CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

engram-memory

ALWAYS ACTIVE — Selective persistent memory: preserve verified, durable knowledge worth reconstructing, with safe topic updates and host-owned lifecycle.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/codex/skills/memory/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

This is a strong, well-engineered protocol: lean and imperative, with concrete tool-level guidance and genuinely rigorous validation loops around the risky operations (topic overwrite, duplicate saves, failed lookups). The only real improvement levers are tightening a few redundant passages and moving host-binding internals out of the main file.

DimensionReasoningScore

Conciseness

The body is a dense, imperative protocol that assumes Claude's competence and explains no known concepts; only minor trims are possible (redundant emphasis in AFTER COMPACTION — 'IMMEDIATELY call' plus 'Do not skip step 1' plus the loss explanation — and the Codex session-binding section restating identity rules twice).

4 / 5

Actionability

Concrete guidance throughout: exact tool names, a field-by-field mem_save format with examples, numbered search and compaction sequences, and a runnable fallback command ('engram setup codex'). Minor gaps keep it from 5: no worked example of a complete mem_save call and fuzzy conditions like 'significant explicit closure'.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with explicit validation and error recovery: search-before-write, full read with mem_get_observation before update, 'On ambiguous identity or failed lookup, do not overwrite', 'If memory work fails... still send the answer', and a concrete repair path when tools are unavailable. The topic-update flow is a checklist with feedback loops for the write path, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist; all content lives in one well-sectioned ~110-line file with clear headers, which is defensible for an always-active protocol. However, detail-heavy material like the Codex session-binding internals could sit in a reference file, leaving minor organization gaps rather than the fully split structure of a 5.

4 / 5

Total

17

/

20

Passed

Description

62%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, third-person, and answers both what and when (via 'ALWAYS ACTIVE'), but its capability list is thin relative to what the skill actually does and it omits the natural trigger phrases users would say when needing memory recall. It is serviceable but under-sells the skill's coverage.

Suggestions

List more of the skill's concrete capabilities in the description (e.g., search/recall of past work, session summaries, recovery after context compaction) to lift specificity.

Add natural trigger terms users would actually say ('remember', 'recall', 'what did we do', 'how did we solve') so the description matches real recall requests even though the skill is always-active.

Mention the memory system by name (Engram) or a distinguishing feature to further reduce overlap with generic memory/notes skills.

DimensionReasoningScore

Specificity

The description names the domain ('Selective persistent memory') and 1-2 concrete actions ('preserve verified, durable knowledge', 'safe topic updates'), but 'worth reconstructing' and 'host-owned lifecycle' are design principles rather than actions, and capabilities the body actually covers (search/recall, session summaries, compaction recovery) are omitted.

3 / 5

Completeness

Both 'what' (selective preservation, topic updates, lifecycle) and 'when' ('ALWAYS ACTIVE', an explicit activation clause equivalent to 'Use when...') are present, but the 'when' is a blanket always-on statement without concrete trigger phrases, so it is not a 5.

4 / 5

Trigger Term Quality

'persistent memory' and 'knowledge' are relevant keywords, but the natural phrases a user would actually say ('remember', 'recall', 'what did we do') and their variations are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

'Selective persistent memory' with topic-update and host-lifecycle semantics carves a mostly distinct niche with only minor overlap risk against other memory/notes skills; it is more specific than a bare domain claim (3) but lacks distinct named triggers for a 5.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Gentleman-Programming/engram

Path

plugin/codex/skills/memory/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.