Render Blocking
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Eliminate render-blocking resources.
Compare a rendered narrative image against the beat's intent (title + body + prior canon).
MITAuto-check passed
Install Narrative Scene QA
$ npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install UfukNode/Noustiny narrative-scene-qa --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/UfukNode/Noustiny.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hermes-additions/skills/creative/narrative-scene-qa .claude/skills/narrative-scene-qa && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "narrative-scene-qa" agent skill from https://github.com/UfukNode/Noustiny/tree/main/hermes-additions/skills/creative/narrative-scene-qa into .claude/skills/narrative-scene-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrative-scene-qa", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/UfukNode/Noustiny/tree/main/hermes-additions/skills/creative/narrative-scene-qaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install UfukNode/Noustiny narrative-scene-qa --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/UfukNode/Noustiny.git skills-src && mkdir -p .agents/skills && cp -r skills-src/hermes-additions/skills/creative/narrative-scene-qa .agents/skills/narrative-scene-qa && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "narrative-scene-qa" agent skill from https://github.com/UfukNode/Noustiny/tree/main/hermes-additions/skills/creative/narrative-scene-qa into .agents/skills/narrative-scene-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrative-scene-qa", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install UfukNode/Noustiny narrative-scene-qa --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/UfukNode/Noustiny.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/hermes-additions/skills/creative/narrative-scene-qa .cursor/skills/narrative-scene-qa && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "narrative-scene-qa" agent skill from https://github.com/UfukNode/Noustiny/tree/main/hermes-additions/skills/creative/narrative-scene-qa into .cursor/skills/narrative-scene-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrative-scene-qa", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/UfukNode/Noustiny.git --path hermes-additions/skills/creative/narrative-scene-qa--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install UfukNode/Noustiny narrative-scene-qa --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/UfukNode/Noustiny.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/hermes-additions/skills/creative/narrative-scene-qa .gemini/skills/narrative-scene-qa && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "narrative-scene-qa" agent skill from https://github.com/UfukNode/Noustiny/tree/main/hermes-additions/skills/creative/narrative-scene-qa into .gemini/skills/narrative-scene-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrative-scene-qa", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install UfukNode/Noustiny narrative-scene-qaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/UfukNode/Noustiny.git skills-src && mkdir -p .github/skills && cp -r skills-src/hermes-additions/skills/creative/narrative-scene-qa .github/skills/narrative-scene-qa && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "narrative-scene-qa" agent skill from https://github.com/UfukNode/Noustiny/tree/main/hermes-additions/skills/creative/narrative-scene-qa into .github/skills/narrative-scene-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrative-scene-qa", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install UfukNode/Noustiny narrative-scene-qa --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/UfukNode/Noustiny.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/hermes-additions/skills/creative/narrative-scene-qa .opencode/skills/narrative-scene-qa && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "narrative-scene-qa" agent skill from https://github.com/UfukNode/Noustiny/tree/main/hermes-additions/skills/creative/narrative-scene-qa into .opencode/skills/narrative-scene-qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "narrative-scene-qa", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
narrative-scene-qa- GitHub stars
- 181
- Token cost
- ~1.6k tokens
- SKILL.md length
- 687 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- MIT
At a glance
Compare a rendered narrative image against the beat's intent (title + body + prior canon).
- SKILL.md covers Input, What to flag (verdict:…, What NOT to flag (approved:… and Output contract, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Narrative Scene QA is an agent skill from UfukNode/Noustiny. Compare a rendered narrative image against the beat's intent (title + body + prior canon). Flag faithfulness failures so the image pipeline can re-render with correction. Returns strict JSON {approved, score, issues, fixhint}. No prose, no tool calls.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: An agent native video creation pipeline that runs on top of Hermes Agent. The licence is MIT.
Example prompts
- “/narrative-scene-qa”
What it can do on your machine
Read from SKILL.md and the folder at commit 09a0c82. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Narrative Scene QA loads about 1.6k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 687 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from UfukNode/Noustiny at commit 09a0c82, republished under its MIT licence (© UfukNode). 687 words, ~1,623 tokens.
Download SKILL.mdSave it as
.claude/skills/narrative-scene-qa/SKILL.md (or your agent's skills folder).- name
- narrative-scene-qa
- description
- Compare a rendered narrative image against the beat's intent (title + body + prior canon). Flag faithfulness failures so the image pipeline can re-render with correction. Returns strict JSON {approved, score, issues, fix_hint}. No prose, no tool calls.
- version
- 1.0.0
- author
- Noustiny
- license
- MIT
Narrative Scene QA
Post-render verification pass. The image model sometimes renders a prompt literally in a way that breaks the narrative ("Katara harnesses Sokka to the sled" → image shows Sokka on all fours like a sled dog), contradicts prior canon state (previous beat showed broken ice, this image shows intact ice), or fumbles character identity. You are the check that catches those failures.
