SKILLEMALL.ai
GitHub ↗ RU Sign in

DD autoresearch

Autonomous iteration loop: modify, verify, keep/discard against any metric

Not recommendedcritical or high security findings · low grade D
mxyhi/ok-skills Agent Skills author: mxyhi Apache-2.0 23 files · 2 scripts body ≈ 1 937 tokens Open the sourcegithub.com↗ analyzed 4 d ago

Autonomous iteration loop: modify, verify, keep/discard against any metric

As a process D 35/100 · Unfinished process — References files that are not bundled: scripts/...

AnalyzerData 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
D
59/100
safety, quality, tests
Safety 60%
57
Quality 40%
61
Run on models
none yet
Process rating
D
35/100
Unfinished process
References files that are not bundled: scripts/...
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. 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 · 5

  • high Dangerous commands cmd-pipe-to-shell autoresearch.md:42
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    Before first dry-run, screen Verify command for: rm -rf, fork bombs, curl|sh, embedded credentials, outbound writes. Block dangerous commands.
  • high Dangerous commands cmd-pipe-to-shell plan.md:54
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    3. **Safety screen:** check proposed command for rm -rf, fork bombs, curl|sh, credentials
Medium and low: 3
  • medium Dangerous commands cmd-pipe-to-shell regression.md:110
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    Verify-command screen (no `rm -rf` / `curl|sh`); worktree cleanup + prune on crash; data-migration refuses any non-allowlisted DB URL; probe auto-skips non-interactively; chained `ship` never auto-dep
    quoted
  • low Risky intent intent-offensive-security references/security-checklist.md:12
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Elevation of Privilege | Unauthorized access | Missing authz checks, IDOR, privilege escalation paths |
  • low Risky intent intent-offensive-security references/security-checklist.md:43
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | High | Requires some access, significant impact | Stored XSS, IDOR, privilege escalation |

Files scanned: 23. 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 missing-ref reference to a missing file: scripts/...

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: scripts/...
  • 0Tools and files. 1 referenced file(s) missing: scripts/...
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 6 mutating operations with no state check
  • 100Steps. 24 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1937 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (4 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)
  • +3Description length 74: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -31 of 2 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 24 items
  • +4Reference files are cited in the instructions (1 of 4)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.