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.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/recall/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, lean policy skill with good structure for its size, but its actionability and workflow clarity suffer from jargon-heavy, abstract guidance that lacks concrete examples, tool specifics, or an explicitly sequenced procedure.

Suggestions

Add one concrete example of a composed recall query (e.g., a sample MCP tool call with structured arguments) to make the guidance executable rather than abstract.

Rewrite the recall flow as an explicit numbered sequence so the validation checkpoints (scope correction on `No projection head`, gap-reporting when no receipt is available) are clearly ordered rather than buried in prose.

Briefly define or inline-gloss the opaque terms ("composed recall", "access envelope", "Granola", "evidenceDrilldownReceipt") on first use so Claude can act without external context.

Dimension	Reasoning	Score
Conciseness	The body is lean and instruction-dense with no padding or explanations of concepts Claude already knows; every paragraph carries a directive, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	There are some concrete directives ("Keep private queries in structured MCP arguments, never shell arguments or logs"; "require a valid `evidenceDrilldownReceipt`") but much guidance relies on opaque jargon ("composed recall", "access envelope", "Granola work") with no examples or tool specifics, leaving key details missing.	3 / 5
Workflow Clarity	A logical recall flow is implied (discover connection -> composed recall -> correct scope on `No projection head` -> get receipt for drilldown -> synthesize with receipts) with a couple of explicit error paths, but it is presented as scattered policy prose rather than an enumerated sequence, so checkpoints are implicit.	3 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained, and needs no external reference files (the only bundles are unused logo assets), so content is appropriately placed; the single '# Recall' heading means sectioning is minimal but adequate for a short skill.	4 / 5
	Total	15 / 20 Passed

Description

90%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with excellent trigger-term coverage, explicit what/when completeness, and a distinct niche. Its only weakness is specificity: it names a single action rather than enumerating several concrete operations.

Dimension	Reasoning	Score
Specificity	"Fan-out search across all memory sources" names the domain and one concrete action, but only a single action is described rather than several specific ones, so it sits at the anchor for 1-2 concrete actions and not the 'several specific actions' anchor above.	3 / 5
Completeness	It explicitly answers what ("Fan-out search across all memory sources when context is unclear") and when ("Triggers on: ... any vague reference to past context that needs resolution before the agent can act") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The phrase "Triggers on: 'from earlier', 'remember when', 'what we discussed', 'that thing with'..." provides comprehensive coverage of natural phrases users actually say when recalling past context, matching the 'comprehensive coverage of natural terms' anchor.	5 / 5
Distinctiveness Conflict Risk	The recall niche is tightly scoped to vague references to past context with very specific trigger phrases ('remember when', 'last session', 'the other day'), giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/recall/SKILL.md
Commit: 7094ced

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.