Arnie016/codex-prompt-templates / skills/auto-skill-build-supercharge-feedback-loop
auto-skill-build-supercharge-feedback-loop
VerifiedRun closed-loop evaluators for Codex Supercharge artifacts and write feedback state for future Codex sessions, subagents, and automations. Use after creating, editing, reviewing, grading, or validating Codex Supercharge skills, references, scripts, metadata, or public docs. Triggers: grade Supercharge edits, closed-loop feedback, evaluator handoff, subagent status, automation feedback. Skip when the task is a one-off repo edit outside Codex Supercharge.
Supercharge Feedback Loop
Generated by: Codex Supercharge maintenance automation.
Goal: make every meaningful Codex Supercharge create/edit/review leave a graded artifact trail and a compact handoff for the next agent or automation.
Workflow
- After changing or reviewing pack artifacts, run the feedback evaluator on the changed files or the full pack.
- Include the task, action, validation commands, and concise notes.
- Read
.agent-runs/supercharge-status.mdbefore future Supercharge work. - Promote repeated feedback items into helper fixtures, skill audit checks, or public-readiness gates.
- Keep feedback state local under
.agent-runs/; public export helpers exclude it by design.
Commands
python3 plugins/codex-supercharge/scripts/supercharge_feedback.py evaluate \
--plugin-root plugins/codex-supercharge \
--task "Describe this Supercharge change" \
--action edited \
--artifact plugins/codex-supercharge/skills/example/SKILL.md \
--command "make -C plugins/codex-supercharge ci" \
--note "What changed and what remains"
python3 plugins/codex-supercharge/scripts/supercharge_feedback.py report \
--runs-dir plugins/codex-supercharge/.agent-runs \
--last 5
For a broad sweep, omit --artifact; the evaluator scans skills, references,
scripts, metadata, and public docs.
Skip When
- The work is unrelated to
plugins/codex-supercharge. - The repo is too sensitive to persist local feedback state.
- You need hosted production traces, gateways, canaries, or live guardrails; use
$auto-skill-build-agent-reliability-loop.
References
plugins/codex-supercharge/references/supercharge-feedback-loop.mdplugins/codex-supercharge/references/agent-run-ledger.mdplugins/codex-supercharge/references/future-agi-agent-reliability-loop.md
Validation
python3 plugins/codex-supercharge/scripts/supercharge_feedback.py evaluate \
--plugin-root plugins/codex-supercharge \
--runs-dir /tmp/codex-supercharge-feedback-smoke \
--task "feedback smoke" \
--artifact plugins/codex-supercharge/skills/auto-skill-build-supercharge-feedback-loop/SKILL.md
python3 "$HOME/.codex/skills/.system/skill-creator/scripts/quick_validate.py" \
plugins/codex-supercharge/skills/auto-skill-build-supercharge-feedback-loop
The feedback run should append one JSONL batch and refresh
supercharge-status.md plus evals.md.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |