remember

Store a learning, pattern, or decision in the memory system for future recall

Quality

64%

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/remember/SKILL.md

Quality

Content

75%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 body is highly actionable with concrete MCP tooling and a clear classification procedure, well-organized into sections. Its main weakness is conciseness: duplicated framing and a heavy repeated rule format add tokens that could be trimmed.

Suggestions

Remove the duplicated opening line under the H1 and the 'What It Does' list, which overlaps the Execution section.

Compress the 7-rule auto-type detection into a compact table (type | test | signal words) to cut the repeated Test/Signal-words/arrow scaffolding.

Drop the obsolete 'This replaces the old bash command approach' line, which references a prior implementation no longer relevant to execution.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient operational guidance without explaining concepts Claude already knows, but the duplicated opening line, the 'What It Does' list overlapping the Execution section, and the heavy repeated Test/Signal-words/arrow format across 7 rules could be tightened. Not a 4 because several trimmable redundancies remain.	3 / 5
Actionability	Provides the exact MCP tool name, fully specified parameters with example values, concrete invocation examples, and a deterministic classification procedure — copy-paste ready and covering common cases, matching the 'fully executable' anchor.	5 / 5
Workflow Clarity	The single store action is unambiguous with an ordered top-to-bottom type-detection procedure and a decomposition pre-check; no validation checkpoint is needed for a non-destructive single store. Not a 5 because the procedure lacks an explicit confirmation/feedback checkpoint after storage.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections and is self-contained with no nested or broken references (no bundle files present), matching the 'good structure, minor organization gaps' anchor. Not a 5 because the 7-rule detection block and decomposition guidance are somewhat dense inline for a >50-line skill.	4 / 5
	Total	16 / 20 Passed

Description

53%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 states what the skill does but omits any 'when to use it' guidance, which caps completeness and limits trigger-term quality. It is specific to the memory niche but would benefit from natural trigger phrases.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user wants to save a learning, pattern, or decision for future recall') to satisfy the 'when' and lift completeness above 3.

Include natural trigger terms users would actually say ('remember this', 'save this learning', 'note this pattern') to improve trigger term quality.

Name additional concrete actions beyond 'store' (e.g., 'classify, tag, and store') to raise specificity toward multiple specific actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('memory system') and one concrete action ('Store') with content types ('learning, pattern, or decision'), but does not list multiple specific actions, matching the '1-2 concrete actions, not comprehensive' anchor. Not a 4 because it stops at a single action rather than several specific ones.	3 / 5
Completeness	Provides a clear 'what' ('Store a learning, pattern, or decision in the memory system') but no 'when' / 'Use when...' clause, so per the boundary guidance completeness is capped at 3. Not a 4 because trigger guidance is entirely missing rather than merely weak.	3 / 5
Trigger Term Quality	Contains relevant keywords ('learning', 'pattern', 'decision', 'memory') but omits natural phrases a user would actually say ('remember this', 'save this'), matching the 'some relevant keywords but missing variations' anchor. Not a 4 because common natural trigger phrasings are absent.	3 / 5
Distinctiveness Conflict Risk	The memory-storage niche is mostly distinct with only minor overlap risk against other memory-related skills, matching the 'mostly distinct; minor overlap' anchor. Not a 5 because the absence of explicit triggers leaves some ambiguity about when it should fire.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: stephenfeather/opc
Path: skills/remember/SKILL.md
Commit: 948072f

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.