{"id":"a912b786-8313-4330-ae8a-1c7c1088e797","shortId":"NWng9T","kind":"skill","title":"reset-context-contamination","tagline":"Discard the accumulated drafts and framings from this thread and re-derive the task from a clean problem statement.","description":"This thread's history has become the problem - prior drafts and framings are anchoring every new attempt. Reset.\n\nFirst, 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.\n\nThen pick the path by severity:\n\n- 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.\n- 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.","tags":["reset","context","contamination","skills","tenequm","agent-skills","ai-agents","claude-code","claude-skills","clawhub","erc-8004","mpp"],"capabilities":["skill","source-tenequm","skill-reset-context-contamination","topic-agent-skills","topic-ai-agents","topic-claude-code","topic-claude-skills","topic-clawhub","topic-erc-8004","topic-mpp","topic-openclaw","topic-skills","topic-solana","topic-x402"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/tenequm/skills/reset-context-contamination","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add tenequm/skills","source_repo":"https://github.com/tenequm/skills","install_from":"skills.sh"}},"qualityScore":"0.464","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 28 github stars · SKILL.md body (973 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:04:39.625Z","embedding":null,"createdAt":"2026-05-14T19:04:44.547Z","updatedAt":"2026-05-18T19:04:39.625Z","lastSeenAt":"2026-05-18T19:04:39.625Z","tsv":"'accumul':7 'alreadi':70 'anchor':38 'anyth':97 'attempt':41 'author':114 'back':83 'becom':30 'brief':121,155,181 'cannot':110 'clean':22,135 'constraint':62 'contamin':4,95,108 'context':3,136 'critic':67 'dead':86 'deep':94 'deriv':17,79,148 'discard':5 'doesn':80 'draft':8,34,168,190 'drift':144 'earlier':167 'end':87 'entir':169 'everi':39 'extract':44,120,154 'fact':65 'factual':51 'first':43,163 'frame':10,36 'fresh':78,124 'genuin':134 'hand':118 'hard':61 'high':99 'high-stak':98 'histori':28 'in-thread':149 'involv':55 'keep':48 'known':64 'mild':143 'model':109 'new':40,131 'otherwis':191 'outcom':57 'patch':174 'path':91 'pick':89 'plain':50 'prior':33 'problem':23,32 'proceed':193 'quot':172 're':16,147 're-der':15,146 'recommend':127 'referenc':171 'reliabl':141 'reset':2,42,105,117,142 'reset-context-contamin':1 'right':184 'rule':74 'see':158 'session':132 'sever':93 'show':185 'skill' 'skill-reset-context-contamination' 'source-tenequm' 'stake':100 'start':129 'statement':24 'subag':125 'task':19,160 'term':52 'thread':13,26,151 'time':164 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-claude-skills' 'topic-clawhub' 'topic-erc-8004' 'topic-mpp' 'topic-openclaw' 'topic-skills' 'topic-solana' 'topic-x402' 'tri':72,103 'trust':112 'unsur':179 'void':165 'walk':82 'want':59 'window':137 'worth':47","prices":[{"id":"3f22b623-189c-449e-bde2-12f236012df8","listingId":"a912b786-8313-4330-ae8a-1c7c1088e797","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"tenequm","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-14T19:04:44.547Z"}],"sources":[{"listingId":"a912b786-8313-4330-ae8a-1c7c1088e797","source":"github","sourceId":"tenequm/skills/reset-context-contamination","sourceUrl":"https://github.com/tenequm/skills/tree/main/skills/reset-context-contamination","isPrimary":false,"firstSeenAt":"2026-05-14T19:04:44.547Z","lastSeenAt":"2026-05-18T19:04:39.625Z"}],"details":{"listingId":"a912b786-8313-4330-ae8a-1c7c1088e797","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"tenequm","slug":"reset-context-contamination","github":{"repo":"tenequm/skills","stars":28,"topics":["agent-skills","ai-agents","claude-code","claude-skills","clawhub","erc-8004","mpp","openclaw","skills","solana","x402"],"license":"mit","html_url":"https://github.com/tenequm/skills","pushed_at":"2026-05-14T18:04:24Z","description":"Agent skills for building, shipping, and growing software products","skill_md_sha":"4f4f39e0f1cb5956d25b4f4c30d025605ca45600","skill_md_path":"skills/reset-context-contamination/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/tenequm/skills/tree/main/skills/reset-context-contamination"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"reset-context-contamination","description":"Discard the accumulated drafts and framings from this thread and re-derive the task from a clean problem statement."},"skills_sh_url":"https://skills.sh/tenequm/skills/reset-context-contamination"},"updatedAt":"2026-05-18T19:04:39.625Z"}}