AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Recall

skill-robabby-claude-skills-recall · by robabby

Search Obsidian memories by keyword and concept

No reviews yet
0 installs
36 views
0.0% view→install

Install

$ agentstack add skill-robabby-claude-skills-recall

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-robabby-claude-skills-recall)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
8mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Recall? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Recall

Search stored memories using keyword/concept matching.

Workflow

  1. Parse the search query from $ARGUMENTS
  • If no arguments provided, ask what to search for
  1. Determine search strategy:
  • Content search: Grep for query in memory file content
  • Concept search: Grep for query in frontmatter concepts
  • Type filter: Optionally narrow to specific memory type folder
  1. Execute searches in /Areas/AI/Memory:

``` # Content search Grep pattern="$QUERY" path="/Areas/AI/Memory" glob="*.md"

# Concept search (frontmatter) Grep pattern="concepts:.$QUERY" path="/Areas/AI/Memory" glob=".md"

# Type-filtered (if specified) Grep pattern="$QUERY" path="/Areas/AI/Memory/Strategic" glob="*.md" ```

  1. Read the matching files (up to limit, default 10)
  1. Sort by importance if multiple results
  1. Present findings:
  • "Found X memories about [topic]..."
  • Summarize top 2-3 findings
  • Note memory types and importance
  • Mention if more results available

Search Parameters

| Parameter | Default | Description | |-----------|---------|-------------| | Query | required | Search terms | | Limit | 10 | Max results to read | | Type | all | Filter: episodic/semantic/procedural/strategic |

Search Patterns

# General content search
Grep pattern="metatron" path="/Areas/AI/Memory" glob="*.md"

# Concept frontmatter search
Grep pattern="concepts:.*interview" path="/Areas/AI/Memory" glob="*.md"

# Type-filtered search
Grep pattern="deploy" path="/Areas/AI/Memory/Procedural" glob="*.md"

# High importance only
Grep pattern="importance: 0\\.[89]" path="/Areas/AI/Memory" glob="*.md"

# Recent memories (Glob sorts by mtime)
Glob pattern="Areas/AI/Memory/**/*.md" path=""

Examples

User: /recall hexis integration -> Search content and concepts for "hexis" and "integration" -> Present matching memories with type and importance

User: /recall deployment procedural -> Search in Areas/AI/Memory/Procedural/ for "deployment" -> Focus on how-to memories

User: /recall -> Ask: "What would you like to search for?"

Response Format

Present findings conversationally:

  • "Found X memories about [topic]..."
  • Summarize the most relevant 2-3 findings
  • Note memory types and importance levels
  • Mention if there are more results available
  • Offer to read specific memories in full if needed

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.