CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ac-memory-manager

Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is ac-memory-manager in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a clean, correctly progressive-disclosed overview: executable Quick Start verified against the real bundle script, with details delegated one level deep. Its weaknesses are minor — a redundant Purpose/Integration repetition and a Quick Start that skips the initialize() call required for cross-session retrieval.

Suggestions

Add 'await memory.initialize()' to the Quick Start between construction and store/retrieve so persisted memories actually load.

Collapse the redundant Purpose and Integration sections into one line (they restate the opening sentence) and use the freed space to note retrieve()'s return type.

Show one line on how memory_type (episodic/semantic/procedural) is passed to store(), since the Memory Types section otherwise has no actionable connection to the API.

DimensionReasoningScore

Conciseness

The body is lean with a useful Quick Start, but the opening line ("Manage persistent memory using Graphiti for cross-session knowledge"), the Purpose section, and the Integration section repeat the same idea three times. Minor redundancy that could be trimmed keeps it at anchor 4 rather than 5.

4 / 5

Actionability

The Quick Start is real executable code matching the actual API in scripts/memory_manager.py (verified: MemoryManager(project_dir), await store(key, value), await retrieve(query)). Not a 5 because it omits the required 'await memory.initialize()' (so prior memories never load, defeating the cross-session purpose) and doesn't show that retrieve() returns a list of entries.

4 / 5

Workflow Clarity

As a simple single-purpose skill, the instantiate -> store -> retrieve sequence is unambiguous. The skipped initialize() step is a real gap in the sequence (retrieval works but returns empty across sessions), so it sits at anchor 4 (clear sequence, minor gaps) rather than 5.

4 / 5

Progressive Disclosure

A short, well-sectioned body with one clearly signaled, one-level-deep bundle reference ("See scripts/memory_manager.py for full implementation" — the file exists and contains the full implementation). Content is appropriately split between the inline overview and the script, matching the anchor-5 structure and the small-skill guidance.

5 / 5

Total

17

/

20

Passed

Description

76%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 clearly and explicitly states both capability and trigger conditions with a well-defined niche. Its main weakness is trigger vocabulary: it relies on domain jargon ("episodic memory", "Graphiti") over the natural phrases a user would say, costing trigger-term quality.

Suggestions

Add natural-language synonyms users would actually say to the 'Use when' clause, e.g. 'remembering', 'recalling', or 'persisting knowledge across sessions'.

Make the action objects slightly more concrete (e.g. 'store and retrieve key-value learnings tagged episodic/semantic/procedural') to reduce overlap with generic knowledge-base skills.

Mention the persistence format or location (e.g. 'backed by Graphiti + LadybugDB') so the scope of 'manage' is unambiguous.

DimensionReasoningScore

Specificity

Names several specific actions ("storing/retrieving knowledge", "managing Graphiti integration", "persisting learnings", "accessing episodic memory") plus the domain (persistent memory for autonomous coding). Not a 5 because the action objects remain abstract ("knowledge", "learnings") compared to fully concrete, comprehensive coverage; not a 3 because more than 1-2 actions are enumerated.

4 / 5

Completeness

Explicitly answers both: what ("Manage persistent memory for autonomous coding") and when ("Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory") with four concrete trigger phrases, matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Relevant keywords exist ("storing/retrieving knowledge", "Graphiti", "persisting learnings", "episodic memory") but common natural variations users would actually say are missing ("remember", "recall", "save memory", "cross-session", "memory across sessions"). Not a 4 because the coverage leans on domain jargon rather than natural phrases.

3 / 5

Distinctiveness Conflict Risk

The Graphiti/episodic-memory framing carves a clear niche with distinct triggers, but generic phrases like "storing/retrieving knowledge" could overlap with general memory or knowledge-base skills. Not a 5 due to that residual overlap risk; not a 3 because the core triggers are firmly tied to this skill's domain.

4 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

fernandezbaptiste/Skrillz

Path

.claude/skills/ac-memory-manager/SKILL.md

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.