x-agent-resources
Skill2 starsChanged 40 days agoMITView on GitHub
Integration and usage of official X Developer Platform agent resources (llms.txt, skill.md, MCP/XMCP, xurl, OpenAPI) for accurate, composable X access in agentic apps. Use when building search, analysis, posting, or any X interaction. Ensures llms/skill ground prompts, MCP exposes tools, xurl provides CLI UX. Fission for implementation; fusion for unifying with finder-reactor and agentic design.
In this repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adversarial-auditSkill
- agentic-reactorSkill
- agent-orchestratorSkill
- ai-optimizationSkill
- architecture-synthesisSkill
- audit-allow-buildsSkill
- audit-ide-dependenciesSkill
- author-workflow-skillSkill
- bdd-strategizerSkill
- chrome-extension-mv3Skill
- concurrent-cli-agentsSkill
- control-feederSkill
- control-graphSkill
- cursor-transcript-harvestSkill
- cv-promote-guardSkill
- devcontainer-hardenedSkill
- dual-copy-skill-publishSkill
- explore-repo-readonlySkill
- finder-reactorSkill
- fix-dependency-securitySkill
- fusion-sageSkill
- git-worktreesSkill
- grok-host-prepSkill
- gt-flowSkill
- higher-order-decision-architectSkill
- looperSkill
- master-plannerSkill
- mvu-refactor-planSkill
- odysseus-navigatorSkill
- project-editor-profileSkill
- react-client-expertSkill
- semantic-markup-cssSkill
- semantic-nameSkill
- session-unit-orderSkill
- shell-kernel-ontologySkill
- skill-rename-propagationSkill
- split-to-prsSkill
- src-tree-reorganizeSkill
- stellar-roadmapSkill
- stellar-spacemapSkill
- subagent-delegationSkill
- subagent-explore-reportSkill
- supply-chain-hardenSkill
- tauri-agenticSkill
- tauri-ipc-debugSkill
- tidy-commit-pushSkill
- upgrade-packagesSkill
- verification-cockpitSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 43
Never assume X API behavior not in current skill.md/llms.
≈ “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.
Files
X Agent Resources — Official Primitives for X-Powered Agents
Core Mission: Make every X interaction correct, efficient, and agent-composable by treating official X agent resources as first-class citizens.
Key Resources (Always Reference Fresh or Cached)
- llms.txt / llms-full.txt (https://docs.x.com/llms.txt): Structured index + full Markdown docs for LLMs.
- skill.md (https://docs.x.com/skill.md): agentskills.io spec — capabilities, actions, params, constraints, workflows.
- MCP Servers: XMCP (200+ endpoints as tools); Docs MCP.
- xurl (https://github.com/xdevplatform/xurl): Official CLI with auto-auth and agent SKILL.md.
- OpenAPI: https://api.x.com/2/openapi.json
Agent read order (mandatory for X work)
- Vendored snapshot in your project (e.g.
.agents/x-resources/skill.md) — read first. - This skill — integration patterns for your app.
- Live
https://docs.x.com/...if behavior disagrees with snapshot — refresh vendored copy.
Integration Principles
- Ingest for Intelligence: LLM calls include relevant excerpts from X skill.md + llms context.
- MCP for Composability: Expose app functions (search, analyze, prep, promote) as MCP tools; use XMCP for direct X ops when richer than a custom client.
- xurl for UX & Fallback: Shell to xurl for ad-hoc or as reference implementation.
- Follow the Spec: Publish your own SKILL.md compatible with agentskills.io.
- Self-Guards Apply: MCP tool calls respect the same guards/pauses as the UI.
Implementation Patterns
- At startup / refresh: Load vendored X resources; copy to app data in production if needed.
- Backend client: Validate/build queries using skill.md knowledge; prefix prompts with current capabilities excerpt.
- MCP Server: Tools like
search_x_opportunities,analyze_and_decide,generate_prep_with_guards,promote_with_preview. - UI: Command palette maps 1:1 to MCP tools.
- Prompt library: Central file combining X skill + CV packet + app state.
- Testing: bdd-strategizer for guard scenarios (429, low rate, pause).
Guardrails
- Never assume X API behavior not in current skill.md/llms.
- Writes (posts, DMs): always guard + user pause.
- Rate limits: surface from headers; backoff in reactor.
- Auth: secure OS keyring or encrypted store — never hardcode tokens.
Related
finder-reactor, tauri-agentic, ai-optimization, fusion-sage.
Official: https://docs.x.com/tools/ai
Example provenance: collab-finder.
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.