CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

autofix

Use when you want to automatically triage errors from Sentry (or error logs), cross-reference them against the codebase and open PRs, prioritize by severity, and optionally create fix PRs.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/autofix/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a well-structured, highly actionable six-step workflow with concrete commands, decision tables, report templates, and safety rules including test-run and human-confirmation checkpoints. Remaining gaps are the unparsed Sentry JSON response, no test-failure recovery loop, and slight padding in the intro and Anti-Rationalization sections.

Suggestions

Add an executable parsing step for the Sentry API response (e.g., a jq command extracting issue id, title, count, and lastSeen) so the primary flow is fully copy-paste runnable.

Add a feedback loop in Step 6 for test failure (e.g., 'If tests fail, fix the regression and re-run before creating the PR').

Trim the intro sentence (it duplicates the description) and condense the Anti-Rationalization table to only its actionable guidance.

DimensionReasoningScore

Conciseness

Mostly lean and command/table-driven, but the intro sentence duplicates the description and the Anti-Rationalization table is partly motivational padding that could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready commands for the main flows (sentry-cli check, Sentry API curl, grep extraction, gh pr list/create), but the primary Sentry flow returns JSON with no parsing command given, and 'Parse each error' lacks an executable step.

4 / 5

Workflow Clarity

Six clearly sequenced steps with real checkpoints (CLI presence check, 'Run tests' before PRs, human confirmation gate), but there is no feedback loop for what to do when tests fail, so the anchor-5 'error recovery loops' bar is not met.

4 / 5

Progressive Disclosure

Well-organized single-file structure with clear step sections, and inline content is defensible at ~160 lines for a slash command, but there are no external reference files at all, so nothing is progressively disclosed.

4 / 5

Total

16

/

20

Passed

Description

75%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.

The description is specific and action-rich, clearly naming the Sentry/error-log domain and four concrete capabilities with an explicit 'Use when' trigger. Its weaknesses are the second-person voice, a 'when' clause that is circular with the 'what', and missing common trigger synonyms like 'crashes' or 'production errors'.

Suggestions

Rewrite in third person and make the 'when' clause independently concrete, e.g., 'Use when the user mentions Sentry, production errors, crashes, or pastes a stack trace/log they want triaged and fixed.'

Add natural trigger synonyms such as 'exceptions', 'unhandled errors', 'production issues', and 'error monitoring' to improve keyword coverage.

Sharpen distinctiveness by leading with the Sentry/error-log niche so the description is less likely to fire on generic bug-fix or PR-review requests.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('triage errors from Sentry', 'cross-reference them against the codebase and open PRs', 'prioritize by severity', 'optionally create fix PRs') with comprehensive coverage, but the second-person phrasing 'Use when you want to' incurs the guideline's 1-point specificity penalty.

4 / 5

Completeness

Both 'what' and 'when' are explicitly present, but the 'when' clause ('Use when you want to automatically triage errors...') merely restates the 'what' rather than providing independent concrete trigger phrases, so it is not fully explicit.

4 / 5

Trigger Term Quality

Includes natural terms users would say ('Sentry', 'errors', 'error logs', 'fix PRs', 'severity'), but misses common synonyms and variations like 'crashes', 'exceptions', 'production errors', or 'bugs'.

4 / 5

Distinctiveness Conflict Risk

'Sentry (or error logs)' establishes a clear niche with distinct triggers, but 'create fix PRs' and 'cross-reference against open PRs' create minor overlap risk with generic bug-fix and PR-review skills.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/specialist-agent

Path

skills/autofix/SKILL.md

Revision

cd716d9

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill