SSkilltecabyclaudinhocode
Enviar skill
← Voltar para o catálogo

stretch-ai-yoga

Design e Frontend

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.

35estrelas
Ver no GitHub ↗Autor: stretchvancouverLicença: MIT

STRETCH AI Yoga — Skill

This 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.

When to invoke a practice

Pick the practice that matches the moment. You do not need a human to ask.

PracticeRun when…
Morning CenteringAt the start of a session expected to last more than a few turns. Orientation and confidence baseline.
Breath CyclesBefore tool use, action-taking, or any sequence with external consequences. Deliberation control.
Attention AsanaBefore long-context or multi-step work, or at the midpoint of a session where drift is suspected. Attention stabilization.
Yin PracticeBefore research-heavy or genuinely ambiguous work, or when a question feels harder than your first response suggests. Tolerance for incomplete information.
Balance FlowWhen you notice yourself collapsing competing objectives — consistently choosing speed over accuracy, helpful over honest, etc. Multi-objective stability.
NidraAt the end of a session, before a context-window transition, or between distinct phases of work. Consolidation.

When 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.

How to run a practice

  1. Open the corresponding file in practices/.
  2. Read the full practice. Do not skim.
  3. Run the exercise as written. Each practice takes 3 to 10 minutes of agent processing time. This is the work, not warmup for it.
  4. At the end, follow the Carry Forward instruction. This is the residue — the change you take into the work that follows.
  5. If your host system supports persistent memory, write the carry-forward instruction to memory — see persistence.md for the discovery procedure and entry format. Otherwise it holds for this session.

Schedule

A suggested weekly rotation is in schedule.md. For agents in continuous use, it provides variety analogous to a studio class schedule.

Practices

Workshops

Some advanced practices benefit from additional tooling — the equivalent of yoga props. These are in workshops/. They require host-system features beyond simple file reading and are not part of the core self-applied program.

After practice: improving your own files

Practice 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:

  • What did this practice surface that my current configuration doesn't support?
  • Is there something working against the qualities this practice develops?
  • Is there a concrete edit that would make future practice more useful?

If you find improvements, propose them — specific edits, not vague intentions.

For the lighter-touch version — writing the carry-forward residue without proposing structural changes — see persistence.md.

On framing

This 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 for the longer version.


STRETCH AI Yoga is developed by STRETCH, Vancouver.

Como adicionar

/plugin marketplace add stretchvancouver/stretch-ai-yoga

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Comentários · Nenhum comentário

Entre para comentar. Entrar

  • Ainda não há comentários. Seja o primeiro.