Agent skill

ctask

Manages tasks using the ctask CLI wrapper over a local SQLite database. Use when tracking work items, creating tasks, managing dependencies, adding comments, labeling, or reviewing task status. Triggers on task tracking, ticket management, work planning, backlog management.

View SKILL.md on GitHub Repository
Stars 5
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/antoniocascais/claude-code-toolkit/tree/main/skills/ctask

SKILL.md

ctask — Local Task Tracker

Use the ctask CLI to track tasks, dependencies, comments, and labels in a local SQLite database.

Prerequisites

ctask must be on $PATH. Database auto-initializes on first use.

CLI Reference

Create a task

bash
ctask create "Title" [--desc "Description"] [--priority low|medium|high|critical] [--project "name"]

List tasks

bash
ctask list [--status open|in_progress|blocked|done|cancelled] [--priority <p>] [--project <name>] [--all]

Default: excludes cancelled tasks. Use --all to show everything.

Show task details

bash
ctask show <id>

Returns task fields, labels, dependencies (blocked by / blocks), and comments.

Update a task

bash
ctask update <id> [--title "New title"] [--desc "New desc"] [--status <s>] [--priority <p>] [--project "name"]

Comments

bash
ctask comment <id> <body>       # Add comment
ctask comments <id>             # List comments

Dependencies

bash
ctask block <id> --by <blocker_id>    # Task <id> is blocked by <blocker_id>
ctask unblock <id> --by <blocker_id>  # Remove dependency
ctask deps <id>                        # Show what blocks/is blocked by

Labels

bash
ctask label <id> <label>       # Add label
ctask unlabel <id> <label>     # Remove label
ctask labels <id>              # List labels

Other

bash
ctask delete <id>              # Permanently delete task
ctask search <query>           # Search title and description

When to Act

User says... Do this
"track this" / "add a task" / "remember to..." ctask create — infer title from context, ask project if ambiguous
"what's open" / "what am I working on" ctask list --status open
"I finished X" / marks work done ctask update <id> --status done + ctask comment <id> "outcome"
"X depends on Y" / "can't do X until Y" ctask block <X> --by <Y>
"I'm stuck on X" ctask update <id> --status blocked + ctask comment <id> "why"
starts working on a task ctask update <id> --status in_progress

Always ctask list first to avoid creating duplicates.

Enums

  • Statuses: open, in_progress, blocked, done, cancelled
  • Priorities: low, medium, high, critical (list output sorts by priority desc, then date desc)

Guidelines

  • Always quote titles with double-quotes to avoid shell issues.
  • Comments are engineering logs, not status updates:
    • Bad: "done" / "updated status"
    • Good: "Fixed by switching to connection pooling — was hitting PG max_connections under load"
  • When completing: update --status done + closing comment summarizing the outcome.
  • When blocked: update --status blocked + comment explaining why + block if another task is the blocker.
  • Use --project to scope tasks when working across multiple projects.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

antoniocascais/claude-code-toolkit

test-quality

Guides strong, effective unit test generation using proven testing techniques. Use when writing unit tests, reviewing test quality, improving existing tests, generating test cases, checking test coverage strength, or when tests exist but may be weak. Triggers on: unit test, test quality, test coverage, write tests, improve tests, review tests, test strength, mutation testing, boundary testing.

5 0
Explore
antoniocascais/claude-code-toolkit

skill-forge

Creates new Claude Code skills with proper structure and best practices. Use when user wants to create a skill, update an existing skill, add a new command, scaffold a workflow, define skill hooks, or asks "how do I make a skill".

5 0
Explore
antoniocascais/claude-code-toolkit

workflow-review

Reviews Claude Code sessions and proposes workflow improvements. Use when: (1) /workflow-review command, (2) "review my workflow", "how can I improve", (3) after long sessions when nudged, (4) start of session with pending review. Analyzes tool usage patterns, CLAUDE.md configuration, and compares against CC best practices. Proposes: CLAUDE.md updates, new skills, underused CC features. Saves session summaries to .claude/workflow-reviews/ for cross-session continuity.

5 0
Explore
antoniocascais/claude-code-toolkit

git-commit

Plans and executes git commits with optional TICKET_ID prefix. Analyzes staged changes, proposes optimal commit structure (single or multiple), generates descriptive messages with technical context, and executes after user approval. Use when committing code changes, creating atomic commits, or splitting large changesets.

5 0
Explore
antoniocascais/claude-code-toolkit

clarice

Conducts realistic mock interviews with detailed feedback and scoring. Use for interview prep, behavioral questions, technical interviews, STAR practice, system design interviews, or interview coaching.

5 0
Explore
antoniocascais/claude-code-toolkit

pr-review

Reviews code changes before merging. Use when reviewing PRs, checking staged changes, reviewing diffs, code review, merge readiness check, or validating changes before commit/push.

5 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results