Ax
Battle-tested Agent Skills for coding agents — source-grounded, failure-driven heuristics that audit and design real surfaces. Install with npx skills.
npx -y skills add justinramos101/agent-skill-kit --skill axAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Audit or design the surfaces an AI agent consumes: as READER — AGENTS.md, llms.txt, tool descriptions, machine-readable reference, context budget; as DEVELOPER — Agent SDK, tools/MCP, structured output, error envelopes, telemetry; as END USER — a UI or computer-use target: machine-readable state, deterministic actions, approval gates. Triggers: 'AGENTS.md/llms.txt design', 'are our tool schemas agent-safe', 'MCP surface review', 'can an agent operate this UI', 'agent keeps calling the wrong tool', 'make our app agent-operable', 'is agent telemetry leaking PII'. Do NOT use for surfaces a human consumes (human developer DX, human-read docs, human-only UX), for scaffolding or enforcing repo hooks/CI gates for coding agents, or for designing evals, judges, or trace loops — measuring agent behavior is a measurement discipline, not a consumed surface.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.3 KB, as published. Nobody here has run it
AX
The three roles in which an AI agent consumes a surface. Infer the role(s); never ask which mode:
- Reader — AGENTS.md, llms.txt, tool descriptions, machine-readable reference, context budget →
references/reader.md - Developer — SDK/agent loop, tools and MCP, structured output, errors and retry, telemetry →
references/developer.md - End user — machine-readable state, deterministic actions, approval and agency →
references/end-user.md
Core principle: an agent consumes the surface alone, at machine speed, with no tooltip to fall back on. Every doc, schema, error, span, or control must let a stochastic consumer find it, parse it, recover from it, and not be harmed by it: typed contracts over prose; recovery designed in, not hoped for; the trust boundary closed by default.
Invariants
- The trust boundary is an injection surface. Tool metadata (name, description, schema) and docs loaded into agent context reach the model before any human — untrusted input: scan and pin before registration, re-review on change, and keep one leg of the lethal trifecta (private data + untrusted content + exfiltration path) broken by default.
- Errors are recovery-shaped. A failed call is the model's next input: a typed envelope with a stable code, the offending input, a recovery hint, and a retryable-vs-terminal flag — never free text to guess at.
- Machine-readable state before clever UI. Load-bearing state, actions, and results live in structure (roles, text, schema) the agent can re-read deterministically; anything living only in a tooltip, color, toast, or pixel is invisible. Gate irreversible actions in-path.
- Prose guides; gates guarantee. Docs and descriptions raise average success, not worst-case reliability — must-hold rules belong in deterministic gates the surface documents.
Workflow
- Assess. Which role(s) does the request target? State the inference and proceed; ask only when no role is inferable.
- Load only the matching reference file(s).
- Apply the named heuristics; cite each one a finding or design choice rests on.
- Emit the findings or design with the concrete fix or paste-ready shape; name the affordance you are deliberately NOT adding.
Run to completion; state assumptions inline. Stop after one emission — a second pass only if an inlined invariant was left unchecked; never a third.