memory-tasks

Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform notes queryable through the knowledge graph.

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/memory-tasks/SKILL.md

Quality

Content

80%Weight 40%Scale 1-3

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

The content is highly actionable and concise, with executable code and clear sectioning, but it does not fully capitalize on progressive disclosure (inline reference material) and omits validation checkpoints inside its batch task workflows.

Suggestions

Add an explicit validation checkpoint to the Pre-Compaction Flush and Resuming workflows (e.g., 'Run schema_validate(noteType="Task") after updating to confirm no task is malformed').

Move the full Task schema YAML and the query reference table into a references/ file (e.g., TASK_SCHEMA.md), keeping SKILL.md a concise overview with one-level-deep links.

Tighten the schema section by showing only the field list inline and linking to the full schema note path.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized — code blocks, a query table, and guidelines — without explaining concepts Claude already knows; the one apparent duplication (frontmatter vs observations) is explicitly justified, so tokens earn their place.	3 / 3
Actionability	Provides fully executable, copy-paste-ready guidance — a complete write_note(...) call with kwargs, concrete search_notes filters, and a query table with specific metadata_filters — matching the anchor for specific, executable examples.	3 / 3
Workflow Clarity	Multi-step flows (resume, pre-compaction flush, updating) are clearly numbered and sequenced, but the batch flush/update operations lack an embedded validation checkpoint (schema_validate appears only in the query table, not as a workflow step), which caps workflow clarity at 2 per the feedback-loop guidance.	2 / 3
Progressive Disclosure	No bundle files exist, so it is a single well-sectioned file, but at ~155 lines it inlines reference-grade material (the full schema YAML and the query reference table) that could live in a separate reference file, fitting the 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 is specific and distinct, naming concrete create/track/resume actions and carving a clear niche around context-compaction survival. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which leaves the 'when to use' dimension only implied.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when starting multi-step work that may outlast the context window, or when resuming tasks after compaction').

Replace internal jargon like 'BM's schema system' and 'uniform notes queryable through the knowledge graph' with natural user-facing terms to improve trigger-term coverage.

Lead with the most common user phrasing (e.g., 'track tasks across compaction') before the schema-mechanism detail.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create, track, and resume structured tasks' — matching the anchor for listing several specific concrete actions rather than naming a domain with only some actions.	3 / 3
Completeness	It clearly states what the skill does (create/track/resume tasks) but provides no explicit 'Use when...' trigger clause, so 'when' is only implied — which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	'Task management' and 'context compaction' are reasonably natural, but 'Basic Memory schemas', 'BM's schema system', and 'uniform notes queryable through the knowledge graph' lean internal/technical and miss common user variations, so it does not reach full natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	The niche (Basic Memory schema-backed tasks surviving context compaction) is specific with distinct triggers and is unlikely to fire for unrelated 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: basicmachines-co/basic-memory
Path: skills/memory-tasks/SKILL.md
Commit: cb95e59

Reviewed: 11 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.