voiceover

write the voice-over, demo script first, voiceover instead of PRD, voiceover-first development, align on the demo, script the demo, ship a feature demo-first. The whole demo-driven journey — approve the narration BEFORE any code, then build on a fresh worktree until the demo holds and open the PR with the proof on it. Use when a feature request arrives, or when the user runs /voiceover.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, action-oriented skill body with a clear sequenced workflow, an explicit approval gate, and a repair-until-holds feedback loop. Minor gains are available in conciseness and in making the sister-skill pointers more navigable.

Suggestions

Trim justifying clauses that restate why a step is safe (e.g. 'so the user's checkout stays untouched') to lift conciseness toward 5.

Convert the 'Source of truth' sister-skill names into explicit links or call-out blocks so the one-level-deep references are as navigable as file links.

Inline a one-line summary of each delegated sister skill's entry command so the body is more self-contained without losing the delegation pattern.

Dimension	Reasoning	Score
Conciseness	Lean body with no padding of concepts Claude already knows; each phase is a tight numbered step. A few justifying clauses (e.g. 'set up an isolated workspace so the user's checkout stays untouched') could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Provides concrete executable commands (git worktree add, gh pr create --base dev --fill, pnpm fraimz:publish) and specific file/import targets, but several steps delegate to sister skills by name rather than being fully self-contained copy-paste guidance.	4 / 5
Workflow Clarity	Four explicit phases with numbered steps 1-6, an explicit approval gate ('no code until the script is approved'), and a clear validate-fix-retry feedback loop in Phase 3 ('load diagnose-a-red-run when the spec fails, and repair until every approved claim has an observable assertion').	5 / 5
Progressive Disclosure	Well organized into phased sections with a 'Source of truth' pointer list to sister skills (write-a-spec, run-tests, diagnose-a-red-run, publish-evidence); no bundle files exist, and the in-body references are one level deep and clearly signaled, though they are bare skill names rather than linked file references.	4 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, distinctive description that concretely covers the whole demo-driven lifecycle and gives explicit 'Use when' triggers. The only demerit is voice: imperative fragments instead of strict third person, which caps specificity at 4.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions across the lifecycle ('approve the narration BEFORE any code', 'build on a fresh worktree until the demo holds', 'open the PR with the proof on it'), approaching comprehensive coverage; reduced from 5 to 4 because the description uses imperative/second-person-voiced fragments rather than strict third person.	4 / 5
Completeness	Explicitly answers both 'what' ('The whole demo-driven journey — approve the narration BEFORE any code, then build on a fresh worktree... open the PR with the proof on it') and 'when' ('Use when a feature request arrives, or when the user runs /voiceover') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-keyword coverage with several user-sayable phrasings ('demo script first', 'align on the demo', 'ship a feature demo-first', 'feature request', '/voiceover'), but a few synonyms or variant triggers are missing so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (demo-first / voiceover-as-spec) with distinctive triggers unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: different-ai/openwork
Path: .opencode/skills/voiceover/SKILL.md
Commit: 7b76a2b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.