SKILLEMALL.ai
GitHub ↗ RU Sign in

CC command-development

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

Galaxy-Dawn/claude-scholar Agent Skills author: Galaxy-Dawn MIT 11 files body ≈ 4 565 tokens Open the sourcegithub.com↗ analyzed 2 d ago

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command…

As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

GeneratorAI and agentstype 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
83/100
safety, quality, tests
Safety 60%
77
Quality 40%
93
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    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 · 23

    ✓ No critical or high findings

    Medium and low: 23
    • low Broad scope meta-dynamic-shell examples/plugin-commands.md:35
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`node ${CLAUDE_PLUGIN_ROOT}/scripts/quality-check.js $1`
      fixture
    • low Broad scope meta-dynamic-shell examples/plugin-commands.md:68
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/security-scan.sh $1`
      fixture
    • low Broad scope meta-dynamic-shell examples/plugin-commands.md:71
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/perf-analyze.sh $1`
      fixture
    • low Broad scope meta-dynamic-shell examples/plugin-commands.md:74
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/best-practices.sh $1`
      fixture
    • low Broad scope meta-dynamic-shell examples/plugin-commands.md:144
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/pre-release-check.sh $1`
      fixture
    • low Broad scope meta-dynamic-shell examples/simple-commands.md:431
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`git status`
      fixture
    • low Broad scope meta-dynamic-shell references/advanced-workflows.md:25
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`gh pr view $1 --json title,body,author,files`
    • low Broad scope meta-dynamic-shell references/advanced-workflows.md:154
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`npm test`
    • low Broad scope meta-dynamic-shell references/advanced-workflows.md:531
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`npm test`
    • low Broad scope meta-dynamic-shell references/advanced-workflows.md:564
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`deploy.sh`
    • low Broad scope meta-dynamic-shell references/advanced-workflows.md:570
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`rollback.sh`
    • low Broad scope meta-dynamic-shell references/documentation-patterns.md:363
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`risky-operation.sh`
    • low Broad scope meta-dynamic-shell references/marketplace-considerations.md:52
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`pbcopy < file.txt`
    • low Broad scope meta-dynamic-shell references/plugin-features-reference.md:182
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`test -f ${CLAUDE_PLUGIN_ROOT}/config.json && echo "exists" || echo "missing"`
    • low Broad scope meta-dynamic-shell references/plugin-features-reference.md:323
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`mkdir -p ${CLAUDE_PLUGIN_ROOT}/cache && date > ${CLAUDE_PLUGIN_ROOT}/cache/last-run.txt`
    • low Broad scope meta-dynamic-shell references/plugin-features-reference.md:423
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`node ${CLAUDE_PLUGIN_ROOT}/scripts/lint.js $1`
    • low Broad scope meta-dynamic-shell references/testing-strategies.md:489
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`exit 1`
      fixture
    • low Broad scope meta-dynamic-shell references/testing-strategies.md:490
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`false`
      fixture
    • low Broad scope meta-dynamic-shell references/testing-strategies.md:491
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`command-that-does-not-exist`
      fixture
    • low Broad scope meta-dynamic-shell references/testing-strategies.md:494
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`echo ""`
      fixture
    • low Broad scope meta-dynamic-shell references/testing-strategies.md:495
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble) (test fixture / example file)
      !`cat /dev/null`
      fixture
    • low Broad scope meta-dynamic-shell SKILL.md:556
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`bash ${CLAUDE_PLUGIN_ROOT}/scripts/script.sh`
    • low Broad scope meta-dynamic-shell SKILL.md:732
      Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)
      !`node ${CLAUDE_PLUGIN_ROOT}/scripts/lint.js $1`

    Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 53/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Execution cost. Instruction body is 4565 tokens
    • 85Steps. 108 steps, 2 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Running it twice. No mutating operations
    • low 14 top-level sections: this looks like several domains in one skill

    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

    • +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
    • +5Description quotes 9 example trigger phrases
    • +3Description length 488: enough signal without eating the budget
    • +4Structure: 53 headings
    • +3Step-by-step instructions: 108 items
    • +4Has examples (44 code blocks)
    • +4Reference files are cited in the instructions (2 of 7)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.