System for tracking tasks and debt via markdown files.

Install

mkdir -p .claude/skills/file-todos-mistakeknot && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11536" && unzip -o skill.zip -d .claude/skills/file-todos-mistakeknot && rm skill.zip

Installs to .claude/skills/file-todos-mistakeknot

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
258 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • Manage file-based todo tracking in the `todos/` directory
  • Create new todo items with sequential IDs
  • Manage status (pending, ready, complete) and priority (p1, p2, p3)
  • Track dependencies between todo items
  • Conduct triage of pending items
  • Integrate with code review processes

How it works

The skill manages a file-based todo system using markdown files with YAML frontmatter in a `todos/` directory. It provides workflows for creating, triaging, and completing tasks, including dependency management.

Inputs & outputs

You give it
code review feedback, debt, features, or work items
You get back
markdown files with YAML frontmatter in the `todos/` directory, organized by status, priority, and dependencies

When to use file-todos

  • Create new todo item
  • Triage technical debt
  • Track code review feedback

About this skill

<!-- compact: SKILL-compact.md — if it exists in this directory, load it instead of following the full instructions below. The compact version contains the same file naming, YAML schema, and workflow instructions. -->

File-Based Todo Tracking

todos/ directory — markdown files with YAML frontmatter for tracking code review feedback, debt, features, and work items.

File Naming

{issue_id}-{status}-{priority}-{description}.md
  • issue_id: sequential 3-digit (001, 002...) — never reused
  • status: pending (needs triage) | ready (approved) | complete (done)
  • priority: p1 (critical) | p2 (important) | p3 (nice-to-have)
  • description: kebab-case

Examples: 001-pending-p1-mailer-test.md, 002-ready-p1-fix-n-plus-1.md, 005-complete-p2-refactor-csv.md

YAML Frontmatter

---
status: ready              # pending | ready | complete
priority: p1               # p1 | p2 | p3
issue_id: "002"
tags: [rails, performance, database]
dependencies: ["001"]      # Issue IDs this is blocked by
---

Required Sections

  • Problem Statement — what is broken/missing
  • Findings — investigation results, root cause
  • Proposed Solutions — multiple options with pros/cons, effort, risk
  • Recommended Action — filled during triage
  • Acceptance Criteria — testable checklist
  • Work Log — chronological record

Optional: Technical Details, Resources, Notes. Use template at assets/todo-template.md.

Workflows

Creating a Todo

# 1. Get next ID
ls todos/ | grep -o '^[0-9]\+' | sort -n | tail -1
# 2. Copy template
cp assets/todo-template.md todos/{NEXT_ID}-pending-{priority}-{description}.md
# 3. Fill required sections, add initial Work Log entry

Create todo when: >15-20 min work, needs research/planning, has dependencies, needs approval, part of larger feature, technical debt. Act immediately when: <15 min, complete context, obvious solution, user requests it.

Triaging Pending Items

ls todos/*-pending-*.md
# For each: read Problem + Solutions, decide approve/defer/reprioritize
# Approve: rename pending→ready, update frontmatter, fill Recommended Action

Use /triage for interactive workflow.

Managing Dependencies

# What blocks this todo?
grep "^dependencies:" todos/003-*.md

# What does this todo block?
grep -l 'dependencies:.*"002"' todos/*.md

# Verify blockers complete before starting
for dep in 001 002 003; do
  [ -f "todos/${dep}-complete-*.md" ] || echo "Issue $dep not complete"
done

Work Log Entry Format

### YYYY-MM-DD - Session Title
**By:** Claude Code / Developer Name
**Actions:**
- Specific changes (include file:line refs), commands, tests, investigation results
**Learnings:**
- What worked/didn't, patterns discovered, key insights

Completing a Todo

  1. Verify all acceptance criteria checked off
  2. Add final Work Log entry
  3. mv {file}-ready-{pri}-{desc}.md {file}-complete-{pri}-{desc}.md
  4. Update frontmatter: status: complete
  5. Check for unblocked work: grep -l 'dependencies:.*"002"' todos/*-ready-*.md
  6. git commit -m "feat: resolve issue 002"

Quick Reference Commands

# Next issue ID
ls todos/ | grep -o '^[0-9]\+' | sort -n | tail -1 | awk '{printf "%03d", $1+1}'

# Unblocked p1 work
grep -l 'dependencies: \[\]' todos/*-ready-p1-*.md

# Pending triage
ls todos/*-pending-*.md

# Count by status
for status in pending ready complete; do
  echo "$status: $(ls -1 todos/*-$status-*.md 2>/dev/null | wc -l)"
done

# By tag / priority / full-text
grep -l "tags:.*rails" todos/*.md
ls todos/*-p1-*.md
grep -r "payment" todos/

Integration

TriggerFlow
Code review/clavain:quality-gates → findings → /clavain:triage → todos
PR comments/clavain:resolve → fixes + todos
Planningbrainstorm → create todo → work → complete

Key Distinctions

  • This system (todos/): markdown files, dev/project tracking, used by humans + agents
  • Rails Todo model (app/models/todo.rb): database model, user-facing feature — unrelated
  • TodoWrite tool: in-memory session tracking only, not persisted

When not to use it

  • When the task is less than 15-20 minutes of work
  • When the task has complete context and an obvious solution
  • When the task is to manage the Rails Todo database model

Limitations

  • The skill manages file-based todos in the `todos/` directory.
  • The skill does not manage the Rails Todo database model.
  • The skill does not use an in-memory session tracking system for persistence.

How it compares

This skill uses a structured file-based system for todo tracking, providing a transparent and version-controlled approach compared to in-memory or database-backed systems for development tasks.

Compared to similar skills

file-todos side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
file-todos (this skill)04moReviewBeginner
session-handoff132moReviewBeginner
spec-to-backlog83moNo flagsIntermediate
create-handoff36moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

session-handoff

davila7

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

1370

spec-to-backlog

atlassian

Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When Claude needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.

868

create-handoff

parcadei

Create handoff document for transferring work to another session

331

moai-workflow-project

modu-ai

Integrated project management system with documentation, language initialization, and template optimization modules. Use when setting up projects, generating documentation, configuring multilingual support, or optimizing templates.

29

granola-core-workflow-b

jeremylongshore

Post-meeting note processing and sharing workflow with Granola. Use when reviewing meeting notes, sharing with team members, or processing action items after meetings. Trigger with phrases like "granola post meeting", "share granola notes", "granola follow up", "process meeting notes", "granola action items".

00

reporting

comeredon

Final pipeline execution report format. Defines the structure, agent registry, Mermaid gantt chart, and change summary. Used by AnalystAgent in Phase 6.

00

Search skills

Search the agent skills registry