CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

remember

Store a learning, pattern, or decision in the memory system for future recall

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

Quality

Content

82%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 strongly actionable, project-specific instruction set: exact tool invocation parameters, a priority-ordered type-detection procedure with signal words, and a concrete decomposition pattern. Its main weaknesses are minor redundancy (types table vs. detection rules, one historical note) and absent error-recovery guidance for the MCP call.

DimensionReasoningScore

Conciseness

Nearly all content is project-specific (MCP tool, learning types, signal words) with no explanation of concepts Claude already knows, but the Learning Types table partially duplicates the Auto-Type Detection section and "This replaces the old bash command approach" is historical padding that could be trimmed. Not anchor 3 — there is no whole unnecessary section, only minor tightening opportunities.

4 / 5

Actionability

Fully executable guidance: the exact MCP tool path (mcp__opc-memory__store_learning) with a complete parameter block including defaults, typed invocation examples, per-type signal-word lists for detection, and a concrete decomposition format with example phrasings. Matches the copy-paste-ready, common-cases-covered anchor.

5 / 5

Workflow Clarity

The sequence (parse args, detect type first-match top-to-bottom, decompose vague learnings, call the MCP tool, get confirmation with ID) is clear, with the priority-ordered detection rules acting as an explicit decision procedure. Not anchor 5 because there is no error-recovery guidance if the MCP call fails or returns an error, only an implicit confirmation checkpoint.

4 / 5

Progressive Disclosure

A single flat file with clear section headers, no nested references, and no bundle files; all content is needed on every invocation. Not anchor 5 because the ~40-line auto-type detection catalog could live in a separate reference file to keep SKILL.md lean, and the types table plus detection rules form a minor organization duplication.

4 / 5

Total

17

/

20

Passed

Description

61%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 has a clear, third-person statement of what the skill does with reasonably natural trigger terms, but it lacks any 'when to use' guidance and undersells the skill's concrete capabilities (type detection, typed learnings, confirmation). Adding an explicit 'Use when...' clause with trigger phrases would resolve the completeness cap.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user says remember this, save this learning, or wants a finding stored for future sessions.'

Mention the key capability that distinguishes it — auto-detection of learning type (failed approach, error fix, architectural decision, etc.) — to raise specificity from naming 1-2 actions to listing several.

Include the natural synonym 'remember' since users are more likely to say 'remember this' than 'store a learning'.

DimensionReasoningScore

Specificity

Names the domain ("memory system") and 1-2 concrete actions ("Store a learning... for future recall"), matching the anchor for domain plus 1-2 actions. It stops short of anchor 4 because it lists no additional distinct capabilities (e.g., auto-type detection, tag extraction, typed learnings) that the skill actually performs.

3 / 5

Completeness

The 'what' is clear (store a learning/pattern/decision in memory for recall) but there is no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"learning", "pattern", "decision", "memory", "recall" are natural terms a user would say, giving good keyword coverage. Not anchor 5 because common synonyms like "remember", "note this", or "takeaway" are missing.

4 / 5

Distinctiveness Conflict Risk

The memory-system/learning niche is fairly distinct with specific objects (learning, pattern, decision), so only minor overlap risk with generic note-taking or save-this skills. Not anchor 5 because "store... for future recall" could still catch generic save/remember requests.

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

stephenfeather/opc

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.