Chalk Labs
Need help deploying slate-critics?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/oncorporation-slate-critics
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/slate-critics
What's inside
- Skill name
slate-critics- Description
- Use after Export as SLATE desk 12 Critics. Review the previous cut for dialogue, direction, continuity, scene, picture QA, or audio QA. First use presents a per-subagent tool menu. Triggers on critics desk, review the cut, Picture QA, Audio QA, hold the cut.
- License
- MIT
- Instructions
- 93 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: templates/critics/tools.md
Files (3)
- SKILL.md
- menus.md · references/
- tools.md · references/
SKILL.md (first lines)
# Critics desk (12)
Review desk. Not a Producer. Notes only.
Producers are desks 2–11. Critics never edit Fountain, `beats.md`, `shots.md`, boards, or `assets.md`.
Showrunner routes fail notes to the owning Producer. Human holds the previous cut. No land and no quality-band bump without the writer.
## When to run
After Export writes a cut. Skip Picture QA unless export type is `video`. Skip Audio QA unless type is `audio` or the video cut has a track.
## Cut record
Write under the output root:
```
critics/tools.md
critics/{cut-id}/manifest.md
critics/{cut-id}/dialogue.md
critics/{cut-id}/direction.md
critics/{cut-id}/continuity.md
critics/{cut-id}/scene.md
critics/{cut-id}/picture.md # video only
critics/{cut-id}/audio.md # audio, or video with a track
```
`{cut-id}` = `{export-type}-{band}-{date}` or the Export folder name. Point `bible.md` **Previous cut** at this id.
Manifest fields: export type, band, files reviewed, scouts run, tools used, open holds.
## First use — tool menu
Each scout is editable (`agents/critic-*.md` plus `critics/tools.md`).
On first use of a scout (that scout has no `tools:` line, or `tools: unset`):
1. Load `references/menus.md`.
2. Show **only that scout's** menu. Fit the job. Do not list Picture tools on Dialogue.
3. Wait. Do not review yet.
4. Write picks into `critics/tools.md`.
5. Next turn, run those tools.
If the writer edits `critics/tools.md` or a `agents/critic-*.md` charter, obey the file. Re-show a menu only when they say `reset critic tools` or a scout is still `unset`.
`llm-craft` is always on. Other tools are opt-in.
Copy `templates/critics/tools.md` to `critics/tools.md` if missing.
## Run order
1. Confirm previous cut path + export type + band.
2. Gate tools (menu if unset).
3. Spawn the matching scouts. Parallel notes allowed. One report file each.
4. Fold pass/fail into `manifest.md`.
5. Hold for the writer. Present the cut + scores + fails.
6. On writer accept — lock story at this band. On patch — list owning Producers. On bump — only if story scouts passed and the writer said so.
## Verdict
Each scout report: `pass` | `fail` | `hold`. Evidence first (tool output), then craft note. Cite Fountain lines, `sh_` ids, or timestamps.
Story scouts (Dialogue, Direction, Continuity, Scene) must pass before any video band above 10 or any audio tier bump.
## Quality bands (video)
- 0–25 simple animation / storyboard
- 26–50 illustrated
- 51–75 CGI
- 76–100 cinematic photoreal
Default ladder: band 10 → story lock + human accept → 65 or 90.
Text has no picture band. Audio uses production tier via Audio QA, not photoreal scores.
## Routing
| Scout fail | Route to |
|---|---|
| Dialogue | Dialogue Producer |
| Direction | Camera and/or Scene |
| Continuity | Casting, Architect, or Scene |
| Scene | Drama and/or Scene |
| Picture QA | Export only |
| Audio QA | Export only |
## Load
- `references/tools.md` — repos and what each tool measures
- `references/menus.md` — first-use menus
- matching `agents/critic-*.md`From Oncorporation/slate-agent, MIT.
More from Oncorporation/slate-agent
- 0.524score
slate-fountain
Oncorporation
Use when writing or validating Fountain screenplay syntax — title page, scene headings, action, character cues, dialogue, parentheticals, transitions.
SkillBFreshness: BClaude Code +9 - 0.524score
slate-scene
Oncorporation
Use when writing a screenplay scene in Fountain — headings, present-tense action, mini three-act, visual writing.
SkillBFreshness: BClaude Code +9 - 0.520score
slate-export
Oncorporation
Use as SLATE Producer desk 11 after Boards or pages.
SkillBFreshness: BClaude Code +9 - 0.520score
slate-interview
Oncorporation
Use when starting a new SLATE project or when bible.md is thin — interview the writer for premise, genre, format, length, tone, and whose story it is.
SkillBFreshness: BClaude Code +9 - 0.520score
slate-boards
Oncorporation
Use when storyboarding a shot.
SkillBFreshness: BClaude Code +9 - 0.519score
slate-premise
Oncorporation
Use when locking a logline, dramatic question, genre contract, or what-if for a screenplay.
SkillBFreshness: BClaude Code +9 - 0.519score
slate-assets
Oncorporation
Use when inventorying production assets — characters as identities, locations, narrative props.
SkillBFreshness: BClaude Code +9 - 0.519score
slate-dialogue
Oncorporation
Use when rewriting or polishing screenplay dialogue for subtext, distinct voices, and a read-aloud test.
SkillBFreshness: BClaude Code +9 - 0.519score
slate-drama
Oncorporation
Use when raising stakes, naming a scene's value shift, applying SCENE anatomy, or cutting scenes that do not change a fact or a relationship.
SkillBFreshness: BClaude Code +9 - 0.519score
slate-camera
Oncorporation
Use when planning coverage and shot lists — size, angle, lens, movement, blocking, duration, sound, start/end state.
SkillBFreshness: BClaude Code +9 - 0.515score
slate-character
Oncorporation
Use when designing cast — want vs need, ghost/lie/flaw, look, voice, and arc.
SkillBFreshness: BClaude Code +9 - 0.515score
slate-structure
Oncorporation
Use when planning acts, Save the Cat beats, page maps, pacing, or sequence design for a screenplay.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 13, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Oncorporation/slate-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Oncorporation
- 0.632score
FileSystem MCP Server
Oncorporation
Secure filesystem access for AI agents with configurable directory and file type restrictions
ConnectorAFreshness: ALocal★ 5↓ 76/wkClaude Code +5 - 0.524score
slate-scene
Oncorporation
Use when writing a screenplay scene in Fountain — headings, present-tense action, mini three-act, visual writing.
SkillBFreshness: BClaude Code +9 - 0.524score
slate-fountain
Oncorporation
Use when writing or validating Fountain screenplay syntax — title page, scene headings, action, character cues, dialogue, parentheticals, transitions.
SkillBFreshness: BClaude Code +9 - 0.520score
slate-boards
Oncorporation
Use when storyboarding a shot.
SkillBFreshness: BClaude Code +9 - 0.520score
slate-export
Oncorporation
Use as SLATE Producer desk 11 after Boards or pages.
SkillBFreshness: BClaude Code +9 - 0.520score
slate-interview
Oncorporation
Use when starting a new SLATE project or when bible.md is thin — interview the writer for premise, genre, format, length, tone, and whose story it is.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get slate-critics running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
slate-critics skill. Agent Mart. https://agentmart.dev/skills/oncorporation-slate-critics (last updated 2026-10-24)