis accordingly.
+</verification_by_section_type>
+
+<success_criteria>
+- [ ] Section/plan identified from SUMMARY.md
+- [ ] Layer 1 (Citation) check completed
+- [ ] Layer 2 (Coherence) issues identified for user verification
+- [ ] Layer 3 (Rubric) check completed
+- [ ] All issues categorized by severity
+- [ ] Issues logged to section ISSUES.md if Critical/Major
+- [ ] Summary presented with clear verdict
+- [ ] User knows next steps based on results
+</success_criteria>