enterprise-software-AI-skills
CLAUDE.md1 starsChanged 15 days agoMITView on GitHub
This repository's engineering standards are always on for sessions that work inside this repo. The directive below is imported, so a session rooted in the repo or a subdirectory loads it automatically as context, with no setup and no approval, and a git pull keeps it current (Claude Code loads a project CLAUDE.md from the working directory and its parents, and a relative import loads with no prompt). The committed hook in .claude/settings.json injects the same directive into subagents as…
In this repository17 other files it gives its agents.
- arch-encodeSkill
- architectural-decision-recordsSkill
- bdd-comprehensive-testingSkill
- bootstrapSkill
- compliance-data-lifecycleSkill
- comprehensive-test-strategySkill
- enterprise-architecture-standardsSkill
- judge-archSkill
- owasp-secure-coding-bddSkill
- pattern-selectorSkill
- release-deployment-safetySkill
- skeptical-auditSkill
- sre-operational-readinessSkill
- universal-accessibility-wcagSkill
- universal-browser-device-supportSkill
- usability-ux-universal-designSkill
- verifiable-quality-gatesSkill
The file
Files
Project instructions
This repository's engineering standards are always on for sessions that work inside this repo. The
directive below is imported, so a session rooted in the repo or a subdirectory loads it automatically as
context, with no setup and no approval, and a git pull keeps it current (Claude Code loads a project
CLAUDE.md from the working directory and its parents, and a relative import loads with no prompt). The
committed hook in .claude/settings.json injects the same directive into subagents as well, including the
built-in Explore and Plan agents that do not read this file, after a one-time workspace-trust step.
These layers deliver the directive text on pull; they do not install the skills themselves, and they do
not reach every session. A session rooted above or outside this repo (for example a parent folder that
holds several repos) does not auto-load this file, and no committed file can reach another machine's
~/.claude, so broader coverage needs the one-time installer in .claude/skills/bootstrap/. See always-on/README.md
for the coverage map and its limits.
See always-on/README.md for how the two layers work and their limits, and .claude/skills/bootstrap/SKILL.md to install
the always-on hook into another project or machine.
The first import below is the universal directive (the skills + the evidence rule) that the always-on hook delivers to every repo. The second is this repo's own contributor process (the fresh-context review log, the skill receipt, the named CI checks); it is imported here, not by the hook, so only sessions working inside this repo load it, and a consumer repo is never pointed at artifacts it does not have.
@always-on/enterprise-skills-always-on.md @always-on/upstream-contributor-process.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.