review

Clear due memory reviews with free recall — the two-minute habit that makes learning permanent. Use when reviews are due, or the user wants to review, practice, or "do my engram reviews".

Quality

83%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced protocol with strong validation feedback loops, weakened mainly by verbosity and a monolithic structure that underuses progressive disclosure.

Suggestions

Move the amnesty protocol, the transfer_ready special case, and version-history justifications (v0.8.1, v1.3, v1.4) into a reference file, leaving SKILL.md as a concise overview that links out.

Trim rhetorical flourishes ('a flattering denominator wearing a helpful face', 'streak-as-goal with better manners') and inline research citations to the lean protocol rule each supports.

Consolidate the repeated 'say nothing the hook already said' guidance into a single rule near the top instead of restating it across the amnesty, decay, and close sections.

Dimension	Reasoning	Score
Conciseness	The body is accurate and project-specific (not explaining general concepts Claude knows), but it is heavily padded with rhetorical flourishes, version-history asides, and motivational justifications that could be tightened without losing the protocol.	2 / 3
Actionability	It provides concrete, copy-paste-ready bash commands with all flags (session-start, due --cap, rate --topic ... --rating, edit-node, retire, decay, log-session) plus exact quoted learner lines, giving fully executable guidance.	3 / 3
Workflow Clarity	A clear numbered sequence (§1 load → §2 per-item 1–4 → §3 audit → §4 close) with explicit validation checkpoints (probe-gap check, criterion loop up to 3 passes, assessor audit) and feedback loops (retry without --error-class on version skew, edit-node repair).	3 / 3
Progressive Disclosure	It signals one-level-deep shared references inline (dialogue-grammar.md, problem-grammar.md, subagents.md), but the SKILL.md itself is a ~150-line monolithic block with substantial inline content (amnesty protocol, transfer case, version notes) that could be split into reference files; no bundle files exist to offload into.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 with explicit what-and-when triggers and natural user-language terms; its only weakness is that it names one composite action rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and core action ('Clear due memory reviews with free recall') but frames a single action rather than listing multiple distinct concrete actions, so it falls short of the score-3 anchor.	2 / 3
Completeness	It states what it does (clear due memory reviews via free recall) and gives an explicit 'Use when...' clause with concrete triggers, satisfying both what and when.	3 / 3
Trigger Term Quality	'reviews are due', 'review', 'practice', and the verbatim user utterance 'do my engram reviews' give good coverage of natural terms a learner would actually say.	3 / 3
Distinctiveness Conflict Risk	The engram-specific niche ('engram reviews', 'reviews are due', free-recall retention loop) is clearly bounded and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nagisanzenin/engram
Path: skills/review/SKILL.md
Commit: c576e9b

Reviewed: 4 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.