agent-carnet

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

Quality

86%

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

Quality

Content

86%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.

A well-structured, executable CLI skill body with strong actionability and exemplary progressive disclosure. The only friction is mild restatement of the use-signal semantics across sections.

Suggestions

Consolidate the weak-vs-strong signal / last_used bumping rules into one canonical location (Hard rules) and reference it from the other sections instead of restating.

Add a one-line pre-check before `agent-carnet rm` (e.g. confirm the path with `agent-carnet show` first) to make the destructive step's validation explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the weak-vs-strong use-signal and "show bumps last_used" semantics are restated across the Quick reference, "When to call used", and "Hard rules" sections — minor trimming opportunity.	4 / 5
Actionability	The Quick reference gives copy-paste-ready bash with real arguments, flags, tags, and paths covering save/find/list/show/used/move/rm, plus a pointer to per-subcommand `-h` help.	5 / 5
Workflow Clarity	Clear when-to-save/recall/used decision guidance with explicit signal semantics; destructive `rm` is mitigated by the 7-day `.trash/` safety net and `--yes` gate, leaving only minor explicit-validation gaps.	4 / 5
Progressive Disclosure	A focused overview with a "When to read references/" table mapping specific conditions to one-level-deep, real reference files (cookbook.md, frontmatter.md) and an explicit "do not read references/ speculatively" guard.	5 / 5
	Total	18 / 20 Passed

Description

86%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, trigger-rich description that clearly states capability and activation conditions with natural user phrases. Its only real weakness is the second-person voice, which costs it on specificity.

Suggestions

Rewrite in third person (e.g. "Saves, recalls, finds, and organizes notes…") to recover the specificity point lost to the voice penalty.

Tighten "organize notes" to a more concrete verb (e.g. "categorize" or "group notes by category") to lift specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names four concrete actions ("save, recall, find, or organize notes"), but the second-person imperative "Use this skill when the user asks…" triggers the voice penalty, reducing the baseline 4 by one.	3 / 5
Completeness	Explicitly answers both what (save/recall/find/organize notes) and when, with a "Use this skill when…" clause, a concrete "Triggers on…" list, and proactive-use guidance.	5 / 5
Trigger Term Quality	"Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'" gives comprehensive coverage of natural phrases a user would actually say, including synonyms.	5 / 5
Distinctiveness Conflict Risk	The "carnet"/notebook framing and "find in carnet" trigger carve a clear niche, though "remember this"/"save this" carry minor overlap with general memory skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: yamadashy/repomix
Path: .agents/skills/agent-carnet/SKILL.md
Commit: c898ff0

Reviewed: about 14 hours 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.