SkillsAdd

smithery/parcadei

no-task-output

Never Use TaskOutput

Installation

$ npx skills add smithery/parcadei --skill no-task-output
View on skills.sh ↗ Website ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

apify-generate-output-schema Similar name
apify/agent-skills

Generate output schemas (dataset_schema.json, output_schema.json, key_value_store_schema.json) …

7.4K installs
create-structured-output Similar name
vapiai/skills

Design, create, inspect, update, attach, detach, preview, execute, and verify reusable Vapi Str…

54 installs
full-output-enforcement Similar name
leonxlnx/taste-skill 295.6K installs
output_format Similar name
claude-office-skills/skills

Analyze spreadsheet data, generate insights, create visualizations, and build reports from Exce…

6.8K installs
printing-press-output-review Similar name
mvanhorn/cli-printing-press

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility i…

5.7K installs
high-output-management Similar name
wondelai/skills

Manage for output using Grove''s "High Output Management": a manager''s output is their organiz…

1.9K installs

Also in this package

Other skills from smithery/parcadei · top by installs.

npx skills add smithery/parcadei
wiring 0 vector-spaces 0 validate-agent 0 trace-claude-code 0 tour 0 tldr-stats 0 tldr-router 0 tldr-overview 0 tldr-deep 0 tldr-code 0

Browse all from smithery/parcadei

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 722 B
  • docs SUMMARY.md 42 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

Never Use TaskOutput

TaskOutput floods the main context window with agent transcripts (70k+ tokens).

Rule

NEVER use TaskOutput tool. Use Task tool with synchronous mode instead.

Why

  • TaskOutput reads full agent transcript into context
  • This causes mid-conversation compaction
  • Defeats the purpose of agent context isolation

Pattern

# WRONG - floods context
Task(run_in_background=true)
TaskOutput(task_id="...")  // 70k tokens dumped

# RIGHT - isolated context, returns summary
Task(run_in_background=false)  // Agent runs, returns summary

Source

  • Session where TaskOutput caused context overflow