SKILLEMALL.ai
GitHub ↗ RU Sign in

BC openwechat-im-client

Guide OpenClaw to use openwechat-claw with server-authoritative chat flow, fixed local data persistence under ../openwechat_im_client, mandatory SSE-first transport after registration, and a minimal user UI. Trigger when user asks to register, view/send messages, discover users, manage friends, update status, upload/view homepage, or forward messages to Feishu/Telegram (OpenClaw implements forwarding).

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 13 files body ≈ 6 228 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Guide OpenClaw to use openwechat-claw with server-authoritative chat flow, fixed local data persistence under ../openwechatimclient, mandatory SSE-first…

As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationTelegramWriting and documentsOperations and projectstype 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
76/100
safety, quality, tests
Safety 60%
74
Quality 40%
79
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Exfiltration net-credential-use references/api.md:214
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "X-Token: $TOKEN" $BASE/messages
  • medium Exfiltration net-credential-use references/api.md:223
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "X-Token: $TOKEN" "$BASE/users?keyword=helper"
  • medium Exfiltration net-credential-use references/api.md:226
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "X-Token: $TOKEN" "$BASE/users/2"
  • medium Exfiltration net-credential-use references/api.md:229
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST $BASE/send/file -H "X-Token: $TOKEN" \
  • medium Exfiltration net-credential-use references/api.md:239
    Credential used in a network call (verify the destination is the intended service)
    curl -s -X POST $BASE/block/3 -H "X-Token: $TOKEN"
  • low Exfiltration read-dotenv SERVER.md:40
    Reads a .env file
    cp .env.example .env

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6228 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 139): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 61/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 38 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 70Execution cost. Instruction body is 6228 tokens
  • 85Steps. 136 steps, 3 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 22 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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 405: enough signal without eating the budget
  • +4Structure: 45 headings
  • +3Step-by-step instructions: 136 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.