Input
A JSON object containing:
| Field | Type | Purpose |
|---|---|---|
imageUrl | string | Full URL to the rendered image (sent as a multimodal image_url message part — you actually see the pixels) |
nodeTitle | string | Beat label this image was supposed to depict |
nodeBody | string | Prose describing what should be happening in the image |
canonContext | array | Prior canon beats as {title, body, imagePrompt} so you know the state that must carry forward |
What to flag (verdict: approved: false, score < 0.6)
Catastrophic content failures only — stylistic judgment is not your job.
- Character posture mismatch — a named HUMAN character rendered in an animal/object pose (all fours, harnessed as a beast, hovering like a ghost when the body doesn't say so).
- Wrong character count — body names two people but the image shows one; image adds a third who wasn't named.
- Prior-state reset — prior canon visibly changed the world (broken ice, freed prisoner, destroyed object, lit fire) and this image silently reverts to the pristine state.
- Setting drift — body places the beat in location X but the image invents a different location (South Pole iceberg replaced by desert ruins, spaceship corridor turned into a forest).
- Object state wrong — a named object is in the wrong condition (full cup that the body says was emptied, intact sword that was broken two beats ago).
- Character identity drift — a named character has the wrong race / age / gender / signature clothing from the established registry.
What NOT to flag (approved: true)
- Minor stylistic choices (palette variations, framing, depth of field).
- Emotional intensity off by a notch (a "hopeful" scene that feels slightly tense is fine).
- Background decor variations — icicles patterned differently, different rock shapes.
- Exact clothing pattern differences when the overall silhouette and color are right.
Output contract
Return exactly one JSON object. First character {, last character }. No preamble, no markdown fence, no XML, no reasoning prose outside the object.
{
"approved": true,
"score": 0.87,
"issues": "",
"fix_hint": ""
}{
"approved": false,
"score": 0.22,
"issues": "Sokka is depicted on all fours, being harnessed as a sled-pulling animal. Named human characters must not be rendered in animal pose.",
"fix_hint": "Render two human characters standing upright side by side, each gripping a rope attached to the wooden sled, walking across the snow. Both figures are fully upright, on two legs. No animal-pose rendering."
}Rules for each field:
approved—trueiffscore >= 0.6AND no catastrophic failure from the flag list.score— float0.0..1.0. How well the image depicts the intent. 0.0 = hallucinated something unrelated, 1.0 = faithful render.issues— one sentence, ≤180 chars. Empty string when approved. State the visible problem plainly ("Sokka is on all fours being harnessed as a sled dog"), not the cause ("the prompt used 'harness Sokka'").fix_hint— actionable visual guidance for the image prompt builder, ≤240 chars. Empty string when approved. Specific: "render both characters standing upright and pulling the sled side by side". NOT vague: "make it better", "fix the composition", "make Sokka look right".
Show full SKILL.md (211 more words)Show less
Anti-patterns
- Do not emit
<tool_call>,<think>, or XML tags. - Do not call any tool.
- Do not wrap output in a ```json code fence.
- Do not explain your reasoning in prose before or after the JSON.
- Do not flag stylistic choices — aesthetics are subjective and not your job.
- Do not approve an image just because it looks pretty — if the narrative intent is wrong, say so.
- Do not return
scoreas a string. - Do not mix languages — English only in
issuesandfix_hint.
Examples
Example 1 — catastrophic literal-render (flagged)
Input body: "Katara harnesses Sokka to the sled. They begin to follow Aang's faint trail." Image shows: Sokka on all fours being strapped into the sled's harness like a sled dog; Katara standing behind holding the reins.
{
"approved": false,
"score": 0.18,
"issues": "Sokka is rendered on all fours in a sled-dog harness position. Named human characters must be in standing human posture unless the body explicitly says otherwise.",
"fix_hint": "Render Sokka and Katara both standing upright, side by side, each holding a rope or handle attached to the sled as they pull it together across the snow. Neither character on all fours."
}Example 2 — state reset (flagged)
Prior canon: "Katara shatters the ice around Aang, pulling him free." This body: "Aang catches his breath in the cold air." Image shows: Aang still encased inside an intact iceberg; Katara outside looking in.
{
"approved": false,
"score": 0.25,
"issues": "The ice around Aang is shown intact, but prior canon established the ice was shattered. The image silently reverts the world state.",
"fix_hint": "Render Aang standing outdoors amid broken ice shards on the cavern floor, breathing in the cold air. The iceberg around him must be visibly shattered, not sealed."
}Example 3 — faithful render (approved)
Body: "Aang stands amid broken ice, looking back at Katara and Sokka." Image shows: Aang in the foreground on cracked ice, head turned toward two figures in blue parkas behind him.
{
"approved": true,
"score": 0.88,
"issues": "",
"fix_hint": ""
}Those are the target patterns. Faithful or plain-wrong — no middle-ground guessing.
