Two tiny Claude Code skills that fixed my two biggest agent problems

A developer at dualform labs released two open-source skills for Claude Code that address common agent failures: spec, which forces upfront clarification of ambiguous tasks, and review-audit, which performs a read-only audit across six axes with evidence. Both are single prompt files under Apache-2.0 with no dependencies.

Two open-source skills for Claude Code. Each is a single prompt file, Apache-2.0, no dependencies. Repos at the bottom. Working with a coding agent, I kept hitting the same two failure modes. Not "the model can't write code" — it writes code fine. The failures were upstream and downstream of the code: the agent guessing on an ambiguous task , and me trusting a review that hadn't actually checked anything. So I built one small skill for each. Here's what they do and why they're shaped the way they are. Hand a vague task to an agent and you watch the same thing happen. It guesses. It drifts. It quietly makes a call you'd have made differently — and you find out after the code is written, when changing your mind is expensive. The cost isn't the typing. It's the rework. spec moves the decisions to the front. You run /spec <one-line idea , it reads your repo and the conversation, then asks only what it Two things keep it honest: done only after it ran on a real case and the output was shown.The whole skill is one prompt file SKILL.md . No build, no dependencies. Ask an AI to "review this change" and you can get a confident, plausible PASS — that skipped half the checks, cited no evidence, and never ran the tests. A green light you can't trust is worse than no review. review-audit is a read-only, single-pass audit over your change across six axes: correctness, wiring built-but-never-called / dead code , security, test efficacy, spec compliance, and regression. The discipline is simple and strict: file:line + grep/run evidence. "I didn't check this" is a first-class output, not a silent gap. file:line . "Looks fine" isn't evidence.It runs in the calling agent's own context — no sub-agent fan-out — so it stays cheap enough to run on every change. When one pass genuinely isn't enough a release gate, a high-risk change , it tells you, in its own output, to escalate. Both are one prompt file each. spec git clone https://github.com/dualform-labs/spec-skill.git cp -r spec-skill/skills/spec ~/.claude/skills/ review-audit git clone https://github.com/dualform-labs/review-audit.git cp -r review-audit/skills/review-audit ~/.claude/skills/ Then in Claude Code: /spec a menu-bar app that warns me when my Mac is thermally throttled , or /review-audit on a change before you call it done. Output language is auto / ja / en . No network calls Claude Code only , no telemetry, no bypass-permissions. These are prompt-file skills, not magic. Single-pass detection in review-audit is model-dependent; if you need per-run proof of detection power or fresh-context adversarial verification, that's the heavier review-audit-pro tier coming soon . And spec won't make a bad idea good — it just makes the decisions explicit before code is written, where they're cheap to change. If you try them, I'd genuinely like to hear where they break or annoy you. — a dualform project