Claude-skill-registry libgraphql-plans
Track, organize, and maintain plans.md files and code TODOs for the libgraphql project. Use when the user asks to update plans, sync TODOs, mark tasks complete, add new tasks, identify high-impact work, or asks what's left to do in the libgraphql codebase. Triggers include phrases like "update plans", "sync TODOs", "what's left to do", "mark X as done", "track a new task", "highest-impact work", or references to plans.md files.
git clone https://github.com/majiayu000/claude-skill-registry
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/libgraphql-plans" ~/.claude/skills/majiayu000-claude-skill-registry-libgraphql-plans && rm -rf "$T"
skills/data/libgraphql-plans/SKILL.mdlibgraphql-plans
Manage project planning for the
libgraphql workspace via plans.md files and code TODO comments.
Overview
The libgraphql project tracks work in two ways:
files — Structured planning documents at crate roots and workspace rootplans.md- Code TODOs — Inline comments marking work to be done
This skill keeps these synchronized and helps prioritize work.
File Hierarchy
libgraphql/ ├── plans.md # Workspace-level plans (items outside crates) └── crates/ ├── libgraphql-parser/plans.md # Parser crate plans ├── libgraphql-core/plans.md # Core crate plans └── libgraphql-macros/plans.md # Macros crate plans
Rule: TODOs go to the nearest
plans.md — if in a crate, use that crate's file; otherwise use the root.
Workflows
1. Sync TODOs from Codebase
When asked to sync or update plans:
- Run
to find all TODOs.claude/skills/libgraphql-plans/scripts/scan_todos.py <repo-path> - For each
file, compare found TODOs against the "Appendix: Code TODOs" tableplans.md - New TODOs: Present them to the user for review before adding to the appropriate section
- Missing TODOs: If a TODO in the appendix no longer exists in code, it may have been completed or removed — investigate and update accordingly
- Regenerate the "Appendix: Code TODOs" table
- Update "Last Updated" date
2. Mark Work Complete
When asked to mark something done:
- Locate the plan item by section number (e.g., "2.1") or description
- Wholly complete:
- Move to "Past Completed Work" section with title, terse description, and date
- Check all "Definition of Done" boxes
- Partially complete:
- Leave in place
- Update "Current Progress" to reflect what's done
- Update description to reflect remaining work
- NEVER re-number plan identifiers — IDs like 2.1, 4.3 must remain stable
- Update "Last Updated" date
3. Add New Task
When asked to track a new task:
- Determine the appropriate
file based on which crate it affectsplans.md - Determine the appropriate section (or create a new section if needed)
- Draft the new plan item following the format in
references/plans_format.md - Present to user for review before adding
- Assign the next available ID within that section (never reuse IDs)
- Update "Last Updated" date
4. Identify High-Impact Work
When asked what to work on next:
- First, sync TODOs and update all
filesplans.md - Analyze by priority markers (HIGH/MEDIUM/LOW) in the Priority Summary
- Consider dependencies (blocked items vs ready items)
- Consider scope (quick wins vs large efforts)
- Present top 3-5 recommendations with rationale
TODO Comment Patterns
Scan for these patterns in
.rs files:
Explicit markers:
or// TODO:
— Standard TODO// TODO
or// FIXME:
— Bug or broken code// FIXME
— May indicate future consideration. Exclude these if they only explain something but do not indicate a need to come back and change or otherwise take action on something.// NOTE:
— Temporary solution needing cleanup// HACK:
Semantic patterns (use judgment):
- Comments mentioning "fix this", "clean up", "reconsider", "revisit"
- Comments about "temporary", "workaround", "should be changed"
- Comments with future tense about changes ("will need to", "should eventually")
Not every comment needs to become a plan item — only clear action items.
plans.md Format
See
references/plans_format.md for the full template.
General style:
- All markdown table cells in a column should have consistent width for human-readability
Key sections:
- Current State Summary — Test counts, implementation status
- Numbered Sections — Grouped by category (Testing, Performance, etc.)
- Priority Summary — HIGH/MEDIUM/LOW categorization
- Past Completed Work — Archive of finished items
- Appendix: Code TODOs — Auto-generated table of inline TODOs
Each plan item includes:
- Purpose — Why this matters
- Current Progress — What's done
- Priority — HIGH/MEDIUM/LOW
- Tasks — Numbered subtasks
- Definition of Done — Checkboxes for completion criteria
Important Rules
-
Stable IDs: Never renumber plan items. If Section 2.1 is completed, the next item in Section 2 is 2.7 (or whatever follows), not 2.1.
-
Always regenerate Code TODOs appendix when updating any
.plans.md -
Ask before adding: New items from TODO scans should be presented for user review.
-
Update timestamps: Always update "Last Updated" date when modifying a
.plans.md -
Terse completions: When moving to "Past Completed Work", use only a title and one-line description.