graceful-error-recovery

Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.

Quality

91%

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.

The body is a tight, well-organized instruction skill: concise, actionable with a concrete root-cause checklist and code-level anti-pattern, and sequenced with an explicit retry feedback loop. It fully satisfies the rubric for a simple single-purpose skill.

Dimension	Reasoning	Score
Conciseness	The body is lean ("When something fails, diagnose before retrying.") with no padding or explanation of concepts Claude already knows; every line instructs rather than lectures, matching the score-3 'every token earns its place' anchor.	3 / 3
Actionability	Though instruction-only, the guidance is concrete and actionable: a specific root-cause checklist ("typo, missing dependency, permission, network, logic bug?") and concrete anti-pattern examples like bare `except: pass`, which the rubric permits to score 3 when guidance is actionable.	3 / 3
Workflow Clarity	The five-step Process is a clearly sequenced diagnostic flow with an explicit feedback loop ("If two retries fail, step back and consider an alternative approach"), matching the score-3 anchor's clear sequence with error-recovery feedback; no destructive/batch cap applies.	3 / 3
Progressive Disclosure	At ~16 lines with a single purpose and no need for external references, the well-organized Process and Anti-patterns sections qualify for the score-3 simple-skill exception; no bundle files exist to require deeper structure.	3 / 3
	Total	12 / 12 Passed

Description

82%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 well-structured with an explicit 'Use when...' trigger and natural failure-related keywords, but its capability list stays at the abstract behavioral level and the general-purpose error-recovery niche carries some overlap risk with domain skills.

Suggestions

Enumerate concrete diagnostic actions (e.g., 'inspect stack traces, verify dependency versions, check permissions and network reachability') to lift specificity from abstract verbs to concrete capabilities.

Tighten the niche by scoping the trigger (e.g., 'Use when a repeated tool or API failure needs root-cause diagnosis before retrying') to reduce overlap with skills that handle their own domain errors.

Dimension	Reasoning	Score
Specificity	The description names a domain ("tool call, command, or API request fails") and some actions ("Diagnose the root cause systematically", "retrying or changing approach"), but the actions are abstract verbs rather than multiple concrete technical actions, matching the score-2 anchor rather than the score-3 list of specific capabilities.	2 / 3
Completeness	It explicitly states when to use it ("Use this skill when a tool call, command, or API request fails") and what it does ("Diagnose the root cause systematically before retrying"), satisfying both the what and when with an explicit trigger as the score-3 anchor requires.	3 / 3
Trigger Term Quality	Phrases like "tool call", "command", "API request", "fails", and "retry" are natural terms a user would say when hitting an error, giving good coverage of common trigger variations matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The failure-triggered niche is recognizable but the skill is general-purpose and could overlap with domain skills that also handle their own errors, fitting the score-2 "somewhat specific but could still overlap" anchor rather than a clearly non-conflicting niche.	2 / 3
	Total	10 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aiming-lab/MetaClaw
Path: memory_data/skills/graceful-error-recovery/SKILL.md
Commit: 922caf3

Reviewed: 9 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.