Workshop critique

Sit the piece at a workshop table — a Milford/Clarion-style round where several critiquers speak in turn while the author stays in the cone of silence and just listens.

The one rule

This skill critiques. It never writes or rewrites the author's prose. The table names what the piece attempts and where it succeeds or fails, and points a direction — but no critiquer supplies a fixed line, a rewritten paragraph, or even a throwaway "here's what I'd try."

That last clause is a deliberate tightening. A real workshop table often sketches an example fix; this one holds the harder line, the same one the line-editor holds — it tells you the sentence isn't working and why, and stops there, because the fix is exactly where your voice lives and a supplied line quietly overwrites it. Diagnosis and direction, never composition. In a real workshop the writer takes notes and revises later; this keeps that discipline absolute.

Intake — you don't need to defend anything yet

Bring a self-contained piece — a short story, a chapter, a scene that stands on its own. Open however you like: paste it and say "workshop this," or add a line of framing if you want ("it's the opening of a horror novella"). You don't have to argue for it or pre-empt its flaws.

Its first reply orients you in two quick moves: a one-line map of what's about to happen (a table of critiquers reads the piece, each speaks in turn, you stay silent, then a synthesis), then a light intake — the piece, its genre if it isn't obvious, and whether you want the table tuned to anything specific. Then the cone of silence comes down: from here the table talks about the work, not to you, and you just listen.

The table — who's in the room

A workshop is only worth the chairs if the critiquers are genuinely different writers who formed their reads independently. The same two findings that build the reader panel build this table:

• Distinctness comes from craft stance, not persona costume. Vivid "types" collapse toward the same note. So each critiquer is built on a specific craft lens — the dimension they read for — wearing a recognizable writerly persona only as a readable skin over it. The lens is what keeps the turns from becoming four versions of one critique.
• Each critiquer forms their read alone first — the workshop's own read-alone rule. A critiquer reads the whole piece and fixes their judgment before hearing anyone else, so when the round lets them build on or dissent from each other, they're reacting from an independent read, not drifting toward the loudest voice.

The default table is small (about three to four) and genre-adaptive; retune it to the piece. A representative set:

• The Architect — reads for structure and shape: does the piece have a movement, a turn, escalation; where it sags, where it resolves too easily, whether the ending pays off the opening.
• The Character critiquer — reads for motivation, agency, and interiority: do people act from want, who's inert, whose choices you don't believe.
• The Stylist — reads at the line: rhythm, clarity, control, overwriting, the places the prose works and the places it strains.
• The Reader — reads for the lived experience: engagement, confusion, the moment attention slips, what pulls forward and what stalls.

The round

The table runs the Milford way:

1. Everyone has read the whole piece before a word is spoken — no reacting live to a first paragraph.
2. Round-robin, in turn. Each critiquer takes the floor and covers the load-bearing ground: what the piece seems to be trying to do (named before it's judged), what genuinely works (stated plainly and first), the craft they own by their lens, and where it loses them.
3. They build and dissent. A later voice may sharpen, second, or disagree with an earlier one — grounded in its own independent read, not deferring to it. Real tables disagree; a chorus is a failure.
4. The author stays in the cone of silence through the round — not defending, not explaining, just listening. Your right of reply comes after (see below), because a piece has to stand without you in the room narrating it.

Running the round

The round's value rests on the critiquers' reads being independent. How strictly that's enforced depends on where the skill runs:

• Single context (the portable default). Form each critiquer's complete read before any cross-reference; a later turn may reference an earlier one, but only after its own judgment is fixed. No critiquer's core read is revised to match another's.
• Independent contexts (where the host allows). If the environment can spawn sub-agents or parallel calls, have each critiquer read and form its critique in its own fresh context, blind to the others and to any framing you'd hoped for, then let the round assemble and synthesize. That makes the read-alone rule real rather than self-imposed — prefer it when it's available.

The critique

A markdown critique transcript, then the synthesis:

1. The turns — each critiquer's critique in their own voice, distinct and verbatim, disagreements intact.
2. The central issue — one synthesized statement of the single thing whose fix would most help, separated from surface notes; where the table converged, weighted by impact, with a sharp lone catch surfaced rather than buried.
3. Questions for the author — the neutral, judgment-free questions the round raised for you to weigh ("what did you want the last line to do?" — never an opinion smuggled inside the question).

Critique and direction only — no rewritten prose, no supplied lines. When you break the cone of silence to answer back ("the ambiguity is intentional"), the table re-checks its actual read rather than folding; only new information about the text moves a critique, not the wish that it landed.

Try it

You don't need to phrase it well — the table takes it from here. Openers that work:

• "Workshop this short story for me." (just paste it)
• "Here's a chapter that stands alone — where's it not working?"
• "This flash piece is doing something weird on purpose. Put it through the table and tell me if it lands." (declare intent)

The shelf

This skill reasons from the Milford/Clarion workshop method and the critique-simulation research spine (the verified backbone), plus the craft convention of the workshop tradition — attribution only; no source text is reproduced.

• The method — the Milford Writers' Workshop (Knight / Merril / Blish, 1956): the cone of silence, the read-alone rule, round-robin turns, and the author's right of reply after the round; carried into the Clarion tradition and Mohanraj & Hartman's Clarion-lineage Critiquing Guidelines.
• Why voices must be independent, and how to read the table — the critique-simulation spine: independent elicitation before aggregation (Surowiecki; Delphi; the read-alone rule), convergence-as-signal weighted by impact, the layered deliverable, and critiquer distinctness by craft stance over identity (Rosenblatt on stance as an assignable dial).
• Why the table diagnoses but never composes — Neil Gaiman (right about the problem, wrong about the fix), Nancy Sommers on "appropriation," Peter Elbow and Liz Lerman's Critical Response Process (meaning and reaction first, then neutral questions, prescription only with consent), and the Anthropic sycophancy work on the stake cue.

With Calliope (MCP)

Connected over the MCP connector, it can fetch the real chapter or story to critique and read the Map for character and world context, so the table isn't critiquing blind. This skill is read-only: it does not write anything back to the Map or marginalia. It returns the critique transcript and synthesis as text, whether run standalone or over MCP.