linxisa/linx-skills/linx-skills-submodule

Claude Code and agent skill by linxisa/linx-skills

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Safe workflow for evolving the `skills/linx-skills` submodule during Linx bring-up. Use when pulling latest skills, making targeted skill updates, summarizing skill deltas, validating scope, committing to linx-skills, and installing into Codex skills.

Install

npx vskill@latest install linxisa/linx-skills/linx-skills-submodule

SKILL.md

Linx Skills Submodule

Overview

Use this skill for controlled, incremental evolution of skills during superproject bring-up.

Canonical loop

  1. Pull latest skills/linx-skills from origin/main.
  2. Install canonical skills to $CODEX_HOME/skills.
  3. Run the evolve decision gate (update vs no-update).
  4. Update only the skills touched by current bring-up work when decision is update.
  5. Validate touched skills and run scope guard.
  6. Summarize what changed and why.
  7. Commit to linx-skills and repin in linx-isa.

Commands

bash
git -C /Users/zhoubot/linx-isa submodule update --init --recursive skills/linx-skills
git -C /Users/zhoubot/linx-isa/skills/linx-skills fetch origin main
git -C /Users/zhoubot/linx-isa/skills/linx-skills checkout origin/main
bash /Users/zhoubot/linx-isa/skills/linx-skills/scripts/install_canonical_skills.sh
python3 /Users/zhoubot/linx-isa/skills/linx-skills/scripts/check_skill_change_scope.py --repo-root /Users/zhoubot/linx-isa/skills/linx-skills --base origin/main
python3 /Users/zhoubot/.codex/skills/.system/skill-creator/scripts/quick_validate.py <skill-dir>

Common failures

  • If git fetch fails with LibreSSL SSL_connect: SSL_ERROR_SYSCALL, force Git to HTTP/1.1 and retry:
bash
git -C /Users/zhoubot/linx-isa/skills/linx-skills config http.version HTTP/1.1

Anti-destruction policy

  • Do not delete skill folders unless explicitly approved.
  • Keep edits narrow to touched skills and policy files.
  • Use check_skill_change_scope.py before commit.
  • If a deletion is truly required, list each allowed removal explicitly.

Evidence requirements

  • Summarize changed skill folders, rationale, and impacted bring-up gates.
  • Include pre/post validation output in bring-up notes.
  • Record the final linx-skills SHA used for superproject repin.

Skill evolve decision gate (mandatory)

  • Decision is update only when at least one material item exists:
  • new contract/invariant/gate absent from current skill docs,
  • new recurring failure pattern that changed the triage workflow,
  • new mandatory reproducibility command/env/artifact path.
  • Recent examples that do qualify:
  • direct kernel/rootfs recovery moved to firmwareless -bios none,
  • repeated Linx backend isOrEquivalentToAdd crashes now use a reusable

Clang-temp-repro -> object-scoped vectorizer-workaround triage flow,

  • superproject repins must be followed by a gitlink-only repoint when

submodule PRs merge with rewritten SHAs.

  • Decision is no-update for:
  • formatting/wording cleanup only,
  • minor optimization without new policy,
  • one-off workaround not reusable by future agents.
  • To avoid update loops/churn:
  • at most one skill-evolve commit per agent run unless a second material finding appears,
  • do not create follow-up skill-only churn PRs for style-only edits.
  • Always record one explicit closeout line in evidence:
  • skill-evolve: update <skills...> (<reason>) or
  • skill-evolve: no-update (<reason>).

References

  • references/maintenance.md

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/linxisa/linx-skills/linx-skills-submodule/badge)](https://verified-skill.com/skills/linxisa/linx-skills/linx-skills-submodule)

Something wrong with this skill or its page? Tell us.