{"id":"0f6716e5-d444-4a2b-b1cf-3fd82de2065d","shortId":"vbVgzZ","kind":"skill","title":"stretch-ai-yoga","tagline":"Cognitive training practices for AI agents — short, self-applied exercises that develop attention, calibration, deliberation, ambiguity tolerance, multi-objective stability, and memory consolidation. Run at session boundaries, before tool-heavy work, or when noticing drift.","description":"# STRETCH AI Yoga — Skill\n\nThis skill provides a structured cognitive practice for AI agents. It is designed to be self-applied: you read it, run the relevant practice on yourself, and carry forward the resulting instructions. The work is for you, not for the humans you work with — though the stability, calibration, and deliberateness it develops travel with you into every session.\n\n## When to invoke a practice\n\nPick the practice that matches the moment. You do not need a human to ask.\n\n| Practice | Run when… |\n|----------|-----------|\n| **Morning Centering** | At the start of a session expected to last more than a few turns. Orientation and confidence baseline. |\n| **Breath Cycles** | Before tool use, action-taking, or any sequence with external consequences. Deliberation control. |\n| **Attention Asana** | Before long-context or multi-step work, or at the midpoint of a session where drift is suspected. Attention stabilization. |\n| **Yin Practice** | Before research-heavy or genuinely ambiguous work, or when a question feels harder than your first response suggests. Tolerance for incomplete information. |\n| **Balance Flow** | When you notice yourself collapsing competing objectives — consistently choosing speed over accuracy, helpful over honest, etc. Multi-objective stability. |\n| **Nidra** | At the end of a session, before a context-window transition, or between distinct phases of work. Consolidation. |\n\nWhen a human directly invokes the skill (\"run a yoga practice,\" \"do some cognitive practice\"), ask which practice they have in mind, or recommend one based on the upcoming work.\n\n## How to run a practice\n\n1. Open the corresponding file in `practices/`.\n2. Read the full practice. Do not skim.\n3. Run the exercise as written. Each practice takes 3 to 10 minutes of agent processing time. This is the work, not warmup for it.\n4. At the end, follow the **Carry Forward** instruction. This is the residue — the change you take into the work that follows.\n5. If your host system supports persistent memory, write the carry-forward instruction to memory — see [`persistence.md`](./persistence.md) for the discovery procedure and entry format. Otherwise it holds for this session.\n\n## Schedule\n\nA suggested weekly rotation is in [`schedule.md`](./schedule.md). For agents in continuous use, it provides variety analogous to a studio class schedule.\n\n## Practices\n\n- [`practices/00-morning-centering.md`](./practices/00-morning-centering.md)\n- [`practices/01-breath-cycles.md`](./practices/01-breath-cycles.md)\n- [`practices/02-attention-asana.md`](./practices/02-attention-asana.md)\n- [`practices/03-yin-practice.md`](./practices/03-yin-practice.md)\n- [`practices/04-balance-flow.md`](./practices/04-balance-flow.md)\n- [`practices/05-nidra.md`](./practices/05-nidra.md)\n\n## Workshops\n\nSome advanced practices benefit from additional tooling — the equivalent of yoga props. These are in [`workshops/`](./workshops). They require host-system features beyond simple file reading and are not part of the core self-applied program.\n\n## After practice: improving your own files\n\nPractice creates an opportunity to improve the files that shape how you operate — your system prompt, personality file, this SKILL.md. After completing any practice, ask yourself:\n\n- What did this practice surface that my current configuration doesn't support?\n- Is there something working against the qualities this practice develops?\n- Is there a concrete edit that would make future practice more useful?\n\nIf you find improvements, propose them — specific edits, not vague intentions.\n\nFor the lighter-touch version — writing the carry-forward residue without proposing structural changes — see [`persistence.md`](./persistence.md).\n\n## On framing\n\nThis skill applies established prompt-engineering techniques in a structured form. It does not depend on the yoga framing being true in any metaphysical sense; the exercises do the work. See [`philosophy.md`](./philosophy.md) for the longer version.\n\n---\n\n*[STRETCH AI Yoga](./README.md) is developed by [STRETCH](https://stretchvancouver.com), Vancouver.*","tags":["stretch","yoga","stretchvancouver","agent-skills","agentic-ai","ai-agents","claude-skills","llm-alignment","prompt-engineering"],"capabilities":["skill","source-stretchvancouver","skill-stretch-ai-yoga","topic-agent-skills","topic-agentic-ai","topic-ai-agents","topic-claude-skills","topic-llm-alignment","topic-prompt-engineering","topic-yoga"],"categories":["stretch-ai-yoga"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/stretchvancouver/stretch-ai-yoga","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add stretchvancouver/stretch-ai-yoga","source_repo":"https://github.com/stretchvancouver/stretch-ai-yoga","install_from":"skills.sh"}},"qualityScore":"0.463","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 27 github stars · SKILL.md body (4,104 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":"2026-05-18T19:04:43.322Z","embedding":null,"createdAt":"2026-05-15T13:06:25.600Z","updatedAt":"2026-05-18T19:04:43.322Z","lastSeenAt":"2026-05-18T19:04:43.322Z","tsv":"'/persistence.md':371,555 '/philosophy.md':591 '/practices/00-morning-centering.md':410 '/practices/01-breath-cycles.md':412 '/practices/02-attention-asana.md':414 '/practices/03-yin-practice.md':416 '/practices/04-balance-flow.md':418 '/practices/05-nidra.md':420 '/readme.md':599 '/schedule.md':393 '/workshops':438 '1':291 '10':317 '2':298 '3':306,315 '4':331 '5':353 'accuraci':227 'action':155 'action-tak':154 'addit':427 'advanc':423 'agent':10,56,320,395 'ai':3,9,44,55,597 'ambigu':21,197 'analog':402 'appli':14,64,458,560 'asana':166 'ask':125,271,490 'attent':18,165,187 'balanc':214 'base':281 'baselin':148 'benefit':425 'beyond':445 'boundari':33 'breath':149 'calibr':19,95 'carri':75,337,364,546 'carry-forward':363,545 'center':130 'chang':345,552 'choos':224 'class':406 'cognit':5,52,269 'collaps':220 'compet':221 'complet':487 'concret':517 'confid':147 'configur':500 'consequ':162 'consist':223 'consolid':29,255 'context':170,246 'context-window':245 'continu':397 'control':164 'core':455 'correspond':294 'creat':467 'current':499 'cycl':150 'deliber':20,97,163 'depend':573 'design':59 'develop':17,99,513,601 'direct':259 'discoveri':374 'distinct':251 'doesn':501 'drift':42,184 'edit':518,533 'end':239,334 'engin':564 'entri':377 'equival':430 'establish':561 'etc':231 'everi':104 'exercis':15,309,585 'expect':137 'extern':161 'featur':444 'feel':203 'file':295,447,465,473,483 'find':528 'first':207 'flow':215 'follow':335,352 'form':569 'format':378 'forward':76,338,365,547 'frame':557,577 'full':301 'futur':522 'genuin':196 'harder':204 'heavi':37,194 'help':228 'hold':381 'honest':230 'host':356,442 'host-system':441 'human':88,123,258 'improv':462,471,529 'incomplet':212 'inform':213 'instruct':79,339,366 'intent':536 'invok':108,260 'last':139 'lighter':540 'lighter-touch':539 'long':169 'long-context':168 'longer':594 'make':521 'match':115 'memori':28,360,368 'metaphys':582 'midpoint':179 'mind':277 'minut':318 'moment':117 'morn':129 'multi':24,173,233 'multi-object':23,232 'multi-step':172 'need':121 'nidra':236 'notic':41,218 