SKILLEMALL.ai
GitHub ↗ RU Sign in

BC topic-monitor

Monitor topics of interest and proactively alert when important developments occur. Use when the user wants automated monitoring of specific subjects like product releases, news topics, technology updates, RSS/Atom feeds, or GitHub releases. Supports scheduled web search plus feed polling, boolean topic filters, AI importance scoring with sentiment tracking, smart alerts vs weekly digests, and memory-aware contextual summaries.

ClawHub Agent Skills author: Robby v1.6.0 MIT-0 52 files · 42 scripts body ≈ 1 697 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Monitor topics of interest and proactively alert when important developments occur.

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

AnalyzerGitHubInfrastructuretype 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
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
82
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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 · 0

    ✓ No critical or high findings

    Files scanned: 52. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 55/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 63 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1697 tokens
    • 100Running it twice. No mutating operations
    • low 13 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
    • -36 of 9 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 431: enough signal without eating the budget
    • +4Structure: 27 headings
    • +3Step-by-step instructions: 63 items
    • +4Has examples (16 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    In the sandbox The scripts kept to themselves

    The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

    Запущено 12 скриптов, ещё 26 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

    Из них 8 не дошли до работы, и об их поведении мы ничего не узнали.

    scripts/config.pyничего за пределами своей папки
    scripts/digest.pyничего за пределами своей папки
    scripts/importance_scorer.pyничего за пределами своей папки
    scripts/manage_topics.pyне запустился: manage_topics.py: error: the following arguments are required: command
    scripts/monitor.pyне запустился: ❌ Config file not found: /work/config.json
    scripts/process_alerts.pyничего за пределами своей папки
    scripts/quick.pyне запустился: quick.py: error: the following arguments are required: topic
    scripts/setup_cron.pyне запустился: {"error": "Config file not found: /work/config.json\nCopy config.example.json to config.json and customize it."}
    scripts/setup.pyне запустился: ⚠️ Input ended. No changes made.
    scripts/_vendor/sgmllib.pyне запустился: test.html : [Errno 2] No such file or directory: 'test.html'
    scripts/_vendor/feedparser/api.pyне запустился: ImportError: attempted relative import with no known parent package
    scripts/_vendor/feedparser/encodings.pyне запустился: ImportError: attempted relative import with no known parent package

    14 Oct 2026

    External checks

    ClawHub: suspicious
    The skill mostly does what it says, but its feed feature accepts unrestricted URLs and the documentation understates the resulting network and data-flow risks.
    LLM: suspicious (high) · VirusTotal: · 10 Sept 2026