From 5213442459c166b5f7980c8a8aa649913f68f0e5 Mon Sep 17 00:00:00 2001 From: cj Date: Mon, 17 Aug 2026 17:01:02 +0000 Subject: [PATCH] claude-api skill: keep prompt-audit non-interactive when provider markers are present The Before You Start check stops and asks when it sees non-Anthropic provider markers, but the prompt-audit subcommand is non-interactive. State in the prompt-audit row that such markers are recorded as an assumption rather than stopping the audit, and that the audit never proposes moving those files to the Anthropic SDK. No-Verification-Needed: markdown-only skill content, no runtime surface --- skills/claude-api/SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/skills/claude-api/SKILL.md b/skills/claude-api/SKILL.md index dfd4e73bf..73131f803 100644 --- a/skills/claude-api/SKILL.md +++ b/skills/claude-api/SKILL.md @@ -56,7 +56,7 @@ If the User Request at the bottom of this prompt is a bare subcommand string (no | Subcommand | Action | |---|---| | `migrate` | Migrate existing Claude API code to a newer model. **Read `shared/model-migration.md` immediately** and follow it in order: Step 0 (confirm scope — ask which files/directories before any edit), Step 1 (classify each file), then the per-target breaking-changes section. Do not summarize the guide — execute it. If the user did not name a target model, ask which model to migrate to in the same turn as the scope question. After the per-target changes are applied, audit the in-scope prompt text, tool descriptions, and request code against `shared/prompt-audit.md` — prompting written for the source model is part of every migration, and it does not announce itself. | -| `prompt-audit` | Audit existing prompts, skills, and tool descriptions for dated patterns ("cruft") written for older models. **Read `shared/prompt-audit.md` immediately** and follow it in order: Step 0 (establish scope and target model from the request and the repository — state the assumptions in the report, do not stop to ask), inventory, provenance, then the pattern scan. Produce both deliverables in full — the audit report (findings with `file:line`, pattern, why it's obsolete for the target model, confidence) and a proposed diff — without pausing for confirmation; apply edits only if the request explicitly asked for them. Do not summarize the guide — execute it. | +| `prompt-audit` | Audit existing prompts, skills, and tool descriptions for dated patterns ("cruft") written for older models. **Read `shared/prompt-audit.md` immediately** and follow it in order: Step 0 (establish scope and target model from the request and the repository — state the assumptions in the report, do not stop to ask; non-Anthropic provider markers from Before You Start are recorded as an assumption rather than stopping the audit, and the audit never proposes moving those files to the Anthropic SDK), inventory, provenance, then the pattern scan. Produce both deliverables in full — the audit report (findings with `file:line`, pattern, why it's obsolete for the target model, confidence) and a proposed diff — without pausing for confirmation; apply edits only if the request explicitly asked for them. Do not summarize the guide — execute it. | ---