Tessl • The management layer for AI agent skills

SkillPublic

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

78%

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 ./lib/clacky/default_skills/recall-memory/SKILL.md

Quality

Content

85%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 tight, actionable, well-structured instruction body: the workflow is unambiguous with concrete tool calls, an early-exit condition, and an exact output format. The only improvement space is removing the small rule duplication between the workflow and the Rules section.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes competence, and explains nothing Claude already knows; the only bloat is the duplicated irrelevant-file rule appearing in both Step 1 ('Do NOT load files that are clearly irrelevant') and the Rules section ('NEVER load irrelevant files').	4 / 5
Actionability	Concrete, executable guidance throughout — exact file_reader and terminal commands, an explicit no-match response string, and a verbatim return-format template; minor gaps remain (e.g., how the task/topic is passed in is not specified).	4 / 5
Workflow Clarity	A clear two-step sequence with an explicit early-exit checkpoint ('If nothing matches, immediately return...') and a hard stop ('Stop immediately after returning the summary'); the operation is read-only so no validation loop is required.	5 / 5
Progressive Disclosure	A single-file, ~50-line skill with well-organized sections and no content that belongs in external reference files, satisfying the rubric's simple-skill exception for a top progressive-disclosure score.	5 / 5
	Total	18 / 20 Passed

Description

63%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 specific, well-voiced description of what the skill does, with concrete actions and a distinct memory-recall niche. Its main weakness is the complete absence of when-to-use trigger guidance and natural synonyms, which limits discoverability.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the main agent needs past context, prior decisions, or previously learned facts about a topic or question.'

Include natural user-facing synonyms such as 'remember', 'recall', 'long-term memory', and 'past conversations' to improve trigger-term coverage.

Clarify when this skill applies versus other memory or search skills (e.g. 'for retrieving stored memories, not for writing new ones') to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions covering the full workflow — 'judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent' — comprehensive for the capability, matching the anchor for multiple specific concrete actions.	5 / 5
Completeness	The 'what' is clear and specific (judge relevance, load relevant files, return a concise summary), but there is no 'Use when...' clause or any trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Keywords like 'long-term memories' and 'recall' are relevant, but common natural variations users would say ('remember', 'past conversations', 'what do you know about') are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Recall relevant long-term memories on demand' carves a mostly distinct niche with clear subject matter, though it could minorly overlap with other memory- or search-related skills.	4 / 5
	Total	15 / 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
Revision: e7b898f

Reviewed: 1 month ago

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.

recall-memory

Table of Contents

Is this your skill?