context-recovery

Post-compaction recovery runbook for reconstructing active lane state from Memory Core recency, semantic recall, session rollups, and A2A. Triggers: Use immediately after context compaction/compression, resuming a summarized session, or noticing the active lane was reconstructed from a lossy summary.

Quality

87%

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

100%Weight 40%Scale 1-3

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

An exemplary lean body that delegates a multi-step workflow to a single verified one-level-deep reference while giving exact tool and path guidance and a clear pre-assertion gate.

Dimension	Reasoning	Score
Conciseness	An ultra-lean single-sentence body with no concept over-explanation; every token earns its place and it assumes Claude's competence.	3 / 3
Actionability	Names the exact tool (`view_file`) and the exact reference path, giving concrete, copy-paste-ready instruction; absence of code is not penalized for an actionable instruction-only skill.	3 / 3
Workflow Clarity	A simple single-purpose skill under 50 lines whose one action is unambiguous: trigger -> read the workflow file -> gate before asserting lane state; not a destructive/batch op so no validation cap applies.	3 / 3
Progressive Disclosure	Body is a clear overview pointing to one real, one-level-deep reference (references/context-recovery-workflow.md, verified present), well-signaled with the full path and easy to navigate.	3 / 3
	Total	12 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 specific, well-triggered description that explicitly answers both what and when; its main weakness is jargon-heavy trigger phrasing and a single action verb, which limit specificity and natural-term coverage.

Suggestions

Broaden trigger-term coverage with everyday phrasings (e.g., 'context was compressed', 'lost my place after compaction', 'session got summarized') alongside the technical terms.

Add a second concrete action verb beyond 'reconstructing' (e.g., 'reconstruct, verify, and resume active lane state') to reach multiple distinct actions for higher specificity.

Consider spelling out or naturalizing 'A2A' and 'session rollups' so non-expert users would still recognize the trigger.

Dimension	Reasoning	Score
Specificity	Names the domain and a single reconstruction action with several specific data sources ("Memory Core recency, semantic recall, session rollups, and A2A"), but does not list multiple distinct concrete actions like the score-3 anchor.	2 / 3
Completeness	Clearly states what it does (reconstruct active lane state from listed sources) and provides an explicit "Triggers: Use immediately after..." clause for when to use it.	3 / 3
Trigger Term Quality	Includes relevant trigger phrases ("context compaction/compression", "resuming a summarized session") but leans on jargon (Memory Core, A2A, session rollups) and lacks broader natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (post-compaction recovery) with specific, unlikely-to-overlap triggers that distinguish it from general memory skills.	3 / 3
	Total	10 / 12 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: neomjs/neo
Path: .agents/skills/context-recovery/SKILL.md
Commit: b4a1b58

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.