CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

break-fix-troubleshooting

Diagnose caddy-security deployment and runtime failures from configs, logs, versions, and HTTP evidence. Use for focused fixes, unresolved support handoffs, or preparing break-fix issue reports.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/break-fix-troubleshooting/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.

A well-honed diagnostic skill body: a concrete 8-step workflow, an unusually specific symptom-check checklist, exact report structure and tooling commands, and sound safety guidance (redaction, disposable reproduction). The remaining gaps are the oversized inline OIDC-consent bullet, a hedged validation step, and the absence of an explicit error-recovery loop.

Suggestions

Move the OIDC consent 403 / ERR_ABORTED deep-dive (Symptom Checks) into the already-referenced oidc-provider.md or oidc-conformance.md reference, leaving a two-line symptom entry with the link in SKILL.md.

Name the concrete validation commands in step 6 (e.g., the exact caddy adapt command and the focused go test invocation) instead of the conditional 'Use Caddy adaptation or focused Go tests when local context supports it'.

Add an explicit feedback loop after validation (e.g., 'If adaptation or tests fail, reconcile the config against the parser fixtures and re-validate before reporting') to complete the workflow's error-recovery path.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious domain specifics (sandbox_secret, /beacon vs /whoami semantics, net::ERR_ABORTED, form-action source lists) and explains nothing Claude already knows, but the ~15-line inline OIDC-consent bullet and a few long Symptom Checks entries could be tightened or split out, keeping it short of 'every token earns its place'.

4 / 5

Actionability

Mostly executable guidance: copy-paste commands (caddy version, caddy list-modules --versions | rg '(auth|security)'), an exact report filename pattern, the issue-template path, and a full section skeleton for the report. The minor gap is step 6's conditional validation guidance ('Use Caddy adaptation or focused Go tests when local context supports it') which names no concrete command.

4 / 5

Workflow Clarity

A clear 8-step sequence with an explicit validation step (step 6), a symptom-to-check recovery checklist, and acceptance criteria. It falls short of a 5 because there is no explicit validate-fail-fix-re-validate feedback loop and step 6 hedges on which validation command to run.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep links to sibling skills (configuration, testing-and-ci, coding-directives, and the OIDC provider/conformance references). However, deep detail such as the OIDC consent Origin/Referrer-Policy troubleshooting is inlined in SKILL.md rather than split into a referenced file, and the skill ships no bundle references of its own.

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.

A strong description: concrete, domain-specific, and correctly structured with an explicit 'Use for' clause covering its three use cases. Its main weaknesses are the absence of natural trigger synonyms (troubleshoot/debug/error) and a when-clause that never restates the caddy-security domain or concrete trigger phrases.

Suggestions

Add natural trigger synonyms and symptom phrases to the when-clause (e.g., 'Use when the user reports caddy-security login, callback, authorization, or portal failures, asks to troubleshoot or debug a deployment, or wants to prepare a break-fix issue report').

Restate the domain inside the 'Use for' clause so the trigger guidance is self-contained and cannot match generic fix requests outside caddy-security.

Enumerate the main diagnostic actions more fully (e.g., 'inspect Caddyfiles and logs, check module versions, compare configs to parser fixtures, validate with the narrowest command') to reach comprehensive action coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions with named inputs — "Diagnose caddy-security deployment and runtime failures from configs, logs, versions, and HTTP evidence" plus deliverables ("focused fixes", "break-fix issue reports") — matching the several-specific-actions anchor with minor coverage gaps rather than the comprehensive enumeration of a 5.

4 / 5

Completeness

It answers both questions explicitly: a clear what ("Diagnose caddy-security deployment and runtime failures from configs, logs, versions, and HTTP evidence") and an explicit "Use for focused fixes, unresolved support handoffs, or preparing break-fix issue reports" when-clause. The when-clause could be more specific with concrete trigger phrases and does not restate the domain, so it is not a 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage ("deployment", "runtime failures", "logs", "fix", "issue reports", "support handoffs"), but common variations users would actually say — "troubleshoot", "debug", "broken", "error", or named symptoms like login/callback failures — are missing, so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The what-clause carves out a clear, unmistakable niche (caddy-security break-fix diagnostics), but the "Use for focused fixes..." trigger clause is generic without restating the domain, leaving minor overlap risk with closely related sibling skills (e.g., the configuration skill) rather than the minimal conflict risk of a 5.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 5 suspicious

Warning

Total

15

/

16

Passed

Repository

greenpau/caddy-security

Path

.codex/skills/break-fix-troubleshooting/SKILL.md

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.