speech-coach
v1.0.0口才陪练龙虾 — AI public speaking coach with 15-step progressive training, 25 methodologies, and personalized progress tracking. Use when user asks about 口才训练, 演讲练...
⭐ 0· 53·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name, description, and curriculum match the runtime artifacts: SKILL.md, curriculum.md, and a progress_tracker.py CLI for tracking. One minor inconsistency: the package does not declare any required binaries but the runtime instructions and CLI expect Python 3.9+ (README mentions Python 3.9+). Otherwise requested resources (local workspace files) are proportional to a coaching/tracker skill.
Instruction Scope
SKILL.md instructs the agent to operate only within ~/.openclaw/workspace/speech-coach (read curriculum.md, read/create user_profile.json, run the bundled progress_tracker.py). It does not request system-wide config, unrelated env vars, remote endpoints, or hidden data collection. The instructions explicitly state text-only operation and forbid pretending to process audio/video.
Install Mechanism
No install spec is present (instruction-only skill plus included files). All code is packaged with the skill (curriculum.md, SKILL.md, progress_tracker.py). No external downloads or installers are used.
Credentials
The skill declares no required environment variables or credentials and uses an optional SPEECH_COACH_DIR env var to override its workspace — this is proportional. Note: the skill did not list a required binary but expects Python 3.9+ to run the CLI (README states Python 3.9+), so the missing declared binary (python) is a small discrepancy to be aware of.
Persistence & Privilege
always is false and the skill does not request system-wide persistence or modify other skills. It creates and updates files only under its own workspace (~/.openclaw/workspace/speech-coach), which is appropriate for a progress-tracking skill.
Assessment
This skill appears coherent and benign for text-based public-speaking coaching. Before installing, note: (1) it stores user_profile.json, progress.json, and other data as plaintext under ~/.openclaw/workspace/speech-coach — avoid putting sensitive personal data there; (2) the CLI requires Python 3.9+ (README mentions this) but the skill metadata did not explicitly declare 'python' as a required binary — ensure your agent environment has a compatible Python; (3) there are no network calls or external credentials requested by the skill; (4) if you prefer not to have files written under your home directory, run it in a controlled environment or set SPEECH_COACH_DIR to a directory you choose. If you want extra assurance, open progress_tracker.py and curriculum.md (they're included) and review the JSON files it will write to the workspace.Like a lobster shell, security has layers — review code before you run it.
latestvk979p6hxjbabwcarcgekm95cjs83wdjz
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🦞 Clawdis