CtrlK
BlogDocsLog inGet started
Tessl Logo

factory-triage

Triage a Factory work item's issue — trace history, understand architecture, diagnose root cause, then advance the stage

69

Quality

83%

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

100%

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

The body is an exemplar of a dense, executable triage workflow: concrete commands, a clear phased sequence, an explicit transition-rejection feedback loop, and tight prose with no concept padding. No bundle files are present or warranted.

DimensionReasoningScore

Conciseness

Lean and dense throughout — it gives concrete commands and operational heuristics (author-history framing, the gh/jq ANSI note) without explaining concepts Claude already knows; every section earns its place.

3 / 3

Actionability

Provides copy-paste-ready, executable commands (gh issue view --json ..., git log --oneline -20 -- <file>, git blame) plus concrete transition parameters (stage: "planning"/"done", rationale max 1000 chars).

3 / 3

Workflow Clarity

Five explicitly sequenced phases with an explicit validation/feedback loop on the terminal transition — "If it is rejected, read the stated reason, address it... and retry once corrected" — and a checkpoint to take stage/expectedRevision from the factory-phase signal.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the single-file workflow is cleanly organized into named Phase 1–5 sections and a Behavior Rules block, satisfying the well-organized-sections criterion for skills with no external references.

3 / 3

Total

12

/

12

Passed

Description

67%

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 distinctively scoped to Factory work-item triage, but it lacks an explicit "Use when..." trigger and relies on a narrow set of trigger terms, so a user might not naturally surface it for generic bug-investigation requests.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when triaging a Factory work item's issue, investigating a reported bug, or deciding whether an issue is valid and ready to plan."

Broaden trigger terms to include common user phrasings ("investigate", "look into", "reproduce", "is this a real bug") so the description matches how users actually request triage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "trace history, understand architecture, diagnose root cause, then advance the stage" — tied to a named domain (Factory work item), matching the multi-action anchor for 3.

3 / 3

Completeness

Clearly states what the skill does, but the "when" is only implied (triaging a Factory work item) with no explicit "Use when..." clause, which caps completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

Relevant terms ("triage", "Factory work item", "issue", "root cause") are present but coverage is narrow and Factory-internal, missing common user phrasings like "investigate this bug" or "look into this issue".

2 / 3

Distinctiveness Conflict Risk

Scoped to "Factory work item's issue" with a distinct triage-to-stage-transition purpose, giving it a clear niche unlikely to trigger for unrelated debugging skills.

3 / 3

Total

10

/

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
mastra-ai/mastra
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.