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.
Best use case
libgraphql-plans is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using libgraphql-plans should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/libgraphql-plans/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How libgraphql-plans Compares
| Feature / Agent | libgraphql-plans | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# libgraphql-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:
1. **`plans.md` files** — Structured planning documents at crate roots and workspace root
2. **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:
1. Run `.claude/skills/libgraphql-plans/scripts/scan_todos.py <repo-path>` to find all TODOs
2. For each `plans.md` file, compare found TODOs against the "Appendix: Code TODOs" table
3. **New TODOs:** Present them to the user for review before adding to the appropriate section
4. **Missing TODOs:** If a TODO in the appendix no longer exists in code, it may have been completed or removed — investigate and update accordingly
5. Regenerate the "Appendix: Code TODOs" table
6. Update "Last Updated" date
### 2. Mark Work Complete
When asked to mark something done:
1. Locate the plan item by section number (e.g., "2.1") or description
2. **Wholly complete:**
- Move to "Past Completed Work" section with title, terse description, and date
- Check all "Definition of Done" boxes
3. **Partially complete:**
- Leave in place
- Update "Current Progress" to reflect what's done
- Update description to reflect remaining work
4. **NEVER re-number plan identifiers** — IDs like 2.1, 4.3 must remain stable
5. Update "Last Updated" date
### 3. Add New Task
When asked to track a new task:
1. Determine the appropriate `plans.md` file based on which crate it affects
2. Determine the appropriate section (or create a new section if needed)
3. Draft the new plan item following the format in `references/plans_format.md`
4. **Present to user for review before adding**
5. Assign the next available ID within that section (never reuse IDs)
6. Update "Last Updated" date
### 4. Identify High-Impact Work
When asked what to work on next:
1. First, sync TODOs and update all `plans.md` files
2. Analyze by priority markers (HIGH/MEDIUM/LOW) in the Priority Summary
3. Consider dependencies (blocked items vs ready items)
4. Consider scope (quick wins vs large efforts)
5. Present top 3-5 recommendations with rationale
## TODO Comment Patterns
Scan for these patterns in `.rs` files:
**Explicit markers:**
- `// TODO:` or `// TODO` — Standard TODO
- `// FIXME:` or `// FIXME` — Bug or broken code
- `// NOTE:` — 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.
- `// HACK:` — Temporary solution needing cleanup
**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
1. **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.
2. **Always regenerate Code TODOs appendix** when updating any `plans.md`.
3. **Ask before adding:** New items from TODO scans should be presented for user review.
4. **Update timestamps:** Always update "Last Updated" date when modifying a `plans.md`.
5. **Terse completions:** When moving to "Past Completed Work", use only a title and one-line description.Related Skills
kitt-create-plans
Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that the AI agent will execute. Produces agent-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.
airtight-plans
Write structured multi-step implementation plans in markdown format. Plans use numbered steps with clear titles and detailed instructions. Use when asked to create an implementation plan, development roadmap, or multi-step task breakdown.
treatment-plans
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
superteam-writing-plans
Create structured implementation plans with machine-parseable task blocks
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
partner-revenue-desk
Operating model for tracking, attributing, and accelerating partner-sourced revenue.
parallel-data-enrichment
Structured company and entity data enrichment using Parallel AI Task API with core/base processors. Returns typed JSON output. No binary install — requires PARALLEL_API_KEY in .env.local.
parallel-agents
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
paper-writing-assistant
Assist in drafting research papers and meeting notes, enforcing academic rigor and formatting.
pandas-data-manipulation-rules
Focuses on pandas-specific rules for data manipulation, including method chaining, data selection using loc/iloc, and groupby operations.
pagent
Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.
page-annotator
AI驱动的网页标注工具,支持高亮元素和添加文字批注。智能防重复、自动滚动、碰撞检测。兼容 GitHub 等严格 CSP 网站。适用场景:(1) 标记网页元素进行讲解 (2) 添加文字批注和注释 (3) 代码审查和设计评审 (4) 教学演示和用户引导 (5) Bug 报告和问题标记