add-mnemon

Add persistent graph-based memory via mnemon. Agents recall past context before responding and remember insights after each turn.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-mnemon/SKILL.md

Quality

Content

92%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 body is a strong, executable runbook with clear phased sequencing and validation throughout; its only weakness is monolithic inline content plus referenced test files that are not actually bundled.

Suggestions

Move the integration tests into a `references/` or `scripts/` bundle and link to them so the cited `cp` source paths exist in the skill bundle.

Consider extracting the lengthy Troubleshooting section into a one-level-deep reference to slim the main SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The body is command- and snippet-driven with only domain-specific prose (NanoClaw provider behavior, stderr routing rationale) that Claude would not already know; it does not pad with general concepts, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	It provides fully executable, copy-paste-ready bash/Dockerfile snippets (version check, install layer, entrypoint wiring, build and smoke-test, verification commands), matching the 'fully executable code/commands' anchor rather than the pseudocode level below.	3 / 3
Workflow Clarity	Three phases with numbered steps and explicit validation checkpoints (idempotency grep checks, `mnemon --version` smoke test, docker logs/exec hook verification, troubleshooting feedback loop) match the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	The skill is well-sectioned but monolithic (~175 lines) with no one-level-deep references, and the test files it cites (`.claude/skills/add-mnemon/mnemon-*.test.ts`) are not present as bundle files, so it sits at 'some structure but could be better organized' rather than a clean split.	2 / 3
	Total	11 / 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 distinctive about what mnemon does and how agents use memory, but it omits explicit "Use when..." trigger guidance and leans on jargon/proper nouns rather than natural user phrasings.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when an agent group should remember context across sessions or recall earlier conversation insights.'

Replace or supplement jargon like 'graph-based memory' and the 'mnemon' proper noun with user-facing phrasings such as 'persistent memory' and 'remember across sessions/restarts'.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Add persistent graph-based memory via mnemon", "recall past context before responding", "remember insights after each turn" — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 ('Has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	Terms like "persistent memory", "recall past context", and "remember insights" are relevant, but "mnemon" and "graph-based memory" are jargon/proper nouns a user would not naturally say, and common phrasings like "remember across sessions" are absent — the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche (persistent agent memory via mnemon) with triggers unlikely to overlap with unrelated skills, matching the 'clear niche with distinct triggers' anchor; it is not the level below because it is not merely 'somewhat specific but overlapping'.	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: nanocoai/nanoclaw
Path: .claude/skills/add-mnemon/SKILL.md
Commit: 641963c

Reviewed: 6 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.