para-memory-files

Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions. Trigger on saving facts, daily notes, entity records, weekly synthesis, recall, tacit user patterns, or plan memory.

Quality

73%

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/para-memory-files/SKILL.md

Quality

Content

72%

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

The content is actionable and well-structured with an effective one-level reference split. It loses points on conciseness (one section is repetitive) and workflow clarity (stateful supersede/archive operations lack explicit validation checkpoints).

Suggestions

Tighten the 'Write It Down -- No Mental Notes' section: collapse the five bullets that restate 'write it to a file' into one or two, since they all make the same point.

Add an explicit validation step to the supersede/archive workflow (e.g., 'confirm superseded_by points to an existing fact before marking status: superseded; verify the folder moved before deleting the source').

For weekly summary rewrites, add a brief checklist or verify step (e.g., 'confirm cold facts remain in items.yaml after they drop from summary.md') to make the destructive curation step safer.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with bullets and tight category definitions, but the 'Write It Down -- No Mental Notes' section restates the same idea five ways ('Memory does not survive session restarts. Files do.' plus five bullets) and could be tightened.	2 / 3
Actionability	Provides concrete executable guidance: directory layout, file conventions (summary.md, items.yaml), specific qmd commands (qmd query/search/vsearch), and concrete rules (status: superseded, add superseded_by) -- specific and copy-ready rather than pseudocode.	3 / 3
Workflow Clarity	Multi-step flows are described (extract facts during heartbeats, weekly summary rewrite, supersede-then-archive), but there are no explicit validation checkpoints for stateful/irreversible operations like superseding facts or moving folders to archives.	2 / 3
Progressive Disclosure	A clear overview with one well-signaled, one-level-deep reference ('see references/schemas.md'), and that file exists and holds the schema/decay detail appropriately split out of SKILL.md.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 and when to trigger it with an explicit trigger clause, giving strong completeness and distinctiveness. Specificity and trigger-term quality are solid but slightly held back by somewhat technical phrasing rather than the most natural user terms.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('store, retrieve, and organize durable knowledge'), but does not enumerate many distinct concrete actions like the score-3 example; it is comprehensive but not exhaustive.	2 / 3
Completeness	Explicitly answers both 'what' (file-based PARA memory system to store/retrieve/organize) and 'when' with an explicit 'Trigger on...' clause, matching the score-3 anchor structure.	3 / 3
Trigger Term Quality	Includes an explicit 'Trigger on' list (saving facts, daily notes, weekly synthesis, recall, tacit user patterns, plan memory), but several terms like 'tacit user patterns' and 'entity records' are technical rather than the natural phrases a user would say.	2 / 3
Distinctiveness Conflict Risk	'PARA memory system' is a clear niche with distinct, specific triggers unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 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: paperclipai/paperclip
Path: skills/para-memory-files/SKILL.md
Commit: 14f20be

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.