factory-triage

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

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./mastracode/factory/factory-skills/factory-triage/SKILL.md

Quality

Content

67%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 content is a well-sequenced, highly actionable governed triage workflow with concrete commands and explicit error-recovery loops. Its weakest point is conciseness — the label-mutation and duplicated template sections are repetitive and could be trimmed or externalized.

Suggestions

Consolidate the marker-comment template, which appears in both Phase 1 and the Output Contract, into a single referenced block to remove duplication.

Tighten the Phase 5 label-reconciliation list by collapsing the repeated `gh issue edit` invocations into a compact table or a single parameterized script.

Consider moving the domain-label table and the severity/effort/impact guides into a reference file to reduce inline bulk while keeping the workflow steps lean.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no explanations of git/PRs/libraries), but the label-reconciliation section and the duplicated marker templates are repetitive and could be tightened, fitting the "mostly efficient but could be tightened" anchor.	3 / 5
Actionability	Concrete executable commands abound — `gh issue view ... --json ...`, `git log --oneline -20 -- <file>`, the domain-label bash loop, and `factory_transition_work_item` with explicit parameters — with only minor gaps, matching the "mostly executable guidance" anchor.	4 / 5
Workflow Clarity	Five numbered phases give a clear sequence with explicit checkpoints — confirm publication via the returned comment identity, and a rejection feedback loop ("read the stated reason, address it... and retry once corrected") — leaving only minor validation gaps in the batch label mutations.	4 / 5
Progressive Disclosure	No bundle files exist, but the single SKILL.md is well-organized into clearly headed sections (phases, output contract, behavior rules) with no nested references, matching the "good structure; most content appropriately placed; minor organization gaps" anchor.	4 / 5
	Total	15 / 20 Passed

Description

58%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 clearly niche-scoped, listing four concrete triage actions. Its main weakness is the missing explicit "when to use" trigger guidance, which caps completeness and leaves trigger-term coverage thin.

Suggestions

Append an explicit "Use when..." clause naming natural trigger phrases, e.g. "Use when triaging a Factory work item, investigating a linked GitHub/Linear issue, or when asked to diagnose and advance a triage-stage item."

Add common synonyms a user might actually say ("investigate", "diagnose", "root-cause", "advance the work item") to broaden trigger-term coverage.

Keep the existing action list but ensure the trigger clause references the source identifiers users mention (GitHub issue, Linear identifier) to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "trace history", "understand architecture", "diagnose root cause", "advance the stage" — with only minor coverage gaps, fitting the "lists several specific actions" anchor.	4 / 5
Completeness	The "what" is clear (trace, understand, diagnose, advance) but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric cap completeness cannot exceed 3.	3 / 5
Trigger Term Quality	Relevant domain keywords ("Factory work item", "issue", "triage") are present but there are no synonyms or common variations a user might naturally say, matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	"Triage a Factory work item's issue" carves a clear niche tied to the Factory/mastra workflow with only minor overlap risk against related issue-handling skills, fitting the "mostly distinct" anchor.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mastra-ai/mastra
Path: mastracode/factory/factory-skills/factory-triage/SKILL.md
Commit: 748d4ed

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.