CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fireworks-tech-graph

Create precise SVG technical diagrams, export PNG or offline HTML, and animate supported semantic SVGs to GIF. Use for architecture, UML, agent, cloud or workflow diagrams; not photos, raster art or statistical charts.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

The canonical home for this skill is fireworks-tech-graph in yizhiyanhua-ai/fireworks-tech-graph

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 tightly written skill body: dense, non-obvious guidance with real commands, an explicit validate-and-repair feedback loop, and a clean one-level reference structure into a well-populated bundle. The only notable gap is that command templates use a placeholder SKILL_ROOT path rather than fully copy-paste-ready invocations.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: no explanations of concepts Claude already knows, every sentence carries non-obvious guidance ('a successful command is not a visual quality verdict', 'Do not assume cwd or a previous shell variable persists'); not 4 because there is no padding to trim.

5 / 5

Actionability

Concrete, mostly executable commands for the full pipeline ('fireworks.py validate architecture input.json', 'render ... --report layout.json', 'check diagram.svg', 'export-png diagram.svg diagram.png --width 1920'), but both command blocks embed a literal placeholder path ('${CLAUDE_SKILL_DIR:-/absolute/path/from-codex-skill-metadata}'), so they are not fully copy-paste ready; not 3 because guidance goes well beyond high-level hints.

4 / 5

Workflow Clarity

Clear sectioned sequence (select → generate/check → additional outputs → verify) with explicit validation commands and a feedback loop: 'After a failed check, use its element IDs and geometry to make a focused repair; change the approach after two unchanged failures'; not 4 because checkpoints and error recovery are explicit, including skip-handling for unavailable image viewing.

5 / 5

Progressive Disclosure

Well-signaled one-level-deep markdown links (style-diagram-matrix.md, composition-quality-contract.md, png-export.md, motion-effects.md, etc.), all of which resolve to real files in references/ with no nested reference chains, plus explicit load-only-what's-needed guidance ('Read other styles only for a requested comparison'); not 4 because the split and navigation are clean throughout.

5 / 5

Total

19

/

20

Passed

Description

92%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: concrete capabilities, an explicit 'Use for...' trigger clause with concrete diagram types, and explicit out-of-scope exclusions that minimize conflict with adjacent skills. The only weakness is modest synonym coverage among trigger terms (e.g., flowchart, sequence diagram, .svg).

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'Create precise SVG technical diagrams, export PNG or offline HTML, and animate supported semantic SVGs to GIF' — covering all output routes comprehensively; not 4 because there are no coverage gaps.

5 / 5

Completeness

Explicitly answers what (create SVG diagrams, export PNG/HTML, animate to GIF) and when ('Use for architecture, UML, agent, cloud or workflow diagrams; not photos, raster art or statistical charts') with concrete trigger phrases and explicit exclusions; not 4 because the when-clause is fully explicit.

5 / 5

Trigger Term Quality

Good natural trigger coverage ('architecture, UML, agent, cloud or workflow diagrams') but misses common synonyms and file extensions users would say, such as 'flowchart', 'sequence diagram', or '.svg'; not 3 because the included terms are natural and specific.

4 / 5

Distinctiveness Conflict Risk

Clear niche (technical/semantic SVG diagrams) with distinct triggers and explicit negative scope that fences off adjacent skills (photos, raster art, statistical charts); not 4 because conflict risk is minimal, not minor.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

yizhiyanhua-ai/fireworks-tech-graph

Path

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.