Conciseness

Lean and dense throughout: command tables, one-line requirements ("It needs Node.js 22+ and FFmpeg"), targeted pitfalls ("never `pgrep -f`, which matches its own loop"), and deprecated aliases quarantined in a single note. Assumes Claude's competence with no concept explanations; every token earns its place.

Actionability

Fully executable, copy-paste-ready commands everywhere: `npx hyperframes check --json`, `render --quality looks --output out.mp4`, `timeline apply plan.json --json`, and a concrete wait loop `until grep -qE 'Render (complete|failed)' render.log; do sleep 5; done`. Specific examples cover the common cases, including failure recovery commands.

Workflow Clarity

"The loop" is a clearly sequenced 5-step process with explicit validation checkpoints: lint after structural changes, `check --json` as the gate, reading snapshot PNGs, confirming the preview URL answers 200, and verifying the render is non-empty with `ffprobe` duration matching `data-duration`. Error recovery is strong: a symptom→fix table, `--plan` previews, edit receipts, and `timeline undo`/`history undo` feedback loops.

Progressive Disclosure

Good structure: the body is a concise overview and the "Read the row before running its command" table maps commands to all 12 real, one-level-deep `references/*.md` files, all of which exist. Not 5 because three referenced paths (`../hyperframes/references/plugin-installation.md`, `format.md`, `motion.md`) point outside this bundle and do not resolve in the actual file structure, leaving minor navigation gaps.

Specificity

Lists multiple concrete actions — "scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history" plus "reading its JSON and recovering from build or render failures" — covering the full project lifecycle comprehensively. Not 4 because there are no meaningful coverage gaps; the actions span start-to-ship plus failure recovery.

Completeness

The "what" is explicit and concrete (scaffold, check, render, publish, history, failure recovery), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline. Not 4 because the "when" is entirely absent rather than merely implicit-but-present.

Trigger Term Quality

Contains natural terms a user of this tool would say ("scaffold", "edit the timeline", "render", "publish", "preview") with good coverage. Not 5 because it lacks synonyms and file extensions (e.g., video, animation, .mp4); not 3 because the keyword set is relevant and natural rather than missing common variations.

Distinctiveness Conflict Risk

"The HyperFrames CLI" names a specific product with a clear niche; its triggers (render, timeline, publish in the HyperFrames context) are distinct and unlikely to fire for unrelated skills. Not 4 because no overlap risk with closely related skills is identifiable.