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

81%

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

Quality

Content

80%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 well-structured, highly actionable skill body: concrete commands, exact paths, and excellent progressive disclosure with one verified, clearly signaled reference file. Its weaknesses are a redundant PARA-rules section that repeats the directory tree, and an implicit maintenance workflow lacking validation checkpoints.

Suggestions

Remove or collapse the 'PARA rules' section, since the directory tree's inline comments already state what each PARA category means; keep only the non-obvious rule ('Move to archives when complete').

Add a short numbered maintenance loop with checkpoints, e.g. heartbeat: scan session -> extract durable facts to items.yaml -> verify entity exists (create if 3+ mentions) -> bump access metadata; and weekly: rewrite summary.md -> verify cold facts remain in items.yaml.

State explicitly what to do when qmd is unavailable or the index is stale (fallback to grepping $AGENT_HOME), so recall does not silently fail.

Dimension	Reasoning	Score
Conciseness	The body is lean with concrete paths, a compact directory tree, and punchy rules ('Memory does not survive session restarts. Files do.'). However, the 'PARA rules' section repeats the folder-tree comments almost verbatim (projects=active work, areas=ongoing, resources=reference, archives=inactive), a redundancy that keeps it below anchor 5.	4 / 5
Actionability	Fully executable guidance throughout: copy-paste-ready qmd commands with examples ('qmd query "what happened at Christmas"', 'qmd index $AGENT_HOME'), concrete supersession mechanics ('status: superseded', add 'superseded_by'), explicit entity-creation thresholds (mentioned 3+ times), and exact file paths. Specific examples cover the common cases.	5 / 5
Workflow Clarity	A temporal sequence is present (write daily notes continuously, extract durable facts during heartbeats, rewrite summary.md weekly) but it is implicit rather than clearly sequenced, and there are no validation checkpoints for heartbeat extraction or weekly synthesis. The Planning section's staleness check is the only feedback loop, matching anchor 3 rather than 4.	3 / 5
Progressive Disclosure	The body is a clean overview with a single well-signaled, one-level-deep reference ('For the atomic fact YAML schema and memory decay rules, see references/schemas.md'), which was verified to exist and contains exactly the promised schema and decay rules. Content is appropriately split with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

83%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 strong description: it states what the skill does in third-person imperative form, gives an explicit trigger clause with natural trigger terms, and carves out a distinctive PARA-memory niche. The only gap is a handful of missing everyday synonyms in the trigger list.

Dimension	Reasoning	Score
Specificity	Names the domain ('file-based PARA memory system') and lists three concrete actions ('store, retrieve, and organize durable knowledge') plus concrete artifact types (daily notes, entity records, weekly synthesis). Minor gaps in coverage keep it below anchor 5, which expects comprehensive action detail.	4 / 5
Completeness	Explicitly answers 'what' (PARA file-based memory system for storing, retrieving, and organizing durable knowledge across sessions) and 'when' via a concrete 'Trigger on...' clause with specific trigger phrases, matching the anchor-5 example pattern exactly.	5 / 5
Trigger Term Quality	Trigger list is natural and varied ('saving facts, daily notes, entity records, weekly synthesis, recall, tacit user patterns, or plan memory'), matching phrases a user would actually say. A few common variations ('remember this', 'forget', 'notes') are missing, so it does not reach anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Distinctive niche terms ('PARA', 'tacit user patterns', 'weekly synthesis', 'plan memory') give it a clear identity with minimal conflict risk. Only minor overlap with generic note-taking or journaling skills, so anchor 4 rather than 5.	4 / 5
	Total	17 / 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: paperclipai/paperclip
Path: skills/para-memory-files/SKILL.md
Commit: 1c07b59

Reviewed: 1 day 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.