SKILLEMALL.ai
GitHub ↗ RU Sign in

CC coco-diagram

Use for architecture, current-state, process, data-flow, medallion, or DP diagrams, including redrawing .drawio and Mermaid sources. Creates branded flowchart, sequence, ER, org, timeline, and chart visuals as standalone HTML/SVG/PNG.

coco-research/coco Agent Skills author: coco-research 80 files body ≈ 9 162 tokens Open the sourcegithub.com↗ analyzed 7 h ago

Use for architecture, current-state, process, data-flow, medallion, or DP diagrams, including redrawing .drawio and Mermaid sources. Creates branded…

As a process C 54/100 · Has gaps — References files that are not bundled: references/style-guide.md, references/onboarding.md, references/semantic-patterns.md

ProcedureWriting and documentsMarketingDesigntype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
65
Run on models
none yet
Process rating
C
54/100
Has gaps
References files that are not bundled: references/style-guide.md, references/onboarding.md, references/semantic-patterns.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9162 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/style-guide.md
  • warning missing-ref reference to a missing file: references/onboarding.md
  • warning missing-ref reference to a missing file: references/semantic-patterns.md
  • warning missing-ref reference to a missing file: references/animation.md
  • warning missing-ref reference to a missing file: references/type-architecture.md
  • warning missing-ref reference to a missing file: references/type-it-state.md
  • warning missing-ref reference to a missing file: references/type-flowchart.md
  • warning missing-ref reference to a missing file: references/type-sequence.md
  • warning missing-ref reference to a missing file: references/type-state.md
  • warning missing-ref reference to a missing file: references/type-er.md
  • warning missing-ref reference to a missing file: references/type-timeline.md
  • warning missing-ref reference to a missing file: references/type-swimlane.md
  • warning missing-ref reference to a missing file: references/type-quadrant.md
  • warning missing-ref reference to a missing file: references/type-radar.md
  • warning missing-ref reference to a missing file: references/type-loop.md
  • warning missing-ref reference to a missing file: references/type-nested.md
  • warning missing-ref reference to a missing file: references/type-tree.md
  • warning missing-ref reference to a missing file: references/type-org-chart.md
  • warning missing-ref reference to a missing file: references/type-layers.md
  • warning missing-ref reference to a missing file: references/type-venn.md
  • warning missing-ref reference to a missing file: references/type-pyramid.md
  • warning missing-ref reference to a missing file: references/type-bar.md
  • warning missing-ref reference to a missing file: references/type-line.md
  • warning missing-ref reference to a missing file: references/type-gantt.md
  • warning missing-ref reference to a missing file: references/type-scatter.md
  • warning missing-ref reference to a missing file: references/type-high-level.md
  • warning missing-ref reference to a missing file: references/type-process.md
  • warning missing-ref reference to a missing file: references/type-medallion.md
  • warning missing-ref reference to a missing file: references/type-data-flow.md
  • warning missing-ref reference to a missing file: references/type-dp-integration.md
  • warning missing-ref reference to a missing file: references/type-dp-security-matrix.md
  • warning missing-ref reference to a missing file: references/primitive-annotation.md
  • warning missing-ref reference to a missing file: references/primitive-sketchy.md
  • warning missing-ref reference to a missing file: references/primitive-icons.md
  • warning missing-ref reference to a missing file: assets/icons.html
  • warning missing-ref reference to a missing file: references/primitive-terminal.md
  • warning missing-ref reference to a missing file: references/output-spec.md
  • warning missing-ref reference to a missing file: references/type-quadrant.md
  • warning missing-ref reference to a missing file: references/import-drawio.md
  • warning missing-ref reference to a missing file: references/import-mermaid.md
  • warning missing-ref reference to a missing file: references/export.md
  • warning missing-ref reference to a missing file: references/type-*.md
  • warning missing-ref reference to a missing file: scripts/self_check.py
  • warning missing-ref reference to a missing file: references/type-<name>.md
  • note frontmatter-key unknown frontmatter key "domain"
  • note edit-residue the text marks something as outdated (lines 83): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 54/100

Will not run. References files that are not bundled: references/style-guide.md, references/onboarding.md, references/semantic-patterns.md
  • 0Tools and files. 44 referenced file(s) missing: references/style-guide.md, references/onboarding.md, references/semantic-patterns.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 15 mutating operations with no state check
  • 40Execution cost. Instruction body is 9162 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 109 steps, 1 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (32 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +2Single-language instructions
  • +3Description length 234: enough signal without eating the budget
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 109 items
  • +3Output format is stated explicitly
  • +4Has examples (8 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.