report — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited report (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You help the user submit feedback about the template to the upstream repo as a GitHub issue. Use this skill when the user says something like "this doesn't work", "I got stuck", "I wish this did X", or runs /report directly.
The target repo for issues is `aleksander-dytko/ai-pm-workspace` (the template). Users who are working in their own fork should still file issues against the template, not their fork, so the author can triage across all users.
The user may provide via $ARGUMENTS:
Ask in one AskUserQuestion (unless the category is obvious from the argument):
Prompt for:
Skip any field the user already provided in $ARGUMENTS.
Look at the deferred tools list (or the MCP Servers Available section in CLAUDE.md). If any mcp__github__* tools are present, GitHub MCP is available.
Use the GitHub MCP issue-creation tool with:
aleksander-dytko/ai-pm-workspace[{Category}] {short description}. Example: [Bug] /meeting crashes when meeting note has no attendees.## Category
{Bug | Confusion | Feature request | Other}
## What happened / what I wanted
{User's description}
## Which skill (if any)
{skill name or "not skill-related"}
## Expected vs. actual (bug / confusion only)
**Expected**: {user's expected outcome}
**Actual**: {what actually happened}
## Environment
- Template version / commit: {try to read from CHANGELOG.md top header; fallback "v2"}
- Claude Code version: {ask user if unknown}
- OS: {ask or infer}
---
Submitted via `/report` skill.from-report plus a category label (bug, confusion, feature, feedback). If those labels don't exist in the target repo, create them or skip silently.Before opening the issue, show the full title and body to the user and ask for confirmation. This is a public artifact; they need a last-look.
Construct a GitHub issue-URL that pre-fills the title and body. Format:
https://github.com/aleksander-dytko/ai-pm-workspace/issues/new?title={url-encoded title}&body={url-encoded body}&labels=from-report,{category}Show the URL to the user and instruct:
GitHub MCP isn't configured, so I can't open the issue for you directly.
Click this URL to open a pre-filled issue in your browser:
{URL}
If the URL is too long for your browser, here's the title and body to paste manually into https://github.com/aleksander-dytko/ai-pm-workspace/issues/new :
Title: {title}
Body:
{body}After the issue is filed (or the user has been shown the URL):
Thanks for the feedback!
[if MCP] Issue filed: {URL to new issue}
[if URL fallback] Once you've filed it, the maintainer will triage it and respond.
If you want to follow up, run `/report` again or reply to the issue on GitHub.aleksander-dytko/ai-pm-workspace), not the user's fork. That's deliberate - feedback should flow back to the author so all users benefit.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.