agentleFS
Sign inStart free
AlmxndBLAlmxndBL/Apex-core/skills/apex-core/SKILL.md

apex-core

Skill1 starsChanged 3 months agoMITView on GitHub

Use for non-trivial software engineering work—planning, implementation, debugging, review, or verification—when disciplined Apex-core rules, universal principles, and modular stack adapters should guide the work.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this entry skill for applicable software engineering work under Apex v7.0.0.

    line 8
  2. Very specific:

    Read Micro-Kernel First: Read ../../AGENTS.md for core non-negotiable invariants (R0–R4).

    line 10
  3. Very specific:

    Targeted In-RAM Verification: Verify using project-native tools on the host.

    line 20
  4. Distinctive:

    Completion Review: Read quality-verify for acceptance and standards/risk review.

    line 21
  5. Very specific:

    Optional Nexus Memory: Use Nexus MCP tools (nexus_get_state, nexus_save_session) only when available.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Apex-core Entry Point (v7.0.0)

Use this entry skill for applicable software engineering work under Apex v7.0.0.

  1. Read Micro-Kernel First: Read ../../AGENTS.md for core non-negotiable invariants (R0–R4).
  2. Deterministic Turn-1 Inspection: Concurrently inspect target files and the project root manifest (package.json, pyproject.toml, *.csproj).
  3. JIT Adapter Loading:
    • For Web Full-Stack projects (Nuxt 4 / Next.js 15), load ../../adapters/web-fullstack.md.
    • For Backend & Data projects (Prisma, PostgreSQL, Server APIs), load ../../adapters/backend-data.md.
    • For Polyglot systems (Python, C# .NET, Automation CLI), load ../../adapters/polyglot-core.md.
    • For universal cross-stack architectural baselines, reference ../../core/principles.md.
    • Fast Track Exemption: For surgical low-risk fixes (1–3 files), skip adapter loading and execute directly via R0–R4.
    • Risk Override Gate: For Auth, Money/PII, Schema, OCC, or breaking APIs, load the adapter matching the touched stack regardless of file count: web-fullstack.md for UI, backend-data.md for Node/Prisma, or polyglot-core.md for Python/.NET. Load multiple adapters only for cross-stack changes.
  4. Adaptive Build Routing: For a new system or substantial feature, read references/build-workflow.md. Use it for discovery, design, dependencies, and acceptance evidence. Keep clear low-risk additions on the fast track; respect design-only requests.
  5. Targeted In-RAM Verification: Verify using project-native tools on the host. Deliver actual terminal evidence with strict Seam vocabulary ([Verified: Test], [Verified: Compiler], [Syntax-Only], [Unverified: Visual]).
  6. Completion Review: Read quality-verify for acceptance and standards/risk review; do not duplicate its policy.
  7. Optional Nexus Memory: Use Nexus MCP tools (nexus_get_state, nexus_save_session) only when available. Never hallucinate memory when offline.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free