error-recoverer

Intelligent error detection and recovery for autonomous coding. Use when handling errors, implementing retry logic, recovering from failures, or managing exception handling.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/error-recoverer/SKILL.md

Quality

Content

71%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.

The body is well-organized, actionable, and presents a clear recovery workflow with verification and escalation. Its main defect is a broken reference: `references/RECOVERY-STRATEGIES.md` is cited but missing from the bundle.

Suggestions

Create the missing `references/RECOVERY-STRATEGIES.md` (or remove the citation) so the References section does not contain a dead link.

Move the inlined error-categories table and RecoveryStrategy enum into the existing `references/ERROR-CATEGORIES.md` / a strategies file so SKILL.md stays a lean overview pointing one level deep.

Replace the decorative ASCII workflow box with a compact numbered list or concrete per-step commands to trim tokens while keeping the sequence clear.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with a useful categories table and enum, but the large ASCII-bordered workflow box is decorative padding and could be tightened, fitting 'efficient; minor instances of over-explanation that could be trimmed' rather than fully lean.	4 / 5
Actionability	Quick-start Python imports the real `scripts.error_recoverer` module and shows executable calls plus a decorator pattern, but placeholders like `project_dir`, `error`, and `context` are undefined, leaving minor gaps consistent with 'mostly executable guidance; concrete code with minor gaps'.	4 / 5
Workflow Clarity	A clear 5-step DETECT→CLASSIFY→STRATEGIZE→RECOVER→ESCALATE sequence includes a 'Verify recovery success' checkpoint and a rollback-on-failure feedback loop, but the steps are abstract descriptions rather than concrete commands, fitting 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	Structure is decent with dedicated References and Scripts sections, but the body cites `references/RECOVERY-STRATEGIES.md` which does not exist in the bundle (only ERROR-CATEGORIES.md is present) — a dead navigation link that drops it from a 4 to 'some structure but could be better organized'.	3 / 5
	Total	15 / 20 Passed

Description

83%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 clearly answers both what the skill does and when to use it, with concrete natural-language triggers. The main weaknesses are the buzzword 'Intelligent' and slightly broad overlap with general debugging skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'error detection and recovery', 'implementing retry logic', 'recovering from failures', 'managing exception handling' — matching the 'lists several specific actions; minor gaps' anchor; the vague adjective 'Intelligent' is mild fluff and classification is absent from the description, keeping it below 5.	4 / 5
Completeness	Explicitly states both what ('Intelligent error detection and recovery for autonomous coding') and when ('Use when handling errors, implementing retry logic, recovering from failures, or managing exception handling') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'handling errors', 'retry logic', 'recovering from failures', and 'exception handling' give good keyword coverage, but common synonyms (crashes, tracebacks, bugs) are missing, fitting 'good keyword coverage; a few natural terms missing' rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'autonomous coding' niche and recovery-focused triggers make it mostly distinct, but 'handling errors' is broad enough to overlap with general debugging/verification skills, fitting 'mostly distinct; minor overlap risk' rather than minimal conflict.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/error-recoverer/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.