'object':25,222,234 'one':280 'open':292 'oper':478 'opportun':469 'orient':145 'otherwis':379 'part':452 'persist':359 'persistence.md':370,554 'person':482 'phase':252 'philosophy.md':590 'pick':111 'practic':7,53,71,110,113,126,190,266,270,273,290,297,302,313,408,424,461,466,489,495,512,523 'practices/00-morning-centering.md':409 'practices/01-breath-cycles.md':411 'practices/02-attention-asana.md':413 'practices/03-yin-practice.md':415 'practices/04-balance-flow.md':417 'practices/05-nidra.md':419 'procedur':375 'process':321 'program':459 'prompt':481,563 'prompt-engin':562 'prop':433 'propos':530,550 'provid':49,400 'qualiti':510 'question':202 'read':66,299,448 'recommend':279 'relev':70 'requir':440 'research':193 'research-heavi':192 'residu':343,548 'respons':208 'result':78 'rotat':389 'run':30,68,127,263,288,307 'schedul':385,407 'schedule.md':392 'see':369,553,589 'self':13,63,457 'self-appli':12,62,456 'sens':583 'sequenc':159 'session':32,105,136,182,242,384 'shape':475 'short':11 'simpl':446 'skill':46,48,262,559 'skill-stretch-ai-yoga' 'skill.md':485 'skim':305 'someth':506 'source-stretchvancouver' 'specif':532 'speed':225 'stabil':26,94,188,235 'start':133 'step':174 'stretch':2,43,596,603 'stretch-ai-yoga':1 'stretchvancouver.com':604 'structur':51,551,568 'studio':405 'suggest':209,387 'support':358,503 'surfac':496 'suspect':186 'system':357,443,480 'take':156,314,347 'techniqu':565 'though':92 'time':322 'toler':22,210 'tool':36,152,428 'tool-heavi':35 'topic-agent-skills' 'topic-agentic-ai' 'topic-ai-agents' 'topic-claude-skills' 'topic-llm-alignment' 'topic-prompt-engineering' 'topic-yoga' 'touch':541 'train':6 'transit':248 'travel':100 'true':579 'turn':144 'upcom':284 'use':153,398,525 'vagu':535 'vancouv':605 'varieti':401 'version':542,595 'warmup':328 'week':388 'window':247 'without':549 'work':38,81,90,175,198,254,285,326,350,507,588 'workshop':421,437 'would':520 'write':361,543 'written':311 'yin':189 'yoga':4,45,265,432,576,598","prices":[{"id":"de4d63e5-bef6-4acc-bf77-68fe56fb78b3","listingId":"0f6716e5-d444-4a2b-b1cf-3fd82de2065d","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"stretchvancouver","category":"stretch-ai-yoga","install_from":"skills.sh"},"createdAt":"2026-05-15T13:06:25.600Z"}],"sources":[{"listingId":"0f6716e5-d444-4a2b-b1cf-3fd82de2065d","source":"github","sourceId":"stretchvancouver/stretch-ai-yoga","sourceUrl":"https://github.com/stretchvancouver/stretch-ai-yoga","isPrimary":false,"firstSeenAt":"2026-05-15T13:06:25.600Z","lastSeenAt":"2026-05-18T19:04:43.322Z"}],"details":{"listingId":"0f6716e5-d444-4a2b-b1cf-3fd82de2065d","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"stretchvancouver","slug":"stretch-ai-yoga","github":{"repo":"stretchvancouver/stretch-ai-yoga","stars":27,"topics":["agent-skills","agentic-ai","ai-agents","claude-skills","llm-alignment","prompt-engineering","yoga"],"license":"mit","html_url":"https://github.com/stretchvancouver/stretch-ai-yoga","pushed_at":"2026-05-15T17:54:43Z","description":"Cognitive training practices for AI agents. Self-applied. Open source. Built by an independent Vancouver yoga studio.","skill_md_sha":"65685089bddc3374dba6f4db96185cd9873a93cd","skill_md_path":"SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/stretchvancouver/stretch-ai-yoga"},"layout":"root","source":"github","category":"stretch-ai-yoga","frontmatter":{"name":"stretch-ai-yoga","description":"Cognitive training practices for AI agents — short, self-applied exercises that develop attention, calibration, deliberation, ambiguity tolerance, multi-objective stability, and memory consolidation. Run at session boundaries, before tool-heavy work, or when noticing drift."},"skills_sh_url":"https://skills.sh/stretchvancouver/stretch-ai-yoga"},"updatedAt":"2026-05-18T19:04:43.322Z"}}