CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

remember

Use when making a decision, choosing a convention, or learning a lesson that should persist across sessions.

Quality

60%

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 ./skills/remember/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 well-structured, actionable instruction set for a single-purpose slash command, with a concrete file template, output format, and examples. Its main defect is a workflow sequencing contradiction — the duplicate check is documented as a pre-creation step but placed after file creation — plus a couple of unresolved specifics like the <project-hash> placeholder.

Suggestions

Reorder the duplicate check to precede file creation (or fold it into Step 2) so the workflow sequence matches its own 'Before creating a new file' instruction.

Explain how to resolve the <project-hash> placeholder in the memory directory path, or point to how the actual memory directory is located.

Add a one-line example of a MEMORY.md entry format so Step 3 is copy-paste ready, matching the concreteness of the memory-file template.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no explanations of what memory or markdown is, every section carries operational weight. It is not 5 because of small redundancies: Rule 3 ('No duplicates - Update existing if same topic') restates Step 4, and Rule 1 ('structure with Why/How to apply') restates the file template.

4 / 5

Actionability

Concrete, executable guidance throughout: an exact file template with frontmatter fields, a memory directory path, a formatted output block, and worked examples for each memory type. It falls short of 5 because the path '.claude/projects/<project-hash>/memory/' leaves the placeholder unresolved with no instruction for resolving it, and no example entry format is given for the MEMORY.md index.

4 / 5

Workflow Clarity

Four steps are listed, but Step 4 ('Before creating a new file, check if a memory on the same topic already exists') contradicts its own position — it must logically precede Step 2 (Create Memory File), making the sequence incoherent on that point. There is also no validation checkpoint (e.g., confirming the write or index line count), fitting anchor 3 ('sequence present but checkpoints missing or implicit') rather than 4.

3 / 5

Progressive Disclosure

A single self-contained SKILL.md with well-organized sections (Workflow, Output, Examples, Rules) and no external references — appropriate for a skill of this scope, so nothing is wrongly inlined or buried. It does not reach 5 because at ~108 lines it exceeds the simple-skill threshold and has minor organization gaps, e.g., the Rules section duplicating workflow steps instead of consolidating them.

4 / 5

Total

15

/

20

Passed

Description

36%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 functions well as a trigger clause but is half a description: it says when to fire without saying what the skill does. Its trigger vocabulary is decent but misses the most natural user phrasings like 'remember this'. Adding a capability statement and core synonyms would move it from below-midline to solid.

Suggestions

Add a 'what' clause, e.g., 'Saves decisions, conventions, and lessons to persistent project memory files and updates the memory index.'

Include natural trigger synonyms users actually say, such as 'remember this', 'save this preference', or 'keep this for future sessions'.

Mention the concrete artifact (markdown memory file + MEMORY.md index) to differentiate from generic decision-support and the built-in auto-memory behavior.

DimensionReasoningScore

Specificity

The description names its domain concretely ("making a decision, choosing a convention, or learning a lesson that should persist across sessions") but never states any action the skill performs, matching the anchor 'Names the domain but actions are minimal or generic'. It scores above 1 because it is not pure abstract fluff like 'Helps with documents', but below 3 because no capability (e.g., writing memory files or updating an index) is ever mentioned.

2 / 5

Completeness

The description is entirely a 'when' clause ("Use when making a decision...") with no 'what' — the reader cannot tell the skill saves anything to memory. This exactly matches anchor 2 ('only when is present without what', example: 'Use when working with documents'). It is not 3 because the 'what' is not merely weak — it is absent.

2 / 5

Trigger Term Quality

Phrases like "making a decision", "choosing a convention", and "learning a lesson" are terms users would plausibly say, but the most natural invocations ("remember this", "save this preference", "keep this for future sessions") are missing. This fits anchor 3 ('Some relevant keywords but missing common variations or synonyms') rather than 4, which requires only a few missing natural terms.

3 / 5

Distinctiveness Conflict Risk

The qualifier "that should persist across sessions" creates a distinguishable niche, but the broad opening triggers "making a decision" could overlap with planning or decision-support skills, and the description does not mention the memory-file output that would distinguish it from the native auto-memory system. Fits anchor 3 ('Somewhat specific but could still overlap with similar skills') better than 4, which requires only minor overlap with closely related skills.

3 / 5

Total

10

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/specialist-agent

Path

skills/remember/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.