SKILLEMALL.ai
GitHub ↗ RU Sign in

CD emergency-rescue

Recover from developer disasters. Use when someone force-pushed to main, leaked credentials in git, ran out of disk space, killed the wrong process, corrupted a database, broke a deploy, locked themselves out of SSH, lost commits after a bad rebase, or hit any other "oh no" moment that needs immediate, calm, step-by-step recovery.

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 7 593 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Recover from developer disasters.

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureGitHubDockerPostgreSQLMySQLInfrastructureSoftware developmenttype 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
C
71/100
safety, quality, tests
Safety 60%
69
Quality 40%
74
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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.

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.
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 · 7

✓ No critical or high findings

Medium and low: 7
  • medium Dangerous commands cmd-privilege SKILL.md:435
    Privilege escalation / world-writable permissions
    sync && echo 3 | sudo tee /proc/sys/vm/drop_caches
  • medium Dangerous commands cmd-privilege SKILL.md:705
    Privilege escalation / world-writable permissions
    sudo cp new-cert.pem /etc/ssl/certs/mysite.pem
  • medium Dangerous commands cmd-privilege SKILL.md:706
    Privilege escalation / world-writable permissions
    sudo cp new-key.pem /etc/ssl/private/mysite.key
  • medium Dangerous commands cmd-persistence SKILL.md:717
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (security demo / example)
    echo '0 9 * * 1 echo | openssl s_client -connect mysi…443 2>/dev/null | openssl x509 -checkend 604800 -noout || echo "CERT EXPIRES WITHIN 7 DAYS" | mail -s "SSL ALERT" ad…@….com' | cront
    demo
  • medium Dangerous commands cmd-privilege SKILL.md:837
    Privilege escalation / world-writable permissions
    echo "nameserver 8.8.8.8" | sudo tee /etc/resolv.conf
  • medium Dangerous commands cmd-privilege SKILL.md:884
    Privilege escalation / world-writable permissions
    echo "93.184.216.34 mysite.com" | sudo tee -a /etc/hosts
  • low Secrets in code secret-aws-key SKILL.md:173
    AWS access key ID (placeholder value)
    aws iam delete-access-key --access-key-id AKIAXXXXXXXXXXXXXXXX --user-name <user>
    placeholder

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7593 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 49/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 20 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (git) that frontmatter does not declare
  • 70Execution cost. Instruction body is 7593 tokens
  • 100Steps. 20 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 12 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

  • +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 332: enough signal without eating the budget
  • +4Structure: 39 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (27 code blocks)

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