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

68%

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

78%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.

The content is a lean, well-structured workflow with concrete tool calls and clear sequencing, supported by good section organization. It is held back only by minor redundancy in the Rules section and placeholder-based rather than fully copy-paste-ready examples.

Dimension	Reasoning	Score
Conciseness	The body is efficient and largely free of concept over-explanation, but the trailing 'Rules' section restates constraints already implied by the workflow and forbidden_tools, leaving minor trimmable redundancy.	4 / 5
Actionability	Provides concrete tool invocations (file_reader, terminal touch) and an explicit return format, but uses placeholders like <filename> and <Topic Name> rather than fully copy-paste-ready examples.	4 / 5
Workflow Clarity	A clear two-step sequence with an early-exit branch for no matches and a token-limit conditional; minor validation gaps (no confirmation that reads or the touch succeeded) keep it below 5.	4 / 5
Progressive Disclosure	The skill is under ~50 lines, needs no external bundle references, and is organized into clear, well-signaled sections (Available Memory Files, Workflow, Rules); per the simple-skill exception this warrants a 5.	5 / 5
	Total	17 / 20 Passed

Description

58%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.

The description clearly conveys what the skill does through several concrete actions, but omits any explicit "Use when..." trigger guidance and lacks keyword synonyms, capping both completeness and trigger quality. Distinctiveness is reasonably strong given the focused memory-recall niche.

Suggestions

Add an explicit 'Use when...' clause naming the triggering situations (e.g., 'Use when the main agent needs relevant long-term memories for a topic or question').

Include natural synonyms users might say — 'remember', 'past context', 'conversation history' — alongside 'recall' and 'memories'.

Tighten the action list with one more concrete detail (e.g., the return format or the touch/LRU behavior) to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "judges relevance from pre-loaded metadata", "loads only relevant files", "returns a concise summary" — with only minor gaps in coverage; not as comprehensively detailed as a score-5 anchor.	4 / 5
Completeness	The "what" is clearly stated, but there is no explicit "Use when..." trigger clause; per the judging guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant natural keywords ("recall", "long-term memories", "topic or question") but misses common synonyms and variations a user might say ("remember", "history", "past context").	3 / 5
Distinctiveness Conflict Risk	"Recall relevant long-term memories on demand" defines a mostly distinct niche with minor overlap risk; not a clear score 5 because explicit distinct triggers are absent.	4 / 5
	Total	14 / 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: clacky-ai/openclacky
Path: lib/clacky/default_skills/recall-memory/SKILL.md
Commit: db23154

Reviewed: 2 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.