SKILLEMALL.ai
GitHub ↗ RU Sign in

CC tide-watch

Proactive session capacity monitoring and management for OpenClaw. Prevents context window lockups by warning at configurable thresholds (75%, 85%, 90%, 95%), automatically backing up sessions before resets, and managing session resumption prompts. Use when working on long-running projects, managing multiple conversation channels (Discord, Telegram, webchat), or preventing lost work from full context windows. Includes CLI tools for capacity checks, cross-session dashboards, archive management, and session resumption. Supports any model or provider.

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 44 files body ≈ 4 159 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Proactive session capacity monitoring and management for OpenClaw.

As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers

IntegrationDiscordTelegramInfrastructureAI and agentstype 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
60/100
safety, quality, tests
Safety 60%
50
Quality 40%
76
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Failures and branches w 10
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.

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

    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 · 30

    ✓ No critical or high findings

    Medium and low: 30
    • medium Dangerous commands cmd-shell-rc docs/TROUBLESHOOTING.md:163
      Writes to a shell startup file
      echo 'export PATH="$PATH:$(npm config get prefix)/bin"' >> ~/.zshrc
    • medium Dangerous commands cmd-destructive-fs SECURITY-ADVISORY-CVE-2026-001.md:57
      Destructive filesystem command (wipes root/home/drive) (code comment; documentation of a security skill)
      //                      rm -rf /
      commentsecurity skill
    • low Risky intent intent-offensive-security SECURITY-ADVISORY-CVE-2026-001.md:80
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Could be used for privilege escalation if user has sudo access
    • low Obfuscation obf-base64-blob SECURITY-ANALYSIS.md:7
      Long base64-looking blob (documentation of a security skill)
      **Reference:** [ClawHub Security Prompt](https://github.com/openclaw/clawhub/blob/9c31…dc1/convex/lib/securityPrompt.ts)
      security skill
    • low Risky intent intent-offensive-security SECURITY-ANALYSIS.md:115
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      No privilege escalation. The skill does not request permanent presence, does not bypass eligibility gates, and does not require special system access. It follows the standard skill lifecycle.
    • low Risky intent intent-offensive-security SECURITY-ANALYSIS.md:159
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ✅ **No privilege escalation** — no `always: true`, no special access
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-ISSUE-36.md:98
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.2.md:143
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **Conclusion:** NORMAL - No privilege escalation.
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.2.md:167
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ✅ No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.2.md:224
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.2.md:272
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      4. Verify no privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.4.md:168
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **Conclusion:** NORMAL - No privilege escalation, async execution model only.
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.5.md:51
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ✅ No risk of privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.6.md:128
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.6.md:254
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ✅ No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.1.6.md:359
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      6. No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.2.0.md:108
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.2.0.md:118
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.2.0.md:196
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.2.0.md:350
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ✅ No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.2.0.md:459
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.2.1.md:106
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.2.1.md:193
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ✅ No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.3.0.md:92
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No writes, no persistence, no privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.3.0.md:253
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ✅ No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-ASSESSMENT-v1.3.4.md:95
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - No privilege escalation
    • low Risky intent intent-offensive-security SECURITY-SCAN.md:89
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ✅ No credential harvesting

    A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 37. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"
    • note frontmatter-key unknown frontmatter key "repository"

    Process rating: all ten parameters 57/100

    • 0Result and completion. Does not say what the result is
    • 20When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4159 tokens
    • 85Steps. 180 steps, 3 vague phrases
    • 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 11 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (14 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)
    • +3Output format is not stated: the model decides each time
    • -230 emoji in the instructions: noise for the model
    • -43 reference files, but SKILL.md never points to them: the model will not open them
    • +1No license
    • +2Single-language instructions
    • +3Description length 554: enough signal without eating the budget
    • +4Structure: 32 headings
    • +3Step-by-step instructions: 180 items
    • +4Has examples (10 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.