runx

In the author's own words, from each skill's SKILL.md — showing the first 30 of 130 files.

• runx

  Governed runtime for agent skills: discover and install portable skills, run bounded skill graphs with explicit authority, and inspect signed receipts for what happened.

  SKILL.md on GitHub (opens in a new tab)

• external-adapter-graph

  External-adapter front example; a graph whose step runs a governed subprocess adapter.

  examples/external-adapter-graph/SKILL.md on GitHub (opens in a new tab)

• external-adapter-echo

  External-adapter sub-skill; a governed subprocess adapter that echoes its inputs.

  examples/external-adapter-tool/SKILL.md on GitHub (opens in a new tab)

• github-mcp-hero

  Governed GitHub over MCP; read is admitted, out-of-scope mutation is sealed as a denial.

  examples/github-mcp-hero/SKILL.md on GitHub (opens in a new tab)

• hello-world

  Echo a first runx message through a checked-in cli-tool script.

  examples/hello-world/SKILL.md on GitHub (opens in a new tab)

• loop-orchestration

  Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy.

  examples/loop-orchestration/SKILL.md on GitHub (opens in a new tab)

• managed-agent-intake

  Managed-agent front example; a governed agent-task that drafts a triage summary.

  examples/managed-agent/SKILL.md on GitHub (opens in a new tab)

• openapi-graph

  OpenAPI front example; a graph whose step turns an OpenAPI operation into a sealed tool result.

  examples/openapi-graph/SKILL.md on GitHub (opens in a new tab)

• openapi-adapter

  External-adapter sub-skill; turns an OpenAPI operation into a sealed tool result.

  examples/openapi-tool/SKILL.md on GitHub (opens in a new tab)

• post-merge-final-outcome-publisher

  Publish a final provider-state update through the Rust thread-outbox-provider front.

  examples/post-merge-final-outcome-publisher/SKILL.md on GitHub (opens in a new tab)

• thread-outbox-provider-fetch

  Fetch fixture thread readback through the Rust thread-outbox-provider front.

  examples/thread-outbox-provider-fetch/SKILL.md on GitHub (opens in a new tab)

• thread-outbox-provider-graph

  Fixture graph that pushes and reads back a thread outbox entry through the Rust front.

  examples/thread-outbox-provider-graph/SKILL.md on GitHub (opens in a new tab)

• thread-outbox-provider-push

  Publish a fixture thread outbox entry through the Rust thread-outbox-provider front.

  examples/thread-outbox-provider-push/SKILL.md on GitHub (opens in a new tab)

• adopt-skill

  Adopt a pinned third-party SKILL.md as an exact native Runx binding bundle with deterministic source digests, a bounded execution profile, isolated harness proof, and no publication claim. Use skill-lab for first-party Runx skills.

  skills/adopt-skill/SKILL.md on GitHub (opens in a new tab)

• agency

  Run a standing team with a mandate, advanced one governed case-turn at a time: a fixed roster, a persistent objective, a multi-turn case, member dispatch under a scoped grant, escalation gates, a measurable done-check, and a sealed receipt trail.

  skills/agency/SKILL.md on GitHub (opens in a new tab)

• answer-from-docs

  Answer one question strictly from a small, caller-supplied documentation corpus, with exact supporting quotations or an explicit account of what the corpus cannot answer.

  skills/answer-from-docs/SKILL.md on GitHub (opens in a new tab)

• audit-receipt

  Audit a sealed runx receipt for governance, comparing exercised authority and any declared approval requirement with signed evidence, and flag over-reach, approval inconsistency, unrecorded refusals, or exposed secret material.

  skills/audit-receipt/SKILL.md on GitHub (opens in a new tab)

• brand-voice

  Build a scoped brand voice packet from source material so downstream agents can write, review, and adapt content without inventing brand claims.

  skills/brand-voice/SKILL.md on GitHub (opens in a new tab)

• business-ops

  Route one business signal through a replayable governed ops graph: classify, docs, release, work, outreach, spend, and proof, with consequential actions stopping at the right gate.

  skills/business-ops/SKILL.md on GitHub (opens in a new tab)

• charge

  Verify and settle one provider-side paid call through Runx Hosted with approval and provider readback.

  skills/charge/SKILL.md on GitHub (opens in a new tab)

• chief-of-staff

  Convert bounded mailbox and calendar evidence into a reviewable executive action packet.

  skills/chief-of-staff/SKILL.md on GitHub (opens in a new tab)

• content-pipeline

  Turn governed source evidence into a citation-bound reader-facing draft, channel package, and provider-neutral publication handoff.

  skills/content-pipeline/SKILL.md on GitHub (opens in a new tab)

• contract-drafter

  Draft a contract from a versioned template with explicit parties and terms, reconciling every clause against the rendered baseline deterministically and keeping delivery behind a human gate.

  skills/contract-drafter/SKILL.md on GitHub (opens in a new tab)

• crm-cleanup

  Reconcile a call transcript against current CRM records and propose allowlisted field updates, each traced to a verbatim transcript quote, with the write left to a gated CRM operator.

  skills/crm-cleanup/SKILL.md on GitHub (opens in a new tab)

• cve-audit

  Audit exact npm dependency versions against OSV through Runx native HTTP and emit replay-verified evidence with no unverified findings.

  skills/cve-audit/SKILL.md on GitHub (opens in a new tab)

• data-store

  Govern provider-agnostic data reads and state transitions through declared data-source operations, not model-authored raw queries.

  skills/data-store/SKILL.md on GitHub (opens in a new tab)

• data-subject-request

  Judge a data subject erasure or export request against explicit policy evidence, record the verdict durably through data-store, and emit only a bounded handoff for a separate governed downstream run.

  skills/data-subject-request/SKILL.md on GitHub (opens in a new tab)

• deep-research

  Produce a decision-ready deep-research brief from bounded governed evidence and preserve every material source binding.

  skills/deep-research/SKILL.md on GitHub (opens in a new tab)

• diagnose-skill-run

  Diagnose a failed or suspicious Runx skill execution from receipts and harness evidence, then propose the smallest bounded improvement without replaying the failed operation.

  skills/diagnose-skill-run/SKILL.md on GitHub (opens in a new tab)

• dispute-respond

  Prepare and explicitly file an evidence-bound payment dispute response using native receipt proof, approval, provider execution, and independent readback.

  skills/dispute-respond/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• paperclipby paperclipai The open-source app everyone uses to manage agents at work 103k stars · 30 skills
• agentsby wshobson Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi 40.9k stars · 30 skills
• invisible_dotsby feder-cr Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems. 32.1k stars · 1 skill
• distillyby titanwings Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）. 25.7k stars · 1 skill
• yaoby YaoApp ✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, o… 8.1k stars · 13 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill