Updated 2w ago
by githubevents
build-once-run-on-any-agent
Resources and demos for Build once, run on any agent.
21 GitHub stars (21)
+11 in 18 days
| Period | New stars |
|---|---|
| Oct 31 | +1 |
| Nov 1 | 0 |
| Nov 2 | +1 |
| Nov 3 | +3 |
| Nov 4 | 0 |
| Nov 5 | 0 |
| Nov 6 | −1 |
| Nov 7 | 0 |
| Nov 8 | 0 |
| Nov 9 | 0 |
| Nov 10 | 0 |
| Nov 11 | 0 |
| Nov 12 | 0 |
| Nov 13 | 0 |
| Nov 14 | +3 |
| Nov 15 | +2 |
| Nov 16 | +2 |
| Nov 17 | 0 |
- 6 skills (6 skills found in its SKILL.md files)
- 5 forks (5 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add githubevents/build-once-run-on-any-agent
Asks which skills and agents to install. Just one: npx skills add githubevents/build-once-run-on-any-agent --skill proof-agent — add -g for every project.
Claude Code
git clone https://github.com/githubevents/build-once-run-on-any-agentcp -r "build-once-run-on-any-agent/demos/proof-agent" ~/.claude/skills/
Copies the proof-agent skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add githubevents/build-once-run-on-any-agent
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
proof-agent
Adversarial verification of AI-generated work. Spawns an independent verifier to check for false claims, broken code, and security issues.
demos/proof-agent/ on GitHub (opens in a new tab)SKILL.md -
proof-review
Adversarial verification of bugfix PRs through production-shaped load reproduction. Use whenever the user asks to review a PR that claims to fix a bug, verify whether a fix is complete, reproduce a timeout or failure, find missed root causes, load-test a change, or produce a verdict-style verification report on a pull request. Trigger on phrases like "proof review", "verify the fix under load", "…
demos/proof-review/ on GitHub (opens in a new tab)SKILL.md -
forge-builder
Universal 7-phase metric pipeline builder. Autonomously discovers upstream data, reasons about metric requirements as a data analyst, engineers pipeline code as a data engineer, and deploys as a data architect. Handles GitHub issue intake with spec-challenge quality gates, source table discovery, metric design, pipeline generation (Daily + Cumulative), schema DDL, ALTER scripts, unit tests, deplo…
demos/dataforge/ on GitHub (opens in a new tab)skills/ forge-builder/ SKILL.md -
forge-dbx
Data platform CLI orchestration driven by dataforge.manifest.yaml. Authenticate to zones, discover and trigger jobs (schema changes, pipeline loads, ad-hoc scripts), execute SQL, explore catalogs, and monitor runs. Supports Databricks and DuckDB engines behind one interface. Reads all project-specific values (zones, profiles, catalogs, job names) from the dataforge manifest so no hardcoded busine…
demos/dataforge/ on GitHub (opens in a new tab)skills/ forge-dbx/ SKILL.md -
forge-init
Cold-start manifest discovery engine. Reads a minimal seed dataforge.manifest.yaml (Tier 1 + optional Tier 2 overrides), auto-discovers all remaining configuration via the platform CLI and codebase scanning, then writes the full dataforge.manifest.resolved.yaml for sub-skills. Supports Databricks (Unity Catalog) and DuckDB (information_schema) engines. Triggers on "forge-init", "initialize datafo…
demos/dataforge/ on GitHub (opens in a new tab)skills/ forge-init/ SKILL.md -
forge-lint
Mandatory standards reference for any manifest-driven metric store. MUST be read before ANY modification to pipeline code, SQL, schema, or job configuration files. Enforces naming conventions, SQL formatting, join strategies, schema alignment, and quality gates -- all parameterized via the dataforge manifest. Triggers on "forge-lint", "dataforge lint", "check standards", "naming convention", "met…
demos/dataforge/ on GitHub (opens in a new tab)skills/ forge-lint/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.