error-recovery

Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.

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

Quality

Content

92%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 concise, actionable, and clearly sequenced with explicit validation and escalation feedback loops, making it a strong instruction-only reference. The only gap is progressive disclosure: it is a self-contained monolith with no navigable references, which is acceptable for its size but not ideal.

Suggestions

If the skill grows beyond the current five patterns, split per-pattern detail into one-level-deep reference files (e.g. RETRY.md, FALLBACK.md) signaled from the overview, or add an explicit index of the patterns for navigation.

Remove the verbatim repeat of the frontmatter description in the opening line to tighten the intro, since the description is already loaded with the skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-structured (When/Pattern/Example per pattern) and assumes Claude already knows what rate limits and build failures are; the only minor inefficiency is the intro repeating the frontmatter description, which does not drop it below the lean-and-efficient anchor.	3 / 3
Actionability	Although code-free, the guidance is concrete and instruction-actionable — 'start at 2s, double each attempt', 'Maximum 3 retries', and specific worked examples like the 429 flow — so per the instruction-only scoring note the absence of code is not penalized.	3 / 3
Workflow Clarity	Each pattern is a clearly numbered sequence with explicit feedback loops and checkpoints ('Re-run to verify the fix', 'Maximum 3 retries before escalating'), matching the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	The file is well-organized into sections but is a single ~90-line monolith with no external references; the under-50-line 'score 3 with just sections' carve-out does not apply, and anchor 3 expects well-signaled one-level-deep references, which are absent.	2 / 3
	Total	11 / 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.

The description cleanly states both what the skill does and when to use it within a distinct squad-agent niche, but its trigger terms and listed actions are generic rather than concrete. Strengthening it with specific failure-mode triggers and named recovery actions would lift the weaker dimensions.

Suggestions

Replace the generic 'When something fails' with concrete triggers users would actually say, e.g. 'Use when an agent hits API timeouts, build failures, rate limits, or tool errors'.

Name the specific recovery actions the skill provides (retry with backoff, fallback alternatives, diagnose-and-fix, escalate) instead of the single abstract verb 'adapt'.

Dimension	Reasoning	Score
Specificity	Names the domain ('recovery patterns for all squad agents') and a general action ('adapt'), but does not enumerate concrete recovery actions like retry, fallback, or escalate, so it stops short of the comprehensive multi-action anchor.	2 / 3
Completeness	It explicitly states what ('Standard recovery patterns for all squad agents') and when ('When something fails'), providing equivalent explicit trigger guidance, so the missing-'Use when' cap does not apply and it reaches the explicit what-and-when anchor.	3 / 3
Trigger Term Quality	'When something fails' is a natural but generic trigger phrase; it lacks the common failure-type variations (timeouts, build failures, rate limits) that users would actually name, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The 'for all squad agents' scoping carves a clear niche (squad agent coordination) with a distinct trigger, making conflict with unrelated skills unlikely.	3 / 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: microsoft/waza
Path: .copilot/skills/error-recovery/SKILL.md
Commit: f466c4f

Reviewed: 13 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.