SKILLEMALL.ai
GitHub ↗ RU Sign in

AF dibp-topic-clustering

Use when the user asks to (re)cluster DIBP topic data into 需求簇/用户主动洞察, regenerate clusters.json, review the long-tail (未分类) topics, add a new theme to the taxonomy, or push cluster results to the dev/prod backend. Covers the offline batch pipeline in scripts/cluster-*.mjs — this is NOT the daily incremental Hive job described in docs/features/dibp-insight-daily-clustering.md, which is unimplemented.

ClawHub Agent Skills author: christinelee3025 v1.0.0 MIT-0 2 files body ≈ 967 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

json, review the long-tail (未分类) topics, add a new theme to the taxonomy, or push cluster results to the dev/prod backend.

As a process F 46/100 · Will not run — References files that are not bundled: scripts/cluster-99-run-pipeline.mjs, scripts/cluster-lib-themes.mjs

ProcedureInfrastructureSoftware 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
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
75
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: scripts/cluster-99-run-pipeline.mjs, scripts/cluster-lib-themes.mjs
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

How to improve

  1. 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 · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/cluster-99-run-pipeline.mjs
  • warning missing-ref reference to a missing file: scripts/cluster-lib-themes.mjs

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: scripts/cluster-99-run-pipeline.mjs, scripts/cluster-lib-themes.mjs
  • 0Tools and files. 2 referenced file(s) missing: scripts/cluster-99-run-pipeline.mjs, scripts/cluster-lib-themes.mjs
  • 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
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 19 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 967 tokens
  • 100Running it twice. No mutating operations

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 402: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 19 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

External checks

ClawHub: clean
This skill is a narrowly scoped guide for manually rerunning DIBP topic clustering, with sensitive backend updates clearly gated on explicit user approval.
LLM: benign (high) · VirusTotal: · 31 Jul 2026