Name: save-learning
Rating: 70.39999999999999 (1 reviews)
Author: caliber-ai-org

save-learning

Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in the future.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is save-learning in caliber-ai-org/ai-setup

Quality

Content

93%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.

An exemplary simple instruction-only skill: terse, fully actionable commands with worked examples and clear step sequencing. The only improvement area is adding a light verification step after running the save command to close the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient: a short intro, five numbered steps, a compact type-prefix list, and three brief worked examples with no padding or explanation of concepts Claude already knows, so every token earns its place.	5 / 5
Actionability	Guidance is fully executable: copy-paste-ready commands (`caliber learn add "<refined learning>"`, the `--personal` variant, `git add CALIBER_LEARNINGS.md`) and complete worked examples covering convention and preference cases.	5 / 5
Workflow Clarity	The five-step sequence is clear with an explicit user-confirmation checkpoint before saving, but there is no post-run validation or error-recovery feedback loop (e.g., checking that the learning was added or handling command failure), which keeps it below the top anchor.	4 / 5
Progressive Disclosure	This is a short (~56-line) single-purpose skill with no bundle files and no need for external references; its well-organized sections (Instructions, Examples, When NOT to trigger) provide clean navigation, satisfying the simple-skill exception.	5 / 5
	Total	19 / 20 Passed

Description

78%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.

A strong description that clearly states what the skill does and provides explicit, natural 'Use when' triggers. The main gaps are modest: only a couple of concrete capabilities are named and a few common trigger variants (e.g., "save this", "going forward") are missing.

Suggestions

Add one or two more concrete actions to the description, e.g. refining instructions into typed learning bullets or distinguishing personal vs. project-level saves, to lift specificity.

Include additional natural trigger variants such as "save this", "going forward", or "keep doing X" to broaden trigger-term coverage.

Tighten the broad clause "any instruction they want persisted across sessions" toward explicit persistence-trigger language to further reduce overlap with general memory skills.

Dimension	Reasoning	Score
Specificity	"Saves user instructions as persistent learnings for future sessions" and "Proactively suggest" name the domain with about two concrete actions, but do not list the several specific operations (refine into typed bullets, confirm, stage the learnings file) that would anchor a 4.	3 / 5
Completeness	Explicitly answers both what ("Saves user instructions as persistent learnings for future sessions") and when ("Use when the user says 'remember this'..." with concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Quotes four natural user phrases ("remember this", "always do X", "from now on", "never do Y") plus "preference, convention, or rule", but omits common variants like "save this" or "going forward" that appear in the skill body itself, fitting the 'good coverage, a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The persist-learning niche with quoted trigger phrases is mostly distinct, but "any instruction they want persisted across sessions" and proactive suggestion of preferences leave minor overlap risk with memory/config-style skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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: caliber-ai-org/ai-setup
Path: .agents/skills/save-learning/SKILL.md
Commit: f5dbc00

Reviewed: 14 days ago

Table of Contents

Discovery Implementation Validation

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.