ai-retrospective
v1.0.0AI Collaboration Retrospective — a tool-agnostic post-session analysis framework. After each AI-assisted coding/development session, it systematically review...
⭐ 0· 0·0 current·0 all-time
byAmos@amoshc
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (AI Collaboration Retrospective) match the runtime instructions: the skill analyzes conversation context, loads local reference docs, and produces a report. There are no unexpected binaries, env vars, or unrelated requirements.
Instruction Scope
Instructions ask the agent to scan the entire conversation history and to read reference files from the skill directory and write report files to the workspace — this is appropriate for a retrospective. Note: the skill assumes access to full session context and (optionally) the ability to persist 'knowledge' if the host tool supports it; users should be aware that the entire conversation content will be processed and included in outputs.
Install Mechanism
No install spec or code files are executed. The skill is instruction-only and has no downloads or scripts. README suggests cloning a public GitHub repo for convenience; that is normal documentation, not an automatic installer.
Credentials
The skill declares no environment variables, no credentials, and no config paths. Runtime requirements (conversation access, reading local reference files, writing reports) are proportionate to the stated purpose.
Persistence & Privilege
always:false (normal). The skill may auto-persist knowledge items or write report files to the workspace when the host supports persistence — this is expected for a retrospective but is a privilege to consider. It does not request elevated system-wide privileges or modify other skills' configs.
Assessment
This skill appears coherent and matches its description, but be aware it will process your entire session transcript and may save a report or 'persist' knowledge if your tool supports that. Before installing or invoking: (1) ensure no sensitive secrets or credentials were included in the conversation you don't want persisted, (2) check where the skill will write reports (workspace path) and whether it will write to any shared storage, and (3) if you prefer not to have automatic persistence, disable the host tool's auto-memory/persistence for this skill or note the step in the report rather than auto-saving. If you need higher assurance, run it first in a non-sensitive session and inspect generated outputs and any persistence behavior.Like a lobster shell, security has layers — review code before you run it.
latestvk979xxx3yszmjs70eexg29dprs84k2s9
License
MIT-0
Free to use, modify, and redistribute. No attribution required.