SKILLEMALL.ai
GitHub ↗ RU Sign in

CC ocas-bower

Automatic Google Drive organizer. Scans Drive structure and file contents, builds a personalized preference profile, applies domain-specific logic (taxes by year, projects by name, home by system, finance by institution), and executes non-destructive moves, renames, and description writes. Learns organizational style over time and auto-approves consistently accepted patterns. Never deletes files. NOT for web research, document analysis, or Chronicle ingestion.

ClawHub Hermes author: Indigo Karasu v1.0.0 MIT-0 30 files · 7 scripts body ≈ 8 728 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

Automatic Google Drive organizer.

As a process C 51/100 · Has gaps — References files that are not bundled: scripts/google_auth.py

ProcedureGoogle DriveSoftware developmentInfrastructureData and analyticstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
C
80/100
safety, quality, tests
Safety 60%
90
Quality 40%
64
Run on models
none yet
Process rating
C
51/100
Has gaps
References files that are not bundled: scripts/google_auth.py
Tools and files w 18
0
Inputs and preconditions w 11
30
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 10

✓ No critical or high findings

Medium and low: 10
  • low Secrets in code secret-high-entropy-token references/light-scan-triage.md:43
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `1uBw…WHS` (33 chars). If you print/echo/copy an ID
    quoted
  • low Instruction override en-ignore-previous references/organization_rules.md:43
    Instruction-override phrase ("ignore previous instructions") (negated — the text forbids it)
    Auto-approved proposals still pass the staleness gate and permission check before execution. They do not bypass safety rules -- only the human approval step.
    negated
  • low Dangerous commands cmd-background-process references/scan-debug.md:68
    Starts a background / autostarted process (documentation of a security skill)
    nohup python3 bower_resume_scan.py > /tmp/bower_resume.log 2>&1 &
    security skill
  • low Secrets in code secret-high-entropy-token scripts/bower_analyze.py:285
    High-entropy token-like string (may be an id, hash or a credential)
    # Check for folders that start with long hex IDs (like 1U6K…YDj)
  • low Secrets in code secret-high-entropy-token scripts/bower_resume_scan.py:37
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "1Axg…udj", "1tcH…lD1", "19lJ…Pmj", "1i8f…coe",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/bower_resume_scan.py:38
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "1Nru…Rdi", "17GF…qyU", "1Bp7…8VJ", "10l4…6s0",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/bower_resume_scan.py:39
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "1gdX…aDZ", "1uBw…WHS", "1_Uk…nXC", "1keQ…RN6",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/bower_resume_scan.py:41
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "1G8j…bmQ", "1D7p…Swv", "1iie…IYu", "1N0Q…AMc",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/bower_resume_scan.py:43
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "1uBw…WHS",  # Hermes
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:281
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **Drive file/folder IDs are 33 chars — never truncate** — A valid Drive ID looks like `1uBw…WHS` (33 chars). If you print/echo/copy an ID and it gets truncated to ~24 (a com
    quoted

Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 464 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning body-long SKILL.md body ≈ 8728 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/google_auth.py
  • note frontmatter-key unknown frontmatter key "warning"
  • note frontmatter-key unknown frontmatter key "source"
  • note frontmatter-key unknown frontmatter key "includes"
  • note frontmatter-key unknown frontmatter key "triggers"

Process rating: all ten parameters 51/100

Will not run. References files that are not bundled: scripts/google_auth.py
  • 0Tools and files. 1 referenced file(s) missing: scripts/google_auth.py
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 17 mutating operations with no state check
  • 40Execution cost. Instruction body is 8728 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
  • 60Consistency. The Hermes dialect needs category and tags
  • 85Steps. 73 steps, 1 vague phrases
  • 100Failures and branches. 2 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 26 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable
  • medium 5 test cases, all positive: not one "should refuse" or "should ask first"
  • low No test case covers injection arriving through data

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
  • +4No input/output examples
  • -34 of 7 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 464: enough signal without eating the budget
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 73 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (16 of 16)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.

External checks

ClawHub: suspicious
This Drive organizer has legitimate organizing features, but it needs Review because it combines broad Drive access with scheduled changes, self-update, and under-disclosed Chronicle/MemPalace profiling flows.
LLM: suspicious (high) · 23 Sept 2026