Name: unified-memory
Rating: 68.8 (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

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

The canonical home for this skill is unified-memory in affaan-m/ECC

Quality

Content

75%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, actionable guidance skill with concrete CLI/MCP examples and a clear validated workflow. It is efficient and navigable, with only minor room to tighten prose and make the doctor feedback loop explicit.

Suggestions

Make the validation feedback loop explicit: after `ecc memory doctor`, state 'fix reported files, then re-run `ecc memory doctor` until clean' rather than only 'Repair reported files manually'.

Tighten the Runtime Prerequisite and Trust And Data Boundaries sections by moving explanatory rationale into a short rationale line, keeping the actionable rules up front.

Replace remaining placeholders (`<memory-id>`, `<repo>`) with a brief inline note on how to obtain them (e.g. from `ecc memory search` output) to make every example fully executable.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with actionable commands, but the Runtime Prerequisite and Trust And Data Boundaries sections contain explanatory prose that could be trimmed slightly.	4 / 5
Actionability	Provides concrete, copy-paste-ready CLI commands with full flags (e.g. the `ecc memory save` example) plus MCP equivalents; minor placeholders like `<memory-id>` and the external `--body-file` keep it just short of fully executable everywhere.	4 / 5
Workflow Clarity	A clear four-step sequence (recall, save, hand off, validate) with an explicit validation step (`ecc memory doctor`); the fix-then-revalidate feedback loop is only implicit ('Repair reported files manually'). Operations are create-only/read-only, so the destructive-cap does not apply.	4 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-organized with clear headers and easy navigation. The MCP Setup and Trust And Data Boundaries sections are somewhat lengthy inline content that could optionally live in reference files, but inlining is reasonable for a guidance skill.	4 / 5
	Total	16 / 20 Passed

Description

92%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 that concisely states the capability and gives explicit, multi-trigger usage guidance in third person. It is comprehensive on actions and triggers with only minor synonym gaps.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'save work state, transfer context, resume another agent's task, or search shared project knowledge' plus 'Share durable, inspectable context and handoffs' — giving comprehensive coverage of the vault's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Share durable, inspectable context and handoffs...through the local ECC Memory Vault') and when ('Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases ('save work state', 'transfer context', 'resume another agent's task', 'search shared project knowledge') are present and relevant, but a few common synonyms (e.g. 'memory', 'handoff' as standalone triggers) are not surfaced.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — cross-harness memory vault and agent handoffs — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: .agents/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.