gsd-ralph-context-loop
Orchestrate coding work with GSD (Capture→Clarify→Organize→Execute→Review) and Ralph Loop (Observe→Act→Feedback→Promote→Enforce). Use parallel agents/workflows for multi-faceted tasks. Auto-invoke when user says GSD, Ralph Loop, get shit done, work in parallel agents, context course, or all of it for context engineering. Slash: /gsd-ralph-context-loop.
Install
npx skillscat add igorganapolsky/thumbgate/gsd-ralph-context-loop Install via the SkillsCat registry.
Here's a thinking process: 1. **Analyze the Request:** - **Goal:** Write a 2-3 sentence plain-text summary in English. - **Subject:** An AI agent skill for a public software directory. - **Key Elements to Cover:** - What the skill does - What problem it solves - When an agent/developer should use it - **Constraints:** - Objective, factual tone only - No marketing language, superlatives, calls to action - Natural prose, no keywords stuffing - No bullet points, no headings, no markdown formatting - No quotes wrapping the answer - At most 60 words - **Output:** ONLY the summary text. 2.
GSD + Ralph Loop for ThumbGate coding
GSD (Get Shit Done)
| Stage | Agent does | Artifact |
|---|---|---|
| Capture | List failures / goals / evidence gaps | Notes or issue bullets |
| Clarify | Skill vs MCP vs hook vs subagent | Layer decision |
| Organize | Files, PR branch, Linear claim, vault | Ledger |
| Execute | Implement + tests (parallel when independent) | Diff + green tests |
| Review | Probes, adversarial verify, three-bus ship | TRUE/FALSE ledger |
Never jump to Execute without Clarify (wrong layer = inert gates / thrash).
Ralph Loop (always-on improvement)
| Stage | Surface |
|---|---|
| Observe | Session preflight, gate-stats, CI, vault |
| Act | Tools under PreToolUse walls |
| Feedback | Thumbs / incident / capture_feedback |
| Promote | Matchable force-gate / auto-promote |
| Enforce | gate-check + deterministic guards |
Ralph without Promote→Enforce is analytics only.
Promote without matchable surface is AGENT-259 theater.
Parallel agents (when)
| Use parallel / workflow | Stay serial |
|---|---|
| PR multi-lane review | One-line fix |
| Enforcement audit | Single file |
| Skills + docs + tests independent | Shared-file conflict |
| Linear top-10 triage | Already claimed by sibling |
Default workflows:
/pr-adversarial-review/thumbgate-enforcement-audit/context-engineering-pr-check/linear-top10-triage
Session execute recipe
# Observe
bash ~/.grok/skills/multi-agent-coord/scripts/session_preflight.sh
bash ~/.grok/skills/three-bus-ship-cycle/scripts/ship_cycle_status.sh
# GSD Capture/Clarify via checklist skill
# Execute with worktree branch
# Review
bash ~/.grok/skills/three-bus-ship-cycle/scripts/ship_cycle_check.sh <PR> <AGENT-ID>Completion gate
Before done/shipped/fixed:
- Review probes green
- Three-bus updated
- No prose-only gates
- No stolen Linear locks
Related
- [[context-engineering-checklist]]
- [[three-bus-ship-cycle]]
- [[xai-workflows-for-system]]
- [[multi-agent-coord]]
Categories
Install
npx skillscat add igorganapolsky/thumbgate/gsd-ralph-context-loop Install via the SkillsCat registry.