CtrlK
BlogDocsLog inGet started
Tessl Logo

critique-theater

Five-role Design Jury review that streams scored rounds, persists a replayable transcript, and ships through the daemon's Critique Theater protocol.

57

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/atoms/critique-theater/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, concrete protocol spec with exact tags, roles, config keys, and endpoints, organized into clear sections with no unnecessary file references. It loses points on conciseness for historical padding and on workflow clarity for an implicit round-to-round recovery loop.

Suggestions

Trim pre-orchestrator/historical notes (e.g., "Those were the pre-orchestrator shape") or consolidate them into a single 'Deprecated patterns' line to recover conciseness.

Make the round-to-round recovery loop explicit: state that unresolved <MUST_FIX> items must be addressed by redrafting in the next round before re-scoring.

Add one short worked example of a complete round envelope so the tagged protocol shape is unambiguous.

DimensionReasoningScore

Conciseness

Mostly dense and assumes competence (no explaining of SSE/SQLite/NDJSON), but includes historical/disambiguation padding such as "Those were the pre-orchestrator shape" and the OD_MAX_DEVLOOP_ITERATIONS aside that could be tightened.

2 / 3

Actionability

Gives concrete, specific identifiers throughout — exact tags (<CRITIQUE_RUN>, <ROUND>, <PANELIST>, <ROUND_END>, <SHIP>), fixed role names, env vars (OD_CRITIQUE_*), SSE channels (critique.*), and the exact interrupt endpoint — which is actionable guidance for an instruction-only protocol skill.

3 / 3

Workflow Clarity

The sequence (envelope → rounds → ship) and the ship-gate (threshold AND no open must-fix) are explicit, but the recovery loop between rounds — how must-fix items drive the next redraft — is left implicit rather than spelled out as steps.

2 / 3

Progressive Disclosure

A single well-organized file under ~50 lines with clear sections (Runtime contract, Convergence and persistence, Interrupting a run) and no external references needed, matching the simple-skill allowance for a score of 3.

3 / 3

Total

10

/

12

Passed

Description

60%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific about capabilities but is written in product-internal jargon rather than natural user trigger terms and omits an explicit "Use when..." clause. It is distinguishable as a niche protocol but lacks the trigger phrasing that would make it clearly distinct in practice.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when the user asks for a scored design review or wants a panel to critique an artifact').

Replace or supplement internal jargon ('daemon's Critique Theater protocol', 'replayable transcript') with terms a user would actually say ('design review', 'panel critique', 'scoring rounds').

State the trigger condition in plain language so it is less likely to be confused with general review skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "streams scored rounds, persists a replayable transcript, and ships through the daemon's Critique Theater protocol" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Clearly states what the skill does, but provides no "Use when..." or equivalent trigger guidance, so the "when" is only implied — capping completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

Contains some relevant keywords ("Design Jury review", "scored rounds") but leans on internal jargon ("daemon's Critique Theater protocol", "replayable transcript") rather than natural user phrasings, missing common variations.

2 / 3

Distinctiveness Conflict Risk

Tied to a specific product protocol (Critique Theater) giving it a niche, but the generic "review" framing and jargon-heavy triggers mean it could still overlap with other review-oriented skills.

2 / 3

Total

9

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.