CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-analyze-triage

Use when the user wants to triage a CORPUS of production crashes/hangs from an aggregator (Sentry, App Store Connect) — grouped, counted issues — rather than a single crash file.

69

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 high-quality, actionable triage skill with concrete commands, explicit validation checkpoints, and clear external reference navigation. The main lever for improvement is trimming the lengthy inlined safety notes, though their byte-identical justification tempers that concern.

DimensionReasoningScore

Conciseness

The body is dense and operational, assuming Claude's competence without explaining basics, but the three inlined standing notes (especially the long anr_suspension_false_positive block) add length that could be trimmed even though the byte-identical requirement justifies them.

4 / 5

Actionability

Provides copy-paste-ready, executable guidance: the exact `xcsym triage` command with flags, concrete Sentry API paths with query params and pagination handling, and named `asc-mcp` tools covering both providers' common cases.

5 / 5

Workflow Clarity

A clearly sequenced 6-step workflow with explicit validation checkpoints (token scope probe with 401/403 handling — 'report that, don't proceed'), error-reporting feedback (errors[] surfaced to the user), and a checklist-style report template for a batch operation.

5 / 5

Progressive Disclosure

Good structure with clearly signaled one-level-deep external references (Related section plus inline pointers to production-triage.md, xcsym-ref.md, hang-diagnostics.md); the inlined standing notes are a deliberate, justified choice, though no bundle files exist and some API detail is inlined rather than split out.

4 / 5

Total

18

/

20

Passed

Description

82%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, well-scoped description with an explicit Use-when trigger and clear disambiguation against the single-file crash skill. It is slightly under-specified on the concrete actions the skill performs, which keeps specificity at the mid-anchor.

DimensionReasoningScore

Specificity

Names the domain ('production crashes/hangs from an aggregator (Sentry, App Store Connect)') and one concrete action ('triage a CORPUS'), but does not enumerate the constituent actions (fetch, normalize, classify, rank) that the body performs, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('triage a CORPUS of production crashes/hangs from an aggregator') and when via a concrete 'Use when...' trigger, and adds a disambiguating 'rather than a single crash file' clause.

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('production crashes', 'hangs', 'Sentry', 'App Store Connect', 'grouped, counted issues') with good coverage; a few common synonyms or phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (corpus triage from aggregators) and explicitly distinguishes itself from the single-crash-file case, minimizing conflict risk with sibling skills.

5 / 5

Total

17

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
CharlesWiltgen/Axiom
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.