ticket-triage

Authoritative protocol for maintainer-side label triage of unlabeled contributor tickets. Codifies the social contract for what happens when a ticket arrives without `ai`, primary (`bug`/`enhancement`/`epic`), or secondary labels. Triggers: Use this skill when an agent with maintainer permissions (`WRITE` permission or higher) encounters a ticket lacking `ai`, primary, or secondary labels — typically authored by a non-maintainer contributor or a lower-privileged agent who couldn't apply labels at create-time.

Quality

77%

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 ./.agents/skills/ticket-triage/SKILL.md

Quality

Content

80%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 an exemplar of lean progressive disclosure, delegating all detail to a real reference file with a concrete tool and path. Its only weakness is workflow clarity: the body holds no validation checkpoint for a state-changing operation, capping that dimension at 3.

Suggestions

Inline a one-line pre-flight validation gate before the delegation (e.g., 'Confirm maintainer permission via get_viewer_permission before reading the reference') so the body itself carries a checkpoint.

Add a brief mention that the reference defines the validation/verification step, so readers know validation exists without opening the file.

Optionally surface the single most important constraint inline (e.g., 'Do not apply labels before completing Step 1 of the reference') to raise workflow clarity above the cap.

Dimension	Reasoning	Score
Conciseness	The two-line body is maximally lean, assumes Claude's competence, and every token earns its place by delegating detail to the reference file.	5 / 5
Actionability	Provides a concrete, executable directive naming the tool and exact path ('use the view_file tool to read...references/ticket-triage-workflow.md'), but the actual triage steps live in the reference rather than inline.	4 / 5
Workflow Clarity	The body is a single delegation pointer with no inline validation checkpoint; since label application is a state-changing operation, the destructive/batch cap applies even though the reference contains the validation checklist.	3 / 5
Progressive Disclosure	A clear overview that points to one well-signaled, one-level-deep reference (verified to exist at references/ticket-triage-workflow.md), making navigation easy and content appropriately split.	5 / 5
	Total	17 / 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 strong on completeness and distinctiveness, with an explicit Triggers clause and a tightly scoped niche. It is held back by jargon-heavy trigger terms and abstract fluff ('codifies the social contract') that limit specificity and natural-language trigger quality.

Suggestions

Replace abstract phrasing like 'Authoritative protocol' and 'codifies the social contract' with concrete actions (e.g., 'Apply missing ai, primary, and secondary labels to unlabeled tickets').

Soften jargon in the trigger clause (e.g., 'WRITE permission or higher') toward phrasing a maintainer would naturally say.

Add a few natural-language synonyms (e.g., 'unlabeled issue', 'ticket labeling') to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('maintainer-side label triage of unlabeled contributor tickets') and 1-2 concrete actions (triaging/labeling), but does not list several specific actions and pads with abstract phrasing like 'codifies the social contract'.	3 / 5
Completeness	Explicitly answers both 'what' (authoritative protocol for label triage) and 'when' via a 'Triggers: Use this skill when an agent... encounters a ticket lacking...' clause with concrete trigger conditions.	5 / 5
Trigger Term Quality	Relevant keywords appear ('unlabeled contributor tickets', 'ticket arrives without...labels', 'ai/primary/secondary labels') but the phrasing is technical-jargon-heavy ('WRITE permission or higher') and misses common natural variations users would say.	3 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (maintainer-permission agent + unlabeled tickets) with distinct triggers and minimal overlap risk against other ticket-handling skills.	5 / 5
	Total	16 / 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: neomjs/neo
Path: .agents/skills/ticket-triage/SKILL.md
Commit: 210c03c

Reviewed: 3 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.