Tessl • The package manager for agent skills

SkillPublic

mnemos

Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies

Quality

75%

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/mnemos/SKILL.md

Quality

Content

82%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 CLI commands and clearly sequenced hook/workflows, and it stays lean by explaining only skill-specific concepts. The main gap is the absence of explicit validation checkpoints after destructive consolidation and the lack of any external reference files for a complex skill.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich, explaining only skill-specific concepts (fatigue, haziness) rather than general ones Claude already knows; minor padding in the three-layer defense prose. Not 5 because a few sections (post-compaction narrative, ingestion details) could be tightened.	4 / 5
Actionability	Provides a copy-paste-ready CLI block, a concrete numbered hook sequence, and specific commands like 'mnemos add goal "..." --task-id session-1' covering the common cases. Not below 5 because the guidance is fully executable.	5 / 5
Workflow Clarity	Clear numbered sequences (hooks 1-7, three-layer recovery, 5-step agent workflow) with the fatigue-state table acting as a monitoring feedback loop. Not 5 because there is no explicit validate-after-consolidation checkpoint for the evicting/compressing operations; not 3 because the fatigue thresholds supply checkpoints.	4 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-sectioned with one-level-deep structure and clear navigation. Not 5 because a skill this complex inlines fatigue/ingestion/iCPG detail that could live in separate reference files; not 3 because organization is genuinely good.	4 / 5
	Total	17 / 20 Passed

Description

58%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 is specific and distinctive about its mechanism but is written in heavy jargon and omits any explicit 'when to use' trigger guidance, capping completeness and trigger-term quality. Adding a natural-language Use-when clause would lift the two lowest dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when you need durable working memory across context compactions — to checkpoint decisions, preserve task handoffs, or audit what was remembered.'

Soften jargon with natural synonyms users would actually say ('context window', 'session memory', 'handoff') alongside 'MnemoGraph' and 'eviction policies'.

State 1-2 concrete user-facing actions (e.g. 'checkpoint decisions', 'resume tasks after compaction') to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete mechanism — 'typed MnemoGraph', 'distinct node types', 'per-type eviction policies' — listing several specific concepts rather than vague abstractions. Not 5 because it is framed as one compound mechanism rather than multiple discrete actions.	4 / 5
Completeness	Gives a clear 'what' (task-scoped memory lifecycle that prevents lossy compaction) but no 'Use when...' trigger clause; per the guidelines a missing explicit trigger caps completeness at 3. Not 4 because 'when' is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	Terms like 'MnemoGraph', 'eviction policies', and 'node types' are jargon-heavy; natural user phrases ('memory', 'context window', 'session handoff') are thin and synonyms are missing. Not 4 because common variations a user would actually say are largely absent.	3 / 5
Distinctiveness Conflict Risk	The MnemoGraph / typed-eviction construct is a clear niche unlikely to trigger for unrelated skills. Not 5 because there is minor overlap risk with general memory/context-tracking skills.	4 / 5
	Total	14 / 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: alinaqi/maggy
Path: skills/mnemos/SKILL.md
Revision: 55aabe2

Reviewed: 20 days 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.

mnemos

Table of Contents

Is this your skill?