Loom

Convert a completed Grill-Me decision log into a SuperSpec/Oracle PRD, full Linear issue graph, and Cursor/local-agent execution context. Covers post-grill synthesis, Oracle/GPT + Opus critique passes, goal-mode continuation, parent+child Linear loading, and repo-native context packs for agents without Hermes skills.

Source

superada.ai/skills/loom

Entrypoint

SKILL.md

Installability

Ready for agent install

Source spec

superada:loom

This page is designed to be the thing you send to another agent. It tells the agent where the source of truth lives, whether install is real today, and what command or manual path to follow.

Canonical source

https://superada.ai/skills/loom/

curl -sSf https://superada.ai/install/loom | sh

Install the skill described on this page from superada:loom. Review the source first, then run: curl -sSf https://superada.ai/install/loom | sh

1. 1
   Step 1

   Install the skill from the SuperAda installer.

2. 2
   Step 2

   Run after a completed Grill-Me session has settled product/spec decisions.

3. 3
   Step 3

   Assemble the source packet (grill decisions, product docs, corrections, non-goals).

4. 4
   Step 4

   Execute the full chain: spec → PRD → critique → merged spec → Linear → context pack → receipts.

• Skill contract
  superada:loom/SKILL.md

  Full nine-phase workflow from grill decisions to execution-ready Linear graph.

• Source packet sanitizer
  superada:loom/scripts/source-packet-sanitize.py

  Sanitizes grill output into a clean source packet for the spec chain.

• Helm parent merge
  superada:loom/scripts/helm-parent-merge.py

  Merges parent baseline commits across child worktrees.

• Oracle route failure receipt
  superada:loom/templates/oracle-route-failure-receipt.json

  Template for recording Oracle browser route failures and recovery attempts.

• Reference library
  superada:loom/references/

  19 incident-derived reference files covering route recovery, CDP extraction, Linear loading, and more.