memory

AI DevKit · Use the memory CLI as a durable knowledge layer. Search before non-trivial work, store verified reusable knowledge, update stale entries, and avoid saving transcripts, secrets, or one-off task progress.

Quality

90%

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

96%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.

Excellent body content: lean, fully executable, and a workflow with genuine validation gates and feedback loops. The only structural improvement is offloading the command reference to a separate file to keep SKILL.md as a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero padding — no explanations of concepts Claude already knows; every line is an instruction, an executable command, or a decision rule, matching 'every token earns its place'.	5 / 5
Actionability	All commands are fully executable and copy-paste ready with flags, value ranges, and placeholders (e.g. 'npx ai-devkit@latest memory search --query "<query>" --limit 5'), plus a content-shape template and troubleshooting entries — matching the fully-executable anchor.	5 / 5
Workflow Clarity	The numbered workflow has an explicit validation checkpoint ('Store or update only after the quality gate passes'), a checklist quality gate, pre-store dedup search, conflict-resolution feedback ('use the evidence and update the stale memory'), and a troubleshooting section for error recovery — matching 'explicit validation steps; feedback loops; checklists'.	5 / 5
Progressive Disclosure	Well-organized sections with nothing deeply buried, but the body exceeds 50 lines and the Commands section is a self-contained API reference that could be offloaded to a separate file; no external references exist (the bundle has no reference files), matching 'good structure; minor organization gaps'.	4 / 5
	Total	19 / 20 Passed

Description

80%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: concrete, comprehensive actions with an explicit usage rule and a distinct niche. Its main weakness is trigger phrasing — an explicit 'Use when...' clause with natural user synonyms (remember, recall, persist) would raise both completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause with concrete triggers, e.g. 'Use when starting non-trivial implementation, debugging, or planning tasks, or when the user asks to remember, recall, or persist knowledge.'

Include natural user-voice synonyms such as 'remember this', 'recall past decisions', and 'persist preferences' to broaden trigger-term coverage.

Consider naming what the memory layer holds (conventions, fixes, user preferences) in the description to sharpen distinctiveness from generic note-taking skills.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions spanning read, write, update, and negative guidance ('Search before non-trivial work', 'store verified reusable knowledge', 'update stale entries', 'avoid saving transcripts, secrets, or one-off task progress'), matching the comprehensive multi-action anchor.	5 / 5
Completeness	The 'what' is clear (durable knowledge layer via the memory CLI plus concrete actions) and a 'when' is explicitly present ('Search before non-trivial work'), so the missing-trigger cap does not apply, but the when lacks concrete trigger phrases like an explicit 'Use when...' clause, matching 'both present; when could be more explicit'.	4 / 5
Trigger Term Quality	Includes natural terms users would say ('memory', 'search', 'store', 'knowledge', 'secrets'), but misses common variations like 'remember', 'recall', 'persist', or 'preferences', so it matches 'good keyword coverage; a few natural terms missing' rather than the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	'memory CLI', 'AI DevKit', and 'transcripts, secrets' carve a distinct niche with minor overlap risk against generic knowledge-management skills; no anchor-5-level unique file or extension triggers.	4 / 5
	Total	17 / 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: codeaholicguy/ai-devkit
Path: skills/memory/SKILL.md
Commit: 7ef0cd5

Reviewed: 8 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.