CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

canvas-manager

Manage a Canvas through its business tools only — initialize and query projects, create Elements and Content candidates, frame Elements, wait on generation, and process design markers. Use when the user asks to create, edit, or generate anything on a Canvas, such as images, videos, storyboards, video edits, or a final composed video, or when the message contains [@design_canvas_project:...] or [@design_marker:...]. Also use when the user says 'generate an image on my canvas', 'make a video from this canvas project', 'add a new element to my design', or 'edit the marked region of this image'. Layout strategies, Connections, video point estimation, video composition, image search, asset reconciliation, and prompt inspiration live in the references.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A highly actionable, well-validated operational guide whose tool documentation and workflow gating are exemplary. Its weaknesses are token efficiency — the same safety rules are restated many times across sections — and some deep policy detail that belongs in the already-existing video reference rather than SKILL.md.

Suggestions

Consolidate repeatedly stated rules (first-Content-is-main, wait/timeout-is-not-failure, retry gating) into a single authoritative section and point to it from the tool sections instead of restating them, cutting significant length without losing enforcement.

Move the audioPolicy edge-case detail (native_mute/mute_fallback, composition vs direct-generation field shapes) and the final-video composition deep dive into references/video-generation.md, which video tasks are already required to load.

Merge the six language/terminology bullets in Ground rules into two: one on consistent user-facing language with the term-pair table, and one on keeping identifiers/paths unchanged.

DimensionReasoningScore

Conciseness

The body is dense domain policy with no filler or explanation of known concepts, but key rules are systematically duplicated — 'the first Content is automatically main' appears ~6 times (Ground rules, Capabilities, Confirmation, add_canvas_contents, select_canvas_main_content, Workflow coverage) and timeout/retry semantics ~5 times. This goes beyond anchor 4's 'minor instances that could be trimmed' while stopping short of anchor 2's padded sections.

3 / 5

Actionability

Every one of the 13 tools gets an executable, copy-paste-ready snippet with the required import shown once, parameter tables with required/optional flags, exact field names, and realistic example values (e.g. the add_canvas_elements items payload and the design-marker reference_images example). Fully matches anchor 5.

5 / 5

Workflow Clarity

Multi-step flows are explicitly sequenced (7-step media-transformation pattern, 4-step marker processing) with hard validation checkpoints: the mandatory preflight before every write, re-query after writes, staged user-confirmation gates, bounded retry gated on explicit status=failed with a 2-attempt cap, and post-import verification via query_canvas_element_details. This is the anchor-5 pattern of sequence + validation + feedback loops.

5 / 5

Progressive Disclosure

All 9 referenced files exist, and the Reference routing section plus Tool map clearly signal one-level-deep conditional loading. However, the ~600-line main file inlines deep detail that overlaps existing references — notably the ~250-word audioPolicy edge-case paragraph and the final-composition section, which duplicate territory of references/video-generation.md — a minor organization gap that keeps it at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

100%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.

The description is a model example: concrete capability list, an explicit 'Use when' clause, verbatim user-utterance triggers, and distinctive marker tokens. It is dense but every clause is functional rather than padded.

DimensionReasoningScore

Specificity

Lists six or more concrete actions ('initialize and query projects, create Elements and Content candidates, frame Elements, wait on generation, and process design markers') and the routing sentence names the remaining capabilities, leaving no material coverage gaps — matching the anchor-5 example's comprehensiveness rather than the 'minor gaps' of anchor 4.

5 / 5

Completeness

Explicitly answers both 'what' (the concrete action list) and 'when' (a 'Use when...' clause with concrete trigger phrases plus quoted example utterances), which is exactly the anchor-5 pattern; it is not anchor 4 because the 'when' guidance is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

Beyond domain nouns (images, videos, storyboards, video edits, final composed video), it quotes four verbatim user utterances ('generate an image on my canvas', 'make a video from this canvas project', 'add a new element to my design', 'edit the marked region of this image') — comprehensive natural-phrase coverage including marker syntax, fitting anchor 5.

5 / 5

Distinctiveness Conflict Risk

The niche (a Canvas product managed through its business tools) is distinct, and the unique [@design_canvas_project:...] / [@design_marker:...] tokens plus canvas-scoped quoted utterances give minimal conflict risk with generic image/video skills — anchor 5 rather than 4's 'minor overlap risk'.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (628 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

dtyq/magic

Path

backend/super-magic/agents/skills/canvas-manager/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.