SkillsAdd

tenequm/skills

reset-context-contamination

Discards the accumulated drafts and framings from this thread and re-derives the task from a clean problem statement.

First seen May 14, 2026

Installation

$ npx skills add tenequm/skills --skill reset-context-contamination
View on skills.sh ↗ GitHub repository ↗

Summary

  • Discards the accumulated drafts and framings from this thread and re-derives the task from a clean problem statement.
  • Use when the user says the thread is contaminated, that the conversation is going in circles, or that they want a fresh take, or when they invoke /reset-context-contamination.

Also in this package

Other skills from tenequm/skills · top by installs.

npx skills add tenequm/skills
chrome-extension-wxt 201 foundry-solidity 152 founder-playbook 135 shadcn-tailwind 131 gh-cli 124 swift-macos 115 python-dev 92 solana-security 91 solana-development 91 tanstack 87

Browse all from tenequm/skills

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

Repository health

Stars 35
License LICENSE
Default branch main
Open issues 0
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Version0.1.3
Declared agents clawdbot
More metadata
version
0.1.3
categories
agents
topics
context, reset, reframing, thread-hygiene
openclaw
{"homepage":"https:\/\/github.com\/tenequm\/skills\/tree\/main\/skills\/reset-context-contamination","emoji":"🧹"}

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,553 B
  • docs SUMMARY.md 328 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 21 installs

SKILL.md

This thread's history has become the problem - prior drafts and framings are anchoring every new attempt. Reset.

First, extract what's worth keeping, in plain factual terms: who is involved, the outcome I want, the hard constraints, the known facts, and - critically - what's already been tried and ruled out, so a fresh derivation doesn't walk back into a dead end.

Then pick the path by severity:

  • Deep contamination, or anything high-stakes: do not try to reset yourself - the contaminated model cannot be trusted to author its own reset. Hand the extracted brief to a fresh subagent, or recommend I start a new session. A genuinely clean context window is the only reliable reset.
  • Mild drift only: re-derive in-thread from the extracted brief, as if seeing the task for the first time. Void the earlier drafts entirely - no referencing, quoting, or patching them. If you are unsure the brief itself is right, show it to me before drafting; otherwise just proceed.