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

81%

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

81%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 content is a strong, highly actionable workflow with clear sequencing and robust validation/feedback loops for a schedule-mutating batch operation. Its main liability is conciseness: scattered version tags and lengthy rationale asides add token weight that could be consolidated, and some inlined protocols could be factored into the referenced shared files.

Suggestions

Consolidate the inline version annotations (v1.3, v1.14, v0.8.1, issue #13, etc.) into a single 'Version notes / changelog' or 'Deprecated behavior' section so they stop penalizing conciseness throughout the body.

Factor the long amnesty-protocol and transfer-probe subsections into referenced files (e.g., docs/05, docs/07) with a one-line pointer, leaving the SKILL.md body a leaner overview.

Trim parenthetical evidence citations to the single most decision-relevant clause per rule, keeping the behavioral instruction foregrounded.

Dimension	Reasoning	Score
Conciseness	The body is dense with actionable specifics rather than basic-concept padding, but it carries pervasive inline version annotations (v1.3, v1.14, v0.8.1, issue #13) and long parenthetical rationale asides that the rubric flags as version-noise/verbosity and could be tightened or moved to a changelog section.	3 / 5
Actionability	It provides copy-paste-ready, fully specified bash commands throughout (engine-resolution block, session-start/stash/due/rate/decay/retire/edit-node/log-session) with flags and placeholders explained, covering the common review cases — matching the fully-executable anchor.	5 / 5
Workflow Clarity	A clearly sequenced four-phase process (Load queue → Per-item retrieval with ordered steps 1-4 → Assessor audit → Close) with explicit validation checkpoints (confidence before reveal, probe-gap check, assessor audit) and feedback loops (criterion re-ask up to 3 passes, version-skew retry, fail-closed engine handling) for a batch/schedule-mutating operation.	5 / 5
Progressive Disclosure	Good section structure with clearly signaled one-level-deep references to shared files (dialogue-grammar.md, problem-grammar.md, subagents.md, docs/05, docs/16), deferring heavy grammar to those files; minor gaps are that several substantial protocols (amnesty, transfer probe, concept discrimination) are inlined rather than split out, and the referenced files live outside this skill's own bundle (no local references/scripts/assets present).	4 / 5
	Total	17 / 20 Passed

Description

82%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 is well-formed: third-person imperative voice, explicit 'Use when' trigger guidance, a quoted verbatim user phrase, and a clearly distinct niche. Its only weakness is specificity, where it states essentially one concrete action wrapped in benefit language rather than a comprehensive action list.

Suggestions

Expand the 'what' clause to list 1-2 more concrete actions (e.g., 'clear due reviews, run catch-up sessions, audit disputed grades') to lift specificity from 3 toward 4-5.

Add a synonym or two to the trigger clause (e.g., 'spaced repetition', 'flashcard review') to push trigger-term coverage toward the comprehensive anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('due memory reviews') and one concrete action with its method ('Clear ... with free recall'), plus a benefit clause ('the two-minute habit that makes learning permanent') that is framing rather than a second action, so it sits at the 1-2 concrete actions anchor rather than the comprehensive 4-5 band.	3 / 5
Completeness	Clearly answers 'what' ('Clear due memory reviews with free recall') and 'when' with an explicit 'Use when...' clause carrying concrete trigger phrases ('reviews are due', 'wants to review, practice'), matching the anchor that requires both with explicit triggers.	5 / 5
Trigger Term Quality	Good coverage of natural phrases a user would say — 'reviews are due', 'review', 'practice', and a verbatim quoted user line 'do my engram reviews' — but a few common synonyms/variants are absent, so it stops short of the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (an engram spaced-retrieval review session) with distinctive triggers like 'do my engram reviews' and 'reviews are due', giving minimal overlap with unrelated skills despite the slightly broad term 'practice'.	5 / 5
	Total	17 / 20 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: cbd56cc

Reviewed: 9 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.