SKILLEMALL.ai
RU Sign in

B github-cli

Comprehensive GitHub CLI (gh) reference. Covers repos, issues, PRs, Actions, releases, gists, search, projects v2, API, secrets/variables, labels, codespaces, extensions, auth, and advanced GraphQL patterns.

ClawHub Agent Skills author: Tag v1.0.0 2 files body ≈ 11 017 tokens open source ↗ analyzed 25 h ago
IntegrationGitHubSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
B
87/100
Overall score
Safety 60%
95
Quality 40%
74
Tests bonus
0

How to improve

  1. The SKILL.md body exceeds 5,000 tokens: move reference detail into references/ and load it on demand.
  2. Add evals/evals.json with 4–6 real requests and expected answers: the full check will then use your cases instead of a model draft.
  3. Add a spec.yaml with triggers and assertions (skilltest init): the behaviour contract for CI.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • low Secrets in code secret-high-entropy-token SKILL.md:1084
    High-entropy token-like string (may be an id, hash or a credential)
    upda…lue(input: {
  • low Secrets in code secret-high-entropy-token SKILL.md:1123
    High-entropy token-like string (may be an id, hash or a credential)
    conv…sue(input: {
  • low Secrets in code secret-high-entropy-token SKILL.md:1154
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    ... on Proj…lue { number field { ... on Proj…eld { name } } }
    placeholder
  • low Secrets in code secret-high-entropy-token SKILL.md:1156
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    ... on Proj…lue { name field { ... on Proj…eld { name } } }
    placeholder
  • low Secrets in code secret-high-entropy-token SKILL.md:1157
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    ... on Proj…lue { title field { ... on Proj…eld { name } } }
    placeholder

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Lint

  • warning body-long SKILL.md body ≈ 11017 tokens (recommended < 5000); move details to references/

Process maturity 40/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 22 mutating operations with no state check
  • 40Execution cost. Instruction body is 11017 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 100Steps. 35 steps
  • 100Consistency. Name and required fields are in place
  • low 22 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (12 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 207: enough signal without eating the budget
  • +4Structure: 113 headings
  • +3Step-by-step instructions: 35 items
  • +4Has examples (92 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: clean
This is a documentation-only GitHub CLI reference whose powerful examples are expected for the tool but require care with tokens, secrets, extensions, and destructive commands.
LLM: benign (high) · VirusTotal: suspicious · 28 May 2026