fix: viewer text downloads as base64; Artifact download note; where claude is; release 0.16.2

CHANGELOG.md

@@ -2,6 +2,24 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.16.2] - 2026-10-03
+
+### Fixed
+- **The eval viewer's Download button failed for text outputs on claude.ai.** Opened from a
+  delivered file on the web and in Claude Desktop, it raised an `atob` error and saved nothing, while
+  binary outputs downloaded after the app's trust prompt. Text downloads now use a base64 `data:` URI
+  like the others (not yet re-tested in the app).
+- **What the viewer's downloads do in the Claude app.** `environments.md` now says the Download links
+  don't work when the viewer is published as an Artifact (the app blocks file downloads there; the
+  outputs still show in the page), and that from a delivered viewer, binary downloads worked after a
+  confirmation.
+
+### Changed
+- **Where the `claude` CLI is.** Measured once each: found on PATH in cloud and local sessions (a
+  nested `claude -p` ran in a cloud session), and not on the chat runtime's PATH (Chat in the older
+  Chat/Cowork picker). The `claude-cli-dependency` message, `SKILL.md` and the README say so again,
+  now backed by a measurement; the advice to gate on `command -v claude` is unchanged.
+
 ## [0.16.1] - 2026-10-03
 
 ### Fixed

README.md

@@ -30,7 +30,7 @@ The skill that builds skills. Draft one and ship it in a single pass, or run eva
 Anthropic ships a `skill-creator` plugin. It's good, but several parts are broken or missing:
 
 - **Best practices guide included** — 620+ lines of patterns, structural templates, troubleshooting guide, and checklists extracted from Anthropic's [Complete Guide to Building Skills for Claude](https://resources.anthropic.com/hubfs/The-Complete-Guide-to-Building-Skill-for-Claude.pdf) and Thariq's [Lessons from Building Claude Code Skills](https://x.com/trq212/status/2024574133011673516). Includes a "Script vs. Instruct" decision framework for when to bundle pre-made scripts vs. keep logic as instructions — covering context window efficiency, reliability, and auditability. The built-in doesn't ship any of this.
-- **A skill that works here can break there, silently** — the `claude` CLI is on PATH in Claude Code and was found in a local session's shell, but other runtimes are unchecked, so gate a `claude -p` step on `command -v claude`; the Claude app's chat runtime has no sub-agent tool, so parallel eval runs have to collapse to serial there (a Claude app conversation running in a cloud session does have one — route by the tool list, not the product); an agent in a cloud or local session can't serve a local HTTP server and open it, so the eval viewer needs a static build; a third-party import there costs an install on every run, and egress is org-configurable, so a locked-down org can refuse it; and file delivery differs per surface — in a cloud session, writing a file is not delivering it. Structure validation can't see any of that, so there are two checks: `quick_validate` for structure, and a 14-rule portability linter for runtime assumptions — including the two ways compaction loses a skill. Both are stdlib-only, because they have to run inside the sandboxes they lint. Rule ids, flags and exit codes are in [`docs/DEVELOPMENT.md`](docs/DEVELOPMENT.md).
+- **A skill that works here can break there, silently** — the `claude` CLI is on PATH in Claude Code and was found in the Claude app's cloud and local sessions, but not in its chat runtime (Chat in the older Chat/Cowork picker), so gate a `claude -p` step on `command -v claude`; the Claude app's chat runtime has no sub-agent tool, so parallel eval runs have to collapse to serial there (a Claude app conversation running in a cloud session does have one — route by the tool list, not the product); an agent in a cloud or local session can't serve a local HTTP server and open it, so the eval viewer needs a static build; a third-party import there costs an install on every run, and egress is org-configurable, so a locked-down org can refuse it; and file delivery differs per surface — in a cloud session, writing a file is not delivering it. Structure validation can't see any of that, so there are two checks: `quick_validate` for structure, and a 14-rule portability linter for runtime assumptions — including the two ways compaction loses a skill. Both are stdlib-only, because they have to run inside the sandboxes they lint. Rule ids, flags and exit codes are in [`docs/DEVELOPMENT.md`](docs/DEVELOPMENT.md).
 - **Claude Code runtime docs** — the mechanics most skill authors hit the hard way, read out of the shipping binary rather than inherited from a blog post: overflow of the shared listing budget drops descriptions **per skill, least-recently-used first**, packing first-fit, so full and name-only entries coexist and a long description can lose to a shorter one; `allowed-tools` **grants** permission rather than requesting it; and compaction is a CHARACTER gate, not the documented token one, losing content two different ways — truncation keeps the first 19,900 characters and leaves a marker, while the combined cross-skill cap **zeroes** a skill outright with no marker and no entry. Verified against Claude Code 2.1.222–2.1.251; the listing budget re-verified at 2.1.280. Where the public docs and the binary disagree, [the reference](skill-creator-plus/skills/skill-creator-plus/references/official-guide-patterns.md) says so and shows which one shipped.
 
 The eval viewer, description optimizer and benchmarking fixes are in the table above; see the [CHANGELOG](CHANGELOG.md) for the full list.

VERSION

@@ -1 +1 @@
-0.16.1
+0.16.2