SKILLEMALL.ai
GitHub ↗ RU Sign in

BF gitlab-cli-skills

Comprehensive GitLab CLI (glab) command reference and workflows for all GitLab operations. Use when working with merge requests, CI/CD pipelines, issues, releases, repositories, authentication, variables, labels, milestones, snippets, or any glab command. Covers 40+ sub-commands including glab mr, glab ci, glab issue, glab repo, glab release, glab variable, and more.

ClawHub Agent Skills author: Vince Lozada v1.13.26 MIT-0 2 files body ≈ 51 564 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 59/100 · Will not run — References files that are not bundled: ../glab-mr/SKILL.md, ../glab-issue/SKILL.md, ../glab-ci/SKILL.md

ProcedureGitLabInfrastructuretype 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
Technical rating
B
77/100
safety, quality, tests
Safety 60%
90
Quality 40%
57
Run on models
none yet
Process rating
F
59/100
Will not run
References files that are not bundled: ../glab-mr/SKILL.md, ../glab-issue/SKILL.md, ../glab-ci/SKILL.md
Tools and files w 18
0
Execution cost w 6
10
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration exfil-read-secret-files SKILL.md:996
    Reads credential / secret files (quoted — discussed, not commanded)
    - Check Docker config: `cat ~/.docker/config.json`
    quoted
  • medium Dangerous commands cmd-shell-rc SKILL.md:1533
    Writes to a shell startup file
    echo "autoload -U compinit; compinit" >> ~/.zshrc

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 51564 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../glab-mr/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-issue/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-ci/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-repo/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-milestone/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-iteration/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-label/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-release/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-packages/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-auth/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-config/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-ssh-key/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-gpg-key/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-token/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-todo/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-job/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-schedule/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-variable/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-securefile/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-runner/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-runner-controller/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-user/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-snippet/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-incident/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-workitems/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-api/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-artifact-registry/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-cluster/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-container-registry/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-dependency-firewall/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-deploy-key/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-orbit/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-quick-actions/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-security/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-stack/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-opentofu/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-alias/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-completion/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-help/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-version/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-check-update/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-whatsnew/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-changelog/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-attestation/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-duo/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-mcp/SKILL.md
  • warning missing-ref reference to a missing file: ../glab-skills/SKILL.md
  • warning missing-ref reference to a missing file: references/commands.md
  • warning missing-ref reference to a missing file: ../SECURITY.md
  • warning missing-ref reference to a missing file: templates/
  • warning missing-ref reference to a missing file: references/pipeline-best-practices.md
  • warning missing-ref reference to a missing file: references/pipeline-best-practices.md
  • warning missing-ref reference to a missing file: references/pipeline-best-practices.md
  • warning missing-ref reference to a missing file: scripts/create-mr-from-issue.sh
  • warning missing-ref reference to a missing file: scripts/ci-debug.sh
  • warning missing-ref reference to a missing file: scripts/sync-fork.sh
  • warning missing-ref reference to a missing file: scripts/batch-label-issues.sh
  • warning missing-ref reference to a missing file: scripts/mr-review-workflow.sh
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 59/100

Will not run. References files that are not bundled: ../glab-mr/SKILL.md, ../glab-issue/SKILL.md, ../glab-ci/SKILL.md
  • 0Tools and files. 58 referenced file(s) missing: ../glab-mr/SKILL.md, ../glab-issue/SKILL.md, ../glab-ci/SKILL.md
  • 10Execution cost. Instruction body is 51564 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 577 steps, 2 vague phrases
  • 100Failures and branches. 19 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 295 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (34 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)
  • -5TODO / placeholder text left in the skill
  • -212 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 369: enough signal without eating the budget
  • +4Structure: 460 headings
  • +3Step-by-step instructions: 577 items
  • +3Output format is stated explicitly
  • +4Has examples (316 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.

External checks

ClawHub: clean
This is a GitLab CLI reference skill that describes powerful GitLab operations, but the sensitive actions are disclosed and aligned with its purpose.
LLM: benign (high) · VirusTotal: · 10 Sept 2026