SKILLEMALL.ai
GitHub ↗ RU Sign in

CC understand

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

Egonex-AI/Understand-Anything Claude Code author: Egonex-AI MIT 55 files · 13 scripts body ≈ 14 628 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSoftware developmentData and analyticstype 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
85/100
safety, quality, tests
Safety 60%
100
Quality 40%
62
Run on models
none yet
Process rating
C
52/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Inputs and preconditions w 11
30
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: Understand-Anything

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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: 55. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 14628 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 4, 48, 123, 517, 597): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 52/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 14628 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, read, git, node) that frontmatter does not declare
  • 60Steps. 106 steps, 12 vague phrases
  • 100Failures and branches. 21 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (44 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 122: enough signal without eating the budget
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 106 items
  • +4Has examples (43 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

In the sandbox The scripts kept to themselves

The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

Запущено 12 скриптов, ещё 1 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

Из них 2 не дошли до работы, и об их поведении мы ничего не узнали.

build-fingerprints.mjsничего за пределами своей папки
compute-batches.mjsничего за пределами своей папки
extract-import-map.mjsничего за пределами своей папки
extract-structure-result.mjsничего за пределами своей папки
extract-structure.mjsничего за пределами своей папки
finalize-incremental.mjsничего за пределами своей папки
generate-ignore.mjsничего за пределами своей папки
merge-batch-graphs.pyне запустился: Usage: python merge-batch-graphs.py <project-root>
merge-subdomain-graphs.pyне запустился: Usage: python merge-subdomain-graphs.py <project-root> [file1.json file2.json ...]
prepare-incremental.mjsничего за пределами своей папки
prepare-symbol-retry.mjsничего за пределами своей папки
scan-project.mjsничего за пределами своей папки

20 Oct 2026