CtrlK
BlogDocsLog inGet started
Tessl Logo

designing-agent-error-messages

Audit and rewrite error messages, exceptions, and API/SDK/CLI failure output so an AI agent (and a human) can self-correct without leaving the terminal. Use when designing or reviewing how a tool fails — error strings, HTTP error bodies, auth/credential errors, CLI errors, thrown exceptions — especially for libraries, APIs, and CLIs that AI agents consume. Grounded in patterns from 2027.dev's evals of 136 dev tools across 3,500+ agent runs.

78

1.17x
Quality

Does it follow best practices?

Impact

93%

1.17x

Average score across 1 eval scenario

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-sequenced review methodology with concrete examples and an explicit verify step, weakened mainly by narrative/promotional padding and the absence of any progressive file structure. The seven-pattern audit and worked rewrites are its core strength.

Suggestions

Trim the narrative "core principle" intro and remove the promotional closing (2027.dev/arena, "Submit a tool eval request") to tighten conciseness toward pure instructional content.

Consider splitting the worked rewrites and/or the seven-pattern reference into a separate reference file linked from a concise overview, improving progressive disclosure.

Make the verify feedback loop explicit (e.g., "if the agent does not self-correct from the error text alone, re-classify and rewrite"), so the validation checkpoint is a clear retry loop rather than implied.

DimensionReasoningScore

Conciseness

The core is high-signal (four-question spec, seven Detect/Fix patterns, worked diffs), but the narrative "core principle" intro and the promotional closing ("agent arena at 2027.dev/arena", "Submit a tool eval request") add tokens that don't aid execution. It is not a 1 because it avoids explaining generic concepts Claude already knows, and not a 3 because of the non-instructional padding.

2 / 3

Actionability

It gives executable grep patterns, concrete ✗/✓ before/after examples with exact env-var names and URLs, and copy-paste-ready worked rewrite diffs. It is not a 2 because the guidance is specific and complete rather than pseudocode or missing key details.

3 / 3

Workflow Clarity

"How to apply" is a clear Inventory→Classify→Rewrite→Kill silent failures→Verify sequence with an explicit validation checkpoint (run an agent with no and wrong credentials, watch recovery) plus an A/C/F self-score checklist. It is not a 2 because validation and a recovery feedback loop are present, not missing or implicit.

3 / 3

Progressive Disclosure

No bundle files exist; the ~135-line body is well-sectioned but monolithic, with no signaled one-level-deep references or file-level split, and the patterns/worked rewrites could be externalized. It is not a 1 because the content is organized under clear headers rather than a wall of text, and not a 3 because there is no reference structure to navigate.

2 / 3

Total

10

/

12

Passed

Description

100%

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, specific description with concrete actions, natural trigger terms, an explicit 'Use when' clause, and a distinctive agent-error niche. It uses third-person/imperative voice throughout with no first/second-person phrasing.

DimensionReasoningScore

Specificity

"Audit and rewrite error messages, exceptions, and API/SDK/CLI failure output" names multiple concrete actions (audit, rewrite) across specific targets, matching the anchor for listing multiple specific concrete actions. It is not a 2 because it goes beyond naming a domain to enumerating several distinct actions and output types.

3 / 3

Completeness

It answers what ("Audit and rewrite error messages… so an AI agent (and a human) can self-correct") and when via an explicit "Use when designing or reviewing how a tool fails…" clause. It is not a 2 because the trigger guidance is explicit, not merely implied, satisfying the 'Use when…' requirement.

3 / 3

Trigger Term Quality

It covers natural terms a user would say — "error strings, HTTP error bodies, auth/credential errors, CLI errors, thrown exceptions" plus "libraries, APIs, and CLIs" — giving good coverage of common variations. It is not a 2 because it lists many relevant natural keywords rather than a single generic phrase.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply defined — error/exception/failure-output design for AI-agent-consumed libraries, APIs, and CLIs — making it unlikely to trigger for unrelated skills. It is not a 2 because the triggers are distinct and specific rather than overlapping with generic code-review or doc skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
team2027/2027-skills
Reviewed

Table of Contents

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.