CtrlK
BlogDocsLog inGet started
Tessl Logo

add-mnemon

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

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

88%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 content is a tightly written, fully executable install procedure with explicit validation checkpoints and error-recovery troubleshooting, scoring top marks on actionability and workflow clarity. The only soft spots are minor conciseness trims and the progressive-disclosure ceiling from keeping a longer procedure in one file.

DimensionReasoningScore

Conciseness

The body is efficient with mostly purposeful prose (idempotency notes, stderr-routing rationale, provider logic), but a few explanatory sentences could be trimmed, landing between the lean 5-anchor and the mostly-efficient 3-anchor.

4 / 5

Actionability

Guidance is fully executable and copy-paste ready throughout — grep checks, a complete Dockerfile ARG/RUN/ENV block, the entrypoint diff, build and smoke-test commands, and docker exec/docker logs verification — matching the 'fully executable; copy-paste ready' anchor.

5 / 5

Workflow Clarity

Clear phased sequence (Pre-flight, Apply, Restart/Verify, Troubleshooting) with explicit validation checkpoints — 'rebuild and smoke-test', 'Confirm mnemon hooks are registered', 'Test memory recall' — plus troubleshooting feedback loops for error recovery, matching the 5-anchor.

5 / 5

Progressive Disclosure

Single-file guide with well-organized section headers and no nested/deep references; good structure and easy header-based navigation, but at ~170 lines it is longer than the under-50-line case the 5-anchor's 'appropriately split' bar presumes, so it sits at 'good structure; minor organization gaps'.

4 / 5

Total

18

/

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 concise and states concrete capabilities with a clear niche, but it omits any 'Use when...' trigger guidance, which caps both completeness and trigger-term quality. Adding explicit when-to-use phrasing would lift the lower dimensions.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user wants the agent to remember context across sessions or mentions persistent memory, mnemon, or recall.'

Broaden trigger keywords with natural synonyms users would say — 'past sessions', 'conversation history', 'context across restarts' — in addition to memory/recall/remember.

Keep the third-person action voice but consider naming the integration target (NanoClaw / Claude Code agent containers) to sharpen distinctiveness against general memory tools.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Add persistent graph-based memory', 'recall past context before responding', 'remember insights after each turn' — which matches the 'several specific actions; minor gaps' anchor rather than the fully comprehensive 5-anchor example.

4 / 5

Completeness

The 'what' is clear (add persistent memory, recall before responding, remember after each turn) but the 'when' is entirely missing — there is no 'Use when...' clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms like 'memory', 'recall', and 'remember' are present, but common variations/synonyms (context, history, past sessions) are missing and there is no explicit 'Use when...' framing to surface triggers.

3 / 5

Distinctiveness Conflict Risk

The 'graph-based memory via mnemon' niche is mostly distinct with low overlap risk, but the lack of explicit trigger phrases keeps it just short of the 5-anchor's clear-niche-with-distinct-triggers bar.

4 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
nanocoai/nanoclaw
Reviewed

Table of Contents

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.