recall-memory

Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./lib/clacky/default_skills/recall-memory/SKILL.md

Quality

Content

85%

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

The content is well-structured and highly actionable, with concrete tool calls, an explicit return format, and a clear sequenced workflow for a simple read-only task; the only slack is minor redundancy between the workflow and the trailing Rules section.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the trailing "## Rules" section duplicates guidance already stated in the workflow (NEVER modify, NEVER load irrelevant files), so it could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready tool invocations — file_reader(path: …) and terminal(command: "touch …") — plus an explicit return-content template, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Clear two-step sequence with an explicit early-exit checkpoint ("If nothing matches, immediately return") and a hard terminator ("Stop immediately after returning"); as a simple read-only task this meets the bar.	3 / 3
Progressive Disclosure	A ~50-line single-file skill with no need for external references, organized into clearly labeled sections (Workflow, Rules, Available Memory Files), satisfying the simple-skill allowance.	3 / 3
	Total	11 / 12 Passed

Description

60%

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

The description is specific and action-oriented, clearly conveying what the skill does, but it lacks an explicit "Use when…" trigger clause and a broad set of natural trigger terms, capping completeness and distinctiveness at 2.

Suggestions

Add a "Use when…" clause naming the situations that should activate this skill (e.g., "Use when the main agent needs relevant long-term memories for a topic or question"), which lifts completeness to 3.

Broaden trigger terms with natural phrasings users would say — "remember", "recall", "past context", "long-term memory", "what we discussed before" — to improve trigger_term_quality.

Tighten distinctiveness by pairing the memory-recall niche with an explicit activation trigger so it is unlikely to fire for unrelated file-reading or search skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "judges relevance from pre-loaded metadata", "loads only relevant files", "returns a concise summary" — matching the multi-action anchor rather than the single-domain score 2.	3 / 3
Completeness	Clearly states what the skill does, but there is no "Use when…" clause or equivalent explicit trigger guidance, which the guideline caps at 2.	2 / 3
Trigger Term Quality	Contains relevant natural terms ("memories", "recall") but no enumerated trigger phrases, and phrases like "pre-loaded metadata" lean technical, so coverage of natural variations is incomplete.	2 / 3
Distinctiveness Conflict Risk	The "long-term memories" niche is somewhat specific, but without explicit trigger guidance it could still overlap with general memory tooling rather than occupying a clearly distinct activation slot.	2 / 3
	Total	9 / 12 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: clacky-ai/openclacky
Path: lib/clacky/default_skills/recall-memory/SKILL.md
Commit: 4aea278

Reviewed: 4 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.