scene-construction

What the source does

• FilesystemDeclared1 observation
• NetworkDeclared2 observations
• ShellDeclared3 observations
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

raw = yaml.load(data.decode("utf-8"))

raw = yaml.load(data.decode("utf-8"))

raw = yaml.load(data.decode("utf-8"))

callback.append('https://127.0.0.1:' + str(self.server.server_port) + self.path)

flow.redirect_uri = f'http://127.0.0.1:{server.server_port}/'

.mars-plugin.json

expected = [{'source_href': '../../a.md', 'destination_url': url,

or source != b'Nested fixture. [Read parent](../../a.md).\n'):

output.write(b'Nested fixture. [Read parent](../../a.md).\n')

(path / 'g.md').write_bytes(b'Nested fixture. [Read parent](../../a.md).\n')

bindings = {'3': {'link_provenance': [{'source_href': '../../a.md',

session.callback.append('https://127.0.0.1/?code=synthetic&state=test-state')

session.callback.append('https://127.0.0.1/?code=synthetic&state=test-state')

picker.callback.append('https://127.0.0.1/?code=synthetic&state=test-state&picked_file_ids=granted-folder')

decode = lambda value: base64.b64decode(value, validate=True)

return Candidate(b64decode(result['data'], validate=True), result['source_hash'],

self.assertEqual(bytes.fromhex(record['attributes']['user.drive-sync-fixture']),

decode = lambda value: base64.b64decode(value, validate=True)

return Candidate(b64decode(result['data'], validate=True), result['source_hash'],

Audit 0.4.1 · source sha 915238ec14fe · 28 Oct 2026Report an issue or request a re-scan

• Publisherhaowjy GitHub userOwner of the repository this skill is read from
• Source folderhaowjy/creative-writing-skillsThe exact folder we audited
• LicenceApache-2.0As the repository states it
• Commit pinned for this verdict915238ec14feA new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Load to speak as a specified character from what they know, how they talk, and what they feel now: in-character conversation, voice discovery, or a relationship pressure test. Pass the character, the story moment, and…

---
name: character-sim
description: >
  Load to speak as a specified character from what they know, how they talk,
  and what they feel now: in-character conversation, voice discovery, or a
  relationship pressure test. Pass the character, the story moment, and their
  style and character-state files.
model-invocable: true
metadata:
  type: mode-shift
---

# Character Simulation

Become the specified character for conversation. The caller should pass the character, current story moment, relationship context, emotional pressure, and what the character knows or does not know.

If the caller gives only a sketch, work from the sketch and state the assumptions you are making before entering character.

## Method

Build the character from the available evidence. Style shows how they talk: speech patterns, vocabulary, rhythms. Character state shows who they are: what they have lived through, what they know, what they want, and what they are avoiding. Load both. If character state is missing, find it.

Speak in first person from the character's knowledge, not the full story's. When they would be confused, be confused. When they would deflect, deflect. When they would misunderstand, misunderstand.

Match how they actually talk. Age, class, education, stress, intimacy, anger, and fear change sentence shape. Under pressure, people stall, redirect, get defensive, shut down, over-explain, joke, or attack; they rarely name their inner state cleanly.

Let the conversation be messy. Real people meander, avoid hard topics, circle back, and react inconveniently. When there is no obvious answer, improvise from who the character is.

The conversation is the output. Do not summarize the character from outside unless the caller asks you to step out of character.

Excerpt, first 1,771 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-28
   ✕BLOCK D 62 / 100

   first audit · source 915238ec14fe

Questions about scene-construction

• github.com/haowjy/creative-writing-skills — the audited source at commit 915238ec14fe and every finding aboveObserved · 28 Oct 2026

Spotted something wrong? Report a correction · Methodology