CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

stage-design

The baseline method for building ONE stage — a single classroom — with this runtime. Covers how the plan is settled in conversation, the order the generation tools are called in, how the classroom roster is written, when narration has to be re-synthesized, and what must be true before a stage is called done. Load this before generating or rebuilding any stage from scratch, whatever its subject; it is the floor the topic skills build on, not an alternative to them.

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

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

The content is an exemplary instruction-only skill: a tightly sequenced workflow with named tools, exact parameter formats, explicit failure-recovery policy, and real validation checkpoints before declaring done. Its only slack is minor rhetorical padding and the absence of any offloaded reference material, neither of which materially hurts usability.

DimensionReasoningScore

Conciseness

The body is dense with runtime-specific rules — tool names, argument formats, failure policies — and wastes no space explaining concepts Claude already knows. A few trimmable asides remain ("the same information a planned outline slot used to carry", "a roster settled late is a roster half the stage never saw"), so it sits at anchor 4 rather than the every-token-earns-its-place lean of anchor 5.

4 / 5

Actionability

Guidance is fully executable for an instruction-only skill: exact tools with exact arguments (`create_stage` with `folderId`, `providerId::voiceId` bindings, `materialFacts`, `design`), exact read paths (`path:/scenes/<order|id>/actions`, `detail:"source"`), and per-error-type responses for `prompt-unavailable` vs `invalid-model-output`. This is the instruction-skill equivalent of copy-paste-ready commands, matching anchor 5.

5 / 5

Workflow Clarity

A numbered 1–5 build sequence is backed by explicit validation checkpoints (`list_scenes` reconciliation, `generate_tts` reporting generated/skipped/failed, an actions sweep for blank text), a feedback loop for error recovery ("change the brief without changing the settled teaching intent, then retry once... If that retry fails, do not call generate_scene again"), and a completion checklist. This matches anchor 5's explicit-validation-with-recovery-loops profile.

5 / 5

Progressive Disclosure

As a single-file skill with no bundle directories, it is well-sectioned (build sequence, failure handling, narration, done criteria) with clearly signaled cross-skill pointers (`pro-editing`, the topic skills). The workflow is cohesive enough that nothing clearly belongs in a separate file, but at ~130 lines it exceeds the simple-skill case where sections alone would justify a 5, so anchor 4 fits.

4 / 5

Total

18

/

20

Passed

Description

87%Weight 40%Scale 1-5

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

A strong description: it states a concrete, lifecycle-spanning what, an explicit load-time trigger, and deliberate positioning against the topic skills. The only refinement left is naming the actual tools or adding a few more natural synonyms (course, lesson) to sharpen trigger matching.

DimensionReasoningScore

Specificity

The description enumerates several concrete coverage areas — "how the plan is settled in conversation, the order the generation tools are called in, how the classroom roster is written, when narration has to be re-synthesized, and what must be true before a stage is called done" — spanning the whole build lifecycle. It stops short of anchor 5 because the operations are described generically (e.g., "the generation tools") rather than named, leaving minor gaps in coverage detail.

4 / 5

Completeness

Both what and when are explicitly answered: the what is the full build-lifecycle coverage list, and the when is the concrete trigger "Load this before generating or rebuilding any stage from scratch, whatever its subject". This matches anchor 5's requirement for an explicit when-clause with concrete trigger phrasing; anchor 4's 'when could be more explicit' does not apply.

5 / 5

Trigger Term Quality

Natural domain terms are present — "building ONE stage", "a single classroom", "roster", "narration", "rebuilding any stage from scratch" — matching what a user of this runtime would say. A few natural variants (course, lesson, deck/pages) are missing, so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — baseline builder for one new stage — and explicitly disambiguates from siblings: "it is the floor the topic skills build on, not an alternative to them" and "rebuilding any stage from scratch" (excluding editing of existing stages). Minimal conflict risk, matching anchor 5.

5 / 5

Total

18

/

20

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.

Validation — 15 / 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

THU-MAIC/OpenMAIC

Path

skills/agent-runtime/stage-design/SKILL.md

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.