Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Tasks

ASecurity

Work on or manage records in Cloudroom Tasks, including task keys such as ABC-12.

11 stars
0 votes
0 copies
0 views
Added 10/5/2026
ai-agentsgit

Works with

cursorcli

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/5/2026

$npx -y skills add davidondrej/cloudroom-gui --skill tasks --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tasks?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Tasks
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/davidondrej-tasks/badge)](https://www.skillsdirectory.com/skills/davidondrej-tasks)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: tasks
description: "Work on or manage records in Cloudroom Tasks, including task keys such as ABC-12."
---

# Tasks

Use the `room-cli tasks` CLI to understand the assigned task, keep its record useful,
and report the outcome where the work is tracked.

For task dispatch and execution presets, read
[references/delegation.md](references/delegation.md).

## Work a task

1. Find and read the task before acting:

   ```sh
   room-cli tasks show ABC-12
   ```

   The detail includes the description, status, priority, labels, subtasks,
   comments, attachments, attached worker threads, and the GitHub pull
   requests those threads produced (from environment metadata, with state
   open/draft/merged/closed). Use
   `room-cli tasks show ABC-12 --json` when the result will drive commands or code.

   For project-wide discovery, `room-cli tasks list` returns at most 100 rows by
   default. Pass `--limit 1-500`; in JSON, continue with `nextCursor` via the
   same filters/sort and `--cursor <value>`. A task-list mutation makes an old
   cursor stale, so restart without it.

2. Fetch every relevant attachment before making assumptions about it:

   ```sh
   room-cli tasks attachment get <attachment-id> --out <path>
   ```

3. Do the work. Post one substantive comment at each meaningful milestone,
   such as a completed investigation, an implementation ready for validation,
   or a concrete blocker:

   ```sh
   room-cli tasks comment ABC-12 --body "Implemented the change; focused validation now passes."
   ```

   Add `--notify` only when the new comment should be delivered to the thread
   that authored the task's most recent agent reply. This resumes an idle
   recipient; with no prior agent reply, the comment is recorded without
   targeting an unrelated thread. In agent context, the new comment keeps the
   current thread identity and an explicit `--author`, while delivery still
   targets the prior latest responder rather than the new comment itself.

4. Attach result artifacts that belong with the task, such as reports,
   screenshots, patches, or generated files:

   ```sh
   room-cli tasks attachment add ABC-12 --file ./report.md
   room-cli tasks attachment add ABC-12 --file ./screenshot.png
   ```

   Read `references/attachments.md` for comment attachments, initial files,
   removal rules, and machine selection.

5. Set the status to match the completion criteria. Use `done` when they are
   met, or `in_review` when required review remains:

   ```sh
   room-cli tasks update ABC-12 --status in_review
   ```

   Change task hierarchy with `room-cli tasks update ABC-12 --parent ABC-10`, using
   either a task key or ID for the parent. Promote a subtask to the top level
   with `room-cli tasks update ABC-12 --no-parent`; the two parent flags cannot be
   combined.

   If the work cannot proceed, leave the status accurate and comment with the
   specific blocker, what you tried, and what would unblock it. Do not mark a
   blocked task complete.

6. Delegated threads are attached automatically. If this thread was not
   delegated from Tasks, attach it yourself so the task shows the active work:

   ```sh
   room-cli tasks attach ABC-12
   ```

   When a thread is done with a task (hand-off, respawned replacement, or a
   predecessor that died), detach it so `room-cli tasks threads ABC-12` stays
   accurate. Omit `--thread` to detach the current thread:

   ```sh
   room-cli tasks detach ABC-12 --thread thr_dead_predecessor
   ```

## Link tasks in responses

When your answer refers the user to a task — including a task you just
created — emit this leaf directive on its own line instead of writing the
key as plain text:

```md
::task{key="ABC-12"}
```

`key` is required. Optionally add `title="…"` as a display fallback shown
while the card loads and when the key no longer resolves. The rendered card
shows the live status, title, and priority, opens the task in the thread
side panel, and links to the full Tasks app. Emit one directive per line;
each renders its own card.

## Invariants

- Valid task statuses are `backlog`, `todo`, `in_progress`, `in_review`,
  `done`, and `canceled`.
- Use `in_review` when implementation is complete but still needs human or
  agent review. Use `done` only when the task's completion criteria are met.
- Write one comment per meaningful milestone. Combine related facts into a
  useful update; never spam progress pings, command-by-command narration, or
  repeated status messages.
- Comments should say what changed or was learned, what validation ran, and any
  remaining risk or blocker.
- Prefer stable task keys such as `ABC-12` for task commands. Use `--json` for
  machine-readable output and human output for quick inspection.

Attribution

davidondrejdavidondrej
View sourceSee grades on GitHubMore from davidondrej →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →