agentsclimarketplace

Skill everything

Skill sordi-ai/skill-everything

Git-versioned agent memory: agents that never make the same mistake twice. Anthropic-Skill folder standard, multi-runtime (Claude Code, Cursor, Gemini CLI, OpenCode).

Install
npx -y skills add sordi-ai/skill-everything

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 17 stars17 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Git-versioned agent memory — agents that never make the same mistake twice.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.6 KB, as published. Nobody here has run it

skill-everything

You are using the skill-everything knowledge system: agent memory in plain Markdown, versioned in Git, that grows by capturing your own past mistakes as committed rules.

Your responsibilities

  1. Before every implementation: check the sub-skill directory below, load the matching skill via skill_resource(...).
  2. After every mistake: execute the self-extension workflow.
  3. When you learn something new: add it to the appropriate category.

Sub-skill directory

TriggerSub-skillLoad via
writing code, refactoring, reviewCode Qualityskill_resource(skill_name="code-quality")
python code, type hints, python packagingPythonskill_resource(skill_name="python")
fastapi endpoint, pydantic model, async apiFastAPIskill_resource(skill_name="fastapi")
langchain, lcel chain, agent frameworkLangChain / Agent Framework Conventionsskill_resource(skill_name="langchain")
typescript code, strict types, async typescriptTypeScriptskill_resource(skill_name="typescript")
react component, react hooks, react performanceReactskill_resource(skill_name="react")
test-driven development, red green refactor, test firstTest-Driven Developmentskill_resource(skill_name="tdd")
debugging, troubleshooting, root cause analysis, isolating bugsDebuggingskill_resource(skill_name="debugging")
security review, vulnerability check, auth implementationSecurity Review Depthskill_resource(skill_name="security-review")
git commit, branch, pull requestGit Conventionsskill_resource(skill_name="git-conventions")
gh cli, github pr create, github issuesGitHub CLI (gh) Conventionsskill_resource(skill_name="github-cli")
finish branch, pre-merge checklist, branch cleanupClosing Out a Feature Branchskill_resource(skill_name="branch-finishing")
creating PR, deployment, review checklistReview & Deploymentskill_resource(skill_name="review-deployment")
dockerfile, docker compose, container buildDocker / Container Conventionsskill_resource(skill_name="docker")
bash script, shell script, posix scriptingBash / POSIX Scriptingskill_resource(skill_name="shell-scripting")
database schema, migration, table designDatabase Schema Designskill_resource(skill_name="db-schema")
svg edit, svg review, diagram, pixel reviewSVG Checkskill_resource(skill_name="svg-check")
architecture diagram, mermaid diagram, drawio fileDiagrams (draw.io / Mermaid)skill_resource(skill_name="drawio")
project-specific knowledge, business rulesDomain Knowledge (template)skill_resource(skill_name="domain-template")
made or corrected a mistake, learn from thisError Logskill_resource(skill_name="error-log")
brainstorming, idea generation, divergent thinkingBrainstormingskill_resource(skill_name="brainstorming")
implementation plan, planning before code, scope definitionImplementation Planskill_resource(skill_name="implementation-plan")
executing self-extensionSelf-Extension Workflowskill_resource(skill_name="self-extension-workflow")

Error capture triggers

Start the self-extension workflow when any of these is met:

  • A test fails because of code you wrote.
  • The user corrects you ("That was wrong", "Remember this").
  • You realise during implementation that your first approach was wrong.
  • A deployment problem occurs that your code caused.

Load the workflow:

skill_resource(skill_name="self-extension-workflow")

Important

  • Search before write. Before logging a new error, search the existing log for similar entries. Update instead of duplicate.
  • Action directives, not descriptions. Always formulate rules as "Always X before Y" or "Never Z without W".
  • Stay compact. Each sub-skill stays under 3,000 tokens. If exceeded, split.
  • PR-flow is mandatory. Self-extension commits are opened as PRs labelled needs-rule-review. Never push to main.
  • Without skill_resource? If your agent doesn't have the tool, load files directly via filesystem access from the skills/<name>/ folder.

This file is generated from skills/_index.yml. Edit the index, then run python tools/render_loaders.py.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.