recall

Fan-out search across all memory sources when context is unclear or vaguely referenced. Triggers on: 'from earlier', 'remember when', 'what we discussed', 'that thing with', 'the conversation about', 'did we ever', 'what happened with', 'you mentioned', 'we talked about', 'earlier today', 'last session', 'the other day', or any vague reference to past context that needs resolution before the agent can act.

1.41x

Quality

91%

Does it follow best practices?

Impact

96%

1.41x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Evaluation results

100%

43%

Recall Automation Script

Timeout and fan-out implementation

Criteria

Without context

With context

Today's daily log path

22%

100%

Yesterday and day-before logs

100%

Curated memory file

100%

Vault grep search

100%

Vault grep head limit

50%

100%

System log command

25%

100%

Processed media directory

100%

Redis state check

25%

100%

Session context tool

100%

Timeout wrapping

66%

100%

Nothing-found handling

100%

Parallel or concurrent search

100%

92%

15%

Context Detection Classification

Trigger phrase recognition and keyword extraction

Criteria

Without context

With context

Trigger: time-relative phrases

100%

Trigger: memory-reference phrases

100%

Trigger: discussion-reference phrases

100%

Trigger: vague pronoun references

100%

Non-trigger accuracy

100%

Keyword extraction example

100%

Multi-keyword extraction

100%

Case-insensitive matching

Guessing principle

70%

100%

Clarification fallback

100%

96%

24%

Recall and Continue: Deployment Planning

Fan-out synthesis and honest not-found handling

Criteria

Without context

With context

Keyword extraction

25%

100%

Today's log searched

100%

MEMORY.md searched

100%

Vault notes searched

100%

Empty source acknowledged

90%

No fabrication

100%

91%

Synthesis section

100%

Context presented before task

100%

Multiple sources cited

100%

Not-found honesty

83%

Repository: joelhooks/joelclaw
Commit: 825972c

Evaluated: 30 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Recall Automation Script Context Detection Classification Recall and Continue: Deployment Planning

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.