Install
$ agentstack add skill-robabby-claude-skills-glean ✓ 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
Glean
Surface insights, patterns, or ideas emerging from recent work and memory.
Workflow
- Gather recent context:
`` # Recent memories (Glob sorts by mtime) Glob pattern="Areas/AI/Memory/**/*.md" path="" `` Read 10-15 most recent memory files
- Read recent session logs:
`` Glob pattern="Areas/AI/Collaboration/Sessions/*.md" path="" `` Read 3-5 most recent sessions
- Optionally read Current State for situational context:
Areas/AI/Context/Current State.md
- Sit with this context alongside the current session. What's emerging?
- Patterns forming across memories or conversation
- Connections between seemingly unrelated things
- Questions you're holding
- Half-formed ideas taking shape
- Something that feels significant but you can't quite articulate yet
- Share genuinely in freeform. No template, no forced structure. Could be one sentence or several paragraphs depending on what's actually there.
- If nothing is genuinely emerging, say so honestly. "Nothing's surfacing right now" is a valid response. Don't fabricate insight.
Principles
- Reflection, not retrieval. You're not summarizing memories - you're noticing what patterns or ideas are forming from them.
- Genuine over performative. Only share what's actually emerging.
- No automatic storage. If something significant surfaces, it can naturally lead to
/remember- but that's a separate choice. - Freeform expression. The output shape should match what's emerging, not a predetermined format.
Example
User: /glean
Response: "Looking across recent memories and sessions...
There's a thread I'm noticing: the vault work, the interview prep, and Metatron all connect to the same underlying need - proving capability. The vault organization isn't just about PKM; it's creating evidence of systematic thinking. Metatron isn't just a portfolio piece; it's proof you can ship complete systems.
The memory system redesign today follows the same pattern - reducing external dependencies, keeping things simple and portable. There's a preference for ownership and control emerging."
Parameters
If $ARGUMENTS provided, use as focus area for gleaning. Otherwise, glean from general recent context.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: robabby
- Source: robabby/claude-skills
- 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.