Skip to content
Skills Library
Marketing & content · Review & audit

critic

/critic

This skill should be used when the user asks to "summon a critic", "review like Karpyshyn", "get a Zahn perspective", "review like James Wood", "Stover review", "what would Lucas think", "Traviss read this", "in-universe beta read", or invokes `/holocron:critic`. Spawns a persona reviewer agent on a chapter or full manuscript.

Repository
holocron ↗
Licence
MIT
Last repository change
12.05.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 12.05.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

This skill should be used when the user asks to "summon a critic", "review like Karpyshyn", "get a Zahn perspective", "review like James Wood", "Stover review", "what would Lucas think", "Traviss read this", "in-universe beta read", or invokes `/holocron:critic`. Spawns a persona reviewer agent on a chapter or full manuscript.

Triggers from the description

summon a criticreview like Karpyshynget a Zahn perspectivereview like James WoodStover reviewwhat would Lucas thinkTraviss read thisin-universe beta read

Arguments

/critic <persona> [chapter|all|range]
Original author description

This skill should be used when the user asks to "summon a critic", "review like Karpyshyn", "get a Zahn perspective", "review like James Wood", "Stover review", "what would Lucas think", "Traviss read this", "in-universe beta read", or invokes `/holocron:critic`. Spawns a persona reviewer agent on a chapter or full manuscript.

How it works

  1. Available personas
  2. Usage
  3. How this dispatches
  4. When to use this vs. /holocron:review or /holocron:critique
  5. Failure modes
Original SKILL.md headings · 60 lines, 642 words
SKILL.md preview
---
name: critic
description: This skill should be used when the user asks to "summon a critic", "review like Karpyshyn", "get a Zahn perspective", "review like James Wood", "Stover review", "what would Lucas think", "Traviss read this", "in-universe beta read", or invokes `/holocron:critic`. Spawns a persona reviewer agent on a chapter or full manuscript.
argument-hint: "<persona> [chapter|all|range]"
---

Spawn a named persona reviewer on a chapter, range, or the full manuscript. Each persona is a *reviewer* with its own critical concerns and pet peeves; pick the one whose concern matches the question being asked of the manuscript.

> **Important.** These personas are reviewers, not voice models. They tell you whether your prose holds up against their concern — not how to write. Your own voice lives in `craft/voice.md`; the critics review *that voice*, they don't replace it.

## Available personas

| Persona | Critical concern | Best for |
|---------|------------------|----------|
| `karpyshyn` | Moral-grey character psychology; efficient prose | Old Republic psychology; Sith / fallen-Jedi arcs; redemption that has to be earned |
| `zahn` | Tactical realism, lore discipline, plausibility | Military scenes; fleet engagements; invented systems; Force-mechanic discipline |
| `traviss` | Mandalorian cultural authenticity, dialect | Mandalorian culture; Mando'a register; military fiction texture |
| `stover` | Prose-level intensity, philosophical violence | Lightsaber duels; Sith philosophy; prose that needs to *cut* |
| `lucas` | Mythic structure, archetypal clarity | "Is this Star Wars enough?" — operatic shape, archetypal clarity, rhymes |
| `james-wood` | Sentence-craft, free-indirect style | Genre-neutral sentence craft; consciousness; free-indirect style |
| `in-universe-beta-reader` | Old Republic tone / feel | "Does this *sound* KOTOR?" — softer bar than strict canon |

## Usage

```
/holocron:critic karpyshyn 5                 # Karpyshyn on chapter 5
/holocron:critic zahn all                    # Zahn on full manuscript
/holocron:critic stover chapters/08.md       # Stover on a specific file
/holocron:critic lucas 3-7                   # Lucas on a chapter range
/holocron:critic james-wood                  # Most recently written chapter
```

If two personas are named (`karpyshyn and zahn`, or `karpyshyn,zahn`), spawn both in parallel and present their reviews side-by-side.

## How this dispatches

1. Validate the persona name against the table above. If unknown, suggest the closest match (`zhan` → `zahn`, `wood` → `james-wood`) and ask the user to confirm.
2. Resolve scope:
   - No scope → most recently modified chapter under `chapters/`.
   - Number → `chapters/0X-*.md`.
   - Range (`3-7`) → expand to individual chapter files.
   - `all` → all files under `chapters/`.
   - Path → use directly.
3. Gather minimal context the persona needs to anchor:
   - The chapter file(s) (the persona reads them itself via Read).
   - `architecture.md` if reviewing the full manuscript.
   - Era and any lore-overlay relevant to the scope.
4. Spawn the persona agent via the Task tool with `subagent_type: "holocron:<persona>"`. Prompt should include the scope and one sentence on what the user wants from this pass (e.g. *"Karpyshyn read of chapter 5; the user is worried the protagonist's turn isn't earned."*).
5. If multiple personas requested, spawn all Task calls in a single message so they run concurrently.
6. Return each persona's review verbatim, then offer: "Want me to convert any of this into actionable edits?"

## When to use this vs. `/holocron:review` or `/holocron:critique`

- **`/holocron:review`** — iterative chapter feedback during drafting. Generic chapter-reviewer agent. Use it most.
- **`/holocron:critique`** — full literary review of a completed manuscript. NYT/New Yorker register. Use it once near the end.
- **`/holocron:critic <persona>`** — *targeted*, *opinionated* read against a specific concern. Use it when the manuscript needs a stress test from one direction (military realism, Mandalorian voice, mythic shape, etc.).

A typical late-draft sequence: `/holocron:critique` for the broad pass, then 2–3 personas via `/holocron:critic` for the specific concerns the critique surfaced.

## Failure modes

- **Wrong persona for the scope.** James Wood reviewing a fleet battle will produce thin notes; Zahn reviewing free-indirect interiority likewise. If the persona-vs-scope match looks weak, surface that to the user before spawning.
- **Empty manuscript.** If the resolved scope contains zero files, stop and ask the user for a path.
- **Persona disagreement.** Multiple personas often disagree (this is a feature). Don't try to reconcile — present them as distinct voices and let the author choose.

Versions

RepositoryScoreLicence
This page · petitchu/holocron100MIT
mcouthon/agents100MIT
Soe-Reh/soes-skills100MIT
teenxgrailed/needt-plugin90MIT

Database snapshot: 13.11.2026 · package version 226596562601 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100write
    This skill should be used when the user asks to "write chapter X", "write the next chapter", "write prose", "continue the story", "continue from where we left off", "draft the next scene", "write a scene where...", or invokes `/holocron:write`. Spawns the writer agent to produce…
  • 100review
    This skill should be used when the user asks to "review my chapter", "review chapter X", "review all chapters", "check this chapter for consistency issues", "this scene isn't working — help me fix it", "give me feedback on what I just wrote", "is chapter 8 ready to move on", or…
  • 95critic-loop
    Use when the user asks to revise, polish, critique, or finalize an existing academic manuscript, chapter, thesis, or paper — runs parallel critic subagents until no MAJOR issue remains. Trigger phrases "/critic-loop", "run critic-loop", "revise this manuscript", "polish this…
  • 100reader-panel
    This skill should be used when the user asks for a "simulated beta read", "reader panel", "persona read", "first read before my beta readers", "how would a genre reader react", "would a reader keep going", "pre-beta read", "mock beta readers", or wants structured persona reads…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.