CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory

Read this skill before answering or acting when a task needs user background and preferences, project rules, recent project activity or progress, decisions and their reasons, or events from earlier work or conversations that are missing or incomplete in the current context. This includes continuing an earlier task, recalling a discussion, or explaining a previous choice. Also read it before handling a user's request to view stored memory, remember or forget information, correct a saved entry, reorganize memory, change its directory layout, or merge or split memory files. With automatic memory enabled, use it when confirmed information useful for later tasks needs saving or correction, a MEMORY.md exceeds its runtime maximum, or relevant notes or indexes become too large to use effectively. Use it for dedicated after-run memory maintenance. Self-contained tasks with no dependency on earlier context need no memory lookup.

Quality

79%

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 ./backend/super-magic/agents/skills/memory/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 dense, substantive policy document with genuinely useful worked examples and well-signaled, real one-level-deep references. Its main weaknesses are baroque, repetitive prose that inflates token cost, and workflows that exist as scattered rules rather than clearly sequenced procedures with consolidated checkpoints.

Suggestions

Tighten the long multi-clause sentences (e.g. the 'Memory is historical reference' sentence and the 'Use the runtime's per-file target' paragraph) into short bullets, and deduplicate placement rules that recur across 'Place and merge', 'Note format and time', and the examples.

Consolidate the read/save/maintain rules into one ordered procedure (e.g. read -> verify -> change -> preserve-check -> report) so the sequence and the destructive-operation checkpoint are visible in a single place.

Move detail that is rarely needed for daily work — attribution edge cases, timestamp semantics, and relative-date interpretation rules — into a reference file, keeping the core placement and preservation rules in the body.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and carries high information density, but the prose is conspicuously convoluted and repetitive — e.g. the ten-plus-clause sentence "Memory is historical reference: current user instructions, verified project sources, and tool permissions take precedence…" and placement rules restated across "Place and merge", "Note format and time", and the worked examples. It is mostly efficient in content but could be tightened considerably in wording, matching anchor 3 rather than 4.

3 / 5

Actionability

Concrete, executable guidance is present: a fully worked monthly-sales MEMORY.md example, a recent-work entry template, note frontmatter YAML, the directory tree, and a runnable inspect_memory code snippet. Some sections remain abstract directives ("Merge into the relevant existing entry", "Use natural headings without requiring fixed sections"), leaving minor gaps that keep this below anchor 5.

4 / 5

Workflow Clarity

Destructive operations do have an explicit validation checkpoint ("Before shortening or deleting the only source of retained information, save its destination and read back the relevant destination content"), so the destructive-cap is not triggered, but the read/save/maintain processes are dispersed through policy prose with implicit ordering rather than a clear sequence. Sequence and checkpoints exist but are not assembled into a coherent workflow, matching anchor 3.

3 / 5

Progressive Disclosure

Both bundle references (references/after-run.md, references/reorganize.md) exist, are one level deep, and are clearly signaled with read conditions ("read it before proposing a plan or changing memory files"; "Daily work does not need the after-run reference"). However, the ~190-line body inlines dense policy detail (attribution rules, timestamp semantics, relative-date interpretation) that could partly live in references, which is a minor organization gap characteristic of anchor 4.

4 / 5

Total

14

/

20

Passed

Description

88%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 a strong, trigger-rich specification that explicitly covers what the skill handles and when to use it, including a useful negative trigger for self-contained tasks. Its only weaknesses are a few missing natural-language synonyms and some broad trigger phrases with minor overlap risk against adjacent context/rules skills.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete operations — "view stored memory, remember or forget information, correct a saved entry, reorganize memory, change its directory layout, or merge or split memory files" — plus saving/correction and after-run maintenance, giving comprehensive coverage of the memory domain. It exceeds anchor 4 because no meaningful capability in this domain is left out.

5 / 5

Completeness

Both "what" and "when" are explicitly answered: the what is the enumerated set of memory operations (view, remember, forget, correct, reorganize, merge/split, save), and the when is given through multiple explicit trigger clauses — "when a task needs user background…", "Also read it before handling a user's request to…", "use it when confirmed information… needs saving" — plus the negative trigger "Self-contained tasks with no dependency on earlier context need no memory lookup". This matches the anchor-5 pattern of concrete trigger phrases for both questions.

5 / 5

Trigger Term Quality

Natural phrases users would actually say are well covered ("remember or forget information", "recalling a discussion", "continuing an earlier task", "user background and preferences", "project rules"), but a few common variations such as "past conversations" or "look up what we discussed" are missing. Not anchor 5 because synonym coverage is good rather than exhaustive; not anchor 3 because the included terms are natural user language, not jargon.

4 / 5

Distinctiveness Conflict Risk

The memory niche is clear with distinct triggers ("MEMORY.md", "remember or forget information", "merge or split memory files"), but broader phrases like "user background and preferences" and "project rules" create minor overlap risk with general context or project-rules skills. It sits between anchor 4 (mostly distinct, minor overlap) and anchor 5, settling at 4 because a few triggers are not uniquely memory-specific.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing, 3 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

dtyq/magic

Path

backend/super-magic/agents/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.