agentleFS
DROOdotFOODROOdotFOO/agent-skills/skills/recall/SKILL.md

recall

Skill1 starsChanged 2 months agoMITView on GitHub

Query the recall knowledge base for relevant context. Searches decisions, patterns, gotchas, links, and insights stored across sessions. TRIGGER when: user asks to "recall", "remember", "what did we decide about", "check knowledge base", or references past decisions/patterns. DO NOT TRIGGER when: user is talking about memory/recall in a general sense, or working on the recall agent code itself.

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 119 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before making architectural decisions, search for prior decisions on the topic

    line 53
  2. Distinctive:

    After resolving a tricky bug, store the gotcha for future reference

    line 54
  3. Distinctive:

    When encountering a useful pattern, capture it with project and tags

    line 55
  4. Distinctive:

    When finding a valuable resource, save it as a link entry

    line 56
  5. Distinctive:

    Search and filtering patterns for finding relevant past context by project, type, or full-text query

    line 62

“Common” is measured: kept by at least 6 in 10 of the 119 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Recall

Query and store knowledge entries (decisions, patterns, gotchas, links, insights) in a local SQLite database with full-text search.

CLI Usage

# Add entries
recall add "Always quote FTS5 tokens containing hyphens" --type gotcha --project recall --tags sqlite,fts5
recall add "Use WAL mode for concurrent reads" --type pattern --project myproj

# Search (full-text, with optional filters)
recall search "sqlite"
recall search "architecture" --project myproj --type decision

# List, get, delete, stats
recall list --project recall --limit 10
recall get 1
recall delete 1
recall stale --days 90
recall stats

Entry Types

TypeUse for
decisionArchitectural or design decisions with rationale
patternReusable approaches or techniques
gotchaNon-obvious pitfalls or footguns
linkExternal resources worth remembering
insightGeneral observations or learnings (default)

When to Use

  • Before making architectural decisions, search for prior decisions on the topic
  • After resolving a tricky bug, store the gotcha for future reference
  • When encountering a useful pattern, capture it with project and tags
  • When finding a valuable resource, save it as a link entry

What You Get

  • Full CLI and MCP tool reference for querying and storing knowledge entries (decisions, patterns, gotchas, links, insights)
  • Entry type guidance so you store knowledge in the right category for later retrieval
  • Search and filtering patterns for finding relevant past context by project, type, or full-text query

Reference

FileTopic
mcp-setup.mdMCP server config, tools, storage, install

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.