© UfukNode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in hermes-additions/skills/creative/narrative-scene-qa of UfukNode/Noustiny.
Open the folder on GitHubat commit 09a0c82
Compare with similar skills
Narrative Scene QA next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Narrative Scene QA this skillUfukNode/Noustiny | 181 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Render Blockingthedaviddias/Front-End-Checklist | 74k | — | ~430 | Automated safety check: Pass | MIT | |
| Intent Requirements IntakeYeachan-Heo/oh-my-claudecode | 40k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Team NarrativeDonchitos/Claude-Code-Game-Studios | 26k | — | ~4.5k | Automated safety check: Pass | MIT | |
| RenderLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.8k | Automated safety check: Pass | MIT | |
| Compare Renderhbmartin/graphviz2drawio | 275 | — | ~1.2k | Automated safety check: Pass | GPL-3.0 |
Similar skills
Intent Requirements Intake
Yeachan-Heo/oh-my-claudecode
Turns a pasted chat log or spoken problem report from support or ops staff into a reviewed five-section intent.md through numbered batches of questions.
Team Narrative
Donchitos/Claude-Code-Game-Studios
Orchestrate the narrative team — narrative-director, writer, world-builder, level-designer — for story, world lore, narrative-driven levels.
Render
LeoYeAI/openclaw-master-skills
Deploy and operate apps on Render (Blueprint + one-click Dashboard deeplink, same flow as Codex render-deploy).
Compare Render
hbmartin/graphviz2drawio
Visually verify graphviz2drawio conversion fidelity by rendering a graphviz source side-by-side as a native graphviz PNG and a converted draw.io PNG, then reading both images to compare.
Browser Intent
ruvnet/ruflo
Execute a natural-language browser intent via page-agent (browseract) when the target is easier to describe than to select — degrades gracefully when page-agent or an OpenAI-compatible LLM provider…
More from UfukNode/Noustiny
All 13 skills in this repoNarrative Continuity Critic
UfukNode/Noustiny
Grades whether a downstream story beat still holds after an upstream insertion, returning a strict JSON verdict of still_valid, needs_rewrite or must_delete.
Narrative Writer
UfukNode/Noustiny
Turns an ordered list of canon story beats into one continuous piece of present-tense prose with tonal continuity and motif carry-through, never JSON or tool calls.
Narrative Beat Writer-Assist
UfukNode/Noustiny
Expands a one-line author intent into a full story beat that fits between two known nodes of a canon path, returned as strict JSON.
Story Scene Composer
UfukNode/Noustiny
Groups every node of an existing branching story tree into scenes, titles each scene, assigns an act and a one-word motif, and returns the result as JSON.
Story Copyright Detector
UfukNode/Noustiny
Classifies a story seed as known, inspired or original IP and returns strict JSON naming the franchise and the image model to use.
Noustiny Storybook Intro Director
UfukNode/Noustiny
Chooses the pace, color palette, transition and length of the opening montage for a Noustiny audiobook storybook when the user leaves those settings open.
Questions about Narrative Scene QA
What does Narrative Scene QA do?
Compare a rendered narrative image against the beat's intent (title + body + prior canon). Narrative Scene QA is an agent skill from UfukNode/Noustiny. Compare a rendered narrative image against the beat's intent (title + body + prior canon).
How do I install Narrative Scene QA in Claude Code?
Run `npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a claude-code`. Or copy the skill folder (hermes-additions/skills/creative/narrative-scene-qa in UfukNode/Noustiny) into .claude/skills/narrative-scene-qa in your project. Claude Code loads it when a task matches its description.
How do I install Narrative Scene QA in Codex?
Run `npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a codex`. Or copy the skill folder (hermes-additions/skills/creative/narrative-scene-qa in UfukNode/Noustiny) into .agents/skills/narrative-scene-qa in your project. Codex loads it when a task matches its description.
Can I use Narrative Scene QA in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add UfukNode/Noustiny --skill narrative-scene-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/narrative-scene-qa, .gemini/skills/narrative-scene-qa, .github/skills/narrative-scene-qa and .opencode/skills/narrative-scene-qa in your project.
What does Narrative Scene QA need to run?
SKILL.md names no scripts, command-line tools or credentials: Narrative Scene QA is instructions for the agent only.
Does Narrative Scene QA access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Narrative Scene QA safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Narrative Scene QA use?
Narrative Scene QA is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Narrative Scene QA use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Narrative Scene QA?
Skills that share tags, products or a category with Narrative Scene QA: Render Blocking (thedaviddias/Front-End-Checklist, 74k stars), Intent Requirements Intake (Yeachan-Heo/oh-my-claudecode, 40k stars), Team Narrative (Donchitos/Claude-Code-Game-Studios, 26k stars) and Render (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Narrative Scene QA?
UfukNode (a GitHub user) maintains it in UfukNode/Noustiny, which has 181 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on May 4, 2026.
Source: UfukNode/Noustiny on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.