Install
$ agentstack add skill-theaichimera-claude-code-project-intelligence-help ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/help — Project Intelligence Quick Reference
Print the following reference card exactly as shown. Do not run any commands — just display this text.
Progressions — How your understanding evolved
| Command | What it does | |---------|-------------| | /progress start | Start tracking a new investigation | | /progress add "" | Add a document (baseline, deepening, correction, pivot, synthesis) | | /progress correct "" | Correct a previous document | | /progress conclude | Mark investigation complete | | /progress show | See current state + open questions | | /progress list | List all progressions | | /progress search | Search across all progressions |
Episodic Memory — What you discussed
| Command | What it does | |---------|-------------| | /recall | Search all your past Claude Code sessions and documents |
Automatic: Every session is archived, summarized, and indexed. Recent sessions are injected at start.
Preferences
| Command | What it does | |---------|-------------| | /remember | Store a preference for all future sessions |
Synthesis
| Command | What it does | |---------|-------------| | /reflect [topic] | Synthesize a progression's state via Opus |
Activity Intelligence — What you did
| Command | What it does | |---------|-------------| | /activity | Show recent activity summary (GitHub + PI) | | /activity search | Search your activities | | /activity gather | Pull latest from GitHub | | /activity report | Generate structured monthly report | | /activity | What has someone else been doing? (GitHub-only) | | /activity team | Activity across all configured users |
Setup: pi-activity sources add YOUR_GITHUB_USERNAME --org YOUR_ORG
Plugins
| Command | What it does | |---------|-------------| | /plugins | Manage installed plugins |
CLI Commands (terminal)
# Episodic
pi-query # Search sessions
pi-backfill # Import existing sessions (one-time)
# Activity
pi-activity sources add --org # Add GitHub source
pi-activity gather # Pull activity
pi-activity search # Search activities
pi-activity report --user --month YYYY-MM # Monthly report
pi-activity recent --days 7 # Recent activity
# Progressions
pi-progression-status # All progressions
pi-progression-status --project --topic # Specific one
# Preferences
pi-remember # Store preference
pi-remember --list # List preferences
# Knowledge
pi-knowledge-sync # Sync knowledge repo
pi-index --all # Re-index documents
# Maintenance
pi-export ~/backup.tar.gz # Export for another machine
pi-import ~/backup.tar.gz # Import on new machine
What runs automatically
- Session start: Archives previous session, syncs knowledge repo, injects context (progressions, preferences, recent sessions, activity, documents)
- Session end: Quick metadata archive, pushes knowledge repo
Full docs: README.md
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: theaichimera
- Source: theaichimera/claude-code-project-intelligence
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.