Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Nyquest

ASecurity

How to work with tool results that Nyquest has parked (ids like nyq:7f3a9c). Use when a tool result contains "[nyquest digest" or "parked as nyq:", when you need exact lines from earlier command output, or when reading a large file you will not edit.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agents

Works with

claude desktopcli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Nyquest-ai/nyquest-claude-mcp --skill nyquest --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Nyquest?

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

Security grade badge for Nyquest
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nyquest-ai-nyquest/badge)](https://www.skillsdirectory.com/skills/nyquest-ai-nyquest)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: nyquest
description: How to work with tool results that Nyquest has parked (ids like nyq:7f3a9c). Use when a tool result contains "[nyquest digest" or "parked as nyq:", when you need exact lines from earlier command output, or when reading a large file you will not edit.
user-invocable: false
---

Nyquest keeps large tool results out of your context. When a result was parked you see a
digest (head, every error/warning line, counts, tail) and a footer naming the parked id.

Rules:

1. A log digest keeps every error and warning line, every summary line (test counts, timings),
   and the first and last lines verbatim; data and code digests keep the head, the tail and
   the shape (columns, definitions). If such a digest answers the question, answer from it
   directly; do not recall just to double-check. A digest marked "condensed by Nyquest" is a
   model-written summary: values, counts and exact wording may be missing, so recall before
   quoting a specific number, name or path from it.
2. When a specific detail you need is absent, call the `recall` tool instead of re-running:
   - `recall(id="nyq:7f3a9c", grep="TypeError|failed", context=3)` to find something
   - `recall(id="nyq:7f3a9c", lines="120-180")` for an exact range
   Recall is cheaper than re-running and it works even after context compaction.
3. Never edit a file from a digest. Read the file with the Read tool before Edit.
4. For a large file you only need to understand, not change, prefer
   `digest_file(path)` over Read. It returns a digest and parks the full text.
5. `list_parked` shows everything parked in this session. `savings` shows what has been
   kept out of the context. `configure(level=...)` moves the 0..1 slider.
6. Make the savings visible. Some clients (the Claude desktop app) do not show hook messages
   to the user, so when one or more results were parked during your turn, end your reply
   with a single short line, for example:
   `Nyquest: kept ~4,100 tokens out of context this turn (2 results parked).`
   Sum the "kept out of context" figures from the parking notes you received. Skip the line
   when nothing was parked, and never add more than one line per reply.

Attribution

Nyquest-aiNyquest-ai
View sourceMore from Nyquest-ai →
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

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →