self-repair

Execute autonomous diagnostics, verify MCP server stability, and treat system degradation using tests and memory core forensics. Triggers: [Healthcheck, run health checklist, diagnose system collapse, MCP infrastructure failure, troubleshoot agent OS, system degraded, Sandman handoff verification failure, self-repair, system recovery]

Quality

82%

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

65%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.

The body is extremely concise and clearly delegates to a single reference, but it offloads the entire actionable workflow and references that file via a path that does not match the actual bundle location. It needs at least a minimal inline repair sequence and a corrected, navigable reference link.

Suggestions

Inline a minimal diagnostic/repair sequence with concrete commands and verification steps in SKILL.md so the skill is actionable before loading the full protocol, rather than delegating everything to the reference.

Add validation checkpoints (e.g., re-run the healthcheck after a repair and confirm stability before declaring success) since self-repair can make destructive system changes.

Fix the reference path: the body cites `.agents/skills/self-repair/references/self-repair-protocol.md` but the bundled file is at `references/self-repair-protocol.md`; use a relative link like `[self-repair-protocol.md](references/self-repair-protocol.md)` so navigation resolves.

Dimension	Reasoning	Score
Conciseness	The body is a single lean directive sentence with no concept explanations or padding; every token earns its place.	3 / 3
Actionability	It gives a concrete tool and target path ("use the `view_file` tool to read ... self-repair-protocol.md"), but defers all actual diagnostic and repair substance to the reference, leaving the body's guidance incomplete.	2 / 3
Workflow Clarity	Only a single "read the file before proceeding" step is present, with no sequenced workflow or validation checkpoints for a potentially destructive self-repair process, capping it at 2.	2 / 3
Progressive Disclosure	The reference is one level deep and clearly signaled, but the cited path `.agents/skills/self-repair/references/self-repair-protocol.md` does not match the bundled `references/self-repair-protocol.md`, breaking easy navigation.	2 / 3
	Total	9 / 12 Passed

Description

100%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.

The description is specific, complete, and distinctive, naming concrete actions and providing an explicit triggers clause in third-person voice. It is a strong, well-targeted skill description.

Dimension	Reasoning	Score
Specificity	"Execute autonomous diagnostics, verify MCP server stability, and treat system degradation using tests and memory core forensics" lists multiple concrete, distinct actions rather than vague language.	3 / 3
Completeness	It states both what the skill does and an explicit "Triggers:" clause satisfying the "Use when..." requirement, so it is not capped at 2.	3 / 3
Trigger Term Quality	The Triggers list covers natural terms a user would say (Healthcheck, run health checklist, troubleshoot agent OS, system degraded, self-repair, system recovery), with only a few internal-jargon entries.	3 / 3
Distinctiveness Conflict Risk	The MCP server / Agent OS self-repair framing with domain-specific triggers carves a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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/self-repair/SKILL.md
Commit: c1ce853

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.