Name: unified-memory
Rating: 72 (1 reviews)
Author: affaan-m

unified-memory

Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.

Quality

89%

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 unified-memory in affaan-m/ECC

Quality

Content

78%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.

Strong, executable body with concrete commands, a clear sequenced workflow, and thoughtful trust/security boundaries. The main gap is progressive disclosure — everything lives in one inline file with no detail references — and the validation loop could be made more explicit.

Suggestions

Move the MCP Setup and full flag/reference detail into a separate references file (e.g. references/mcp-setup.md) and link to it one level deep, keeping SKILL.md as a lean overview.

Turn the 'Validate the vault' step into an explicit feedback loop: run `ecc memory doctor` → if issues, repair files → re-run doctor → only proceed when clean.

Tighten the Trust And Data Boundaries and MCP identity paragraphs to bullet-style rules to recover a few tokens without losing the safety guidance.

Dimension	Reasoning	Score
Conciseness	Mostly lean and command-driven with no padding about concepts Claude already knows, but a few explanatory prose passages (e.g. the trust-boundary and MCP-identity paragraphs) could be trimmed slightly further while keeping the safety guidance.	4 / 5
Actionability	Copy-paste-ready CLI commands with full flag sets for search, read, save, handoff, and doctor, plus the named MCP tools (memory_save, memory_search, memory_read, memory_doctor) cover the common cases concretely.	5 / 5
Workflow Clarity	A clear four-step sequence (recall → save → hand off → validate) with an explicit `ecc memory doctor` validation step, but the validate→fix→re-run feedback loop is only implied ('Repair reported files manually') rather than spelled out as a retry cycle.	4 / 5
Progressive Disclosure	Well-organized section headers, but the skill is a single ~165-line monolith with no bundle reference files; content like the full MCP setup and flag reference is inlined rather than split into one-level-deep reference docs.	3 / 5
	Total	16 / 20 Passed

Description

100%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 textbook description: concrete capabilities, explicit 'Use when' triggers, third-person voice, and a clearly distinct multi-agent memory niche. It matches the 5-anchor examples closely on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Share durable, inspectable context and handoffs', 'save work state', 'transfer context', 'resume another agent's task', 'search shared project knowledge' — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (share durable, inspectable context and handoffs through the ECC Memory Vault) and 'when' (Use when an agent must save work state, transfer context, resume a task, or search shared knowledge) with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when' clause supplies comprehensive natural trigger phrases ('save work state', 'transfer context', 'resume another agent's task', 'search shared project knowledge') that an operator would plausibly say when needing this skill.	5 / 5
Distinctiveness Conflict Risk	The named harnesses (Claude, Codex, Hermes, Cursor, OpenCode) and 'local ECC Memory Vault' carve a clear inter-agent memory niche with minimal overlap risk against generic memory or doc skills.	5 / 5
	Total	20 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: .cursor/skills/unified-memory/SKILL.md
Commit: e04ea0b

Reviewed: 2 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.