CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

apply-triage-action

Apply, reject, or defer exactly one issue or CI recommendation from a local triage queue report. Use when the on-duty engineer explicitly supplies an item ID.

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An excellent instruction-only skill body: terse, fully directive, with explicit validation and confirmation gates around every external write and a clearly sequenced workflow. The only minor gap is the absence of worked examples (e.g., a sample action record or preview payload) that would make the guidance copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean and entirely directive — no concept explanations, no padding, and no filler (e.g., "PRs are informational in v1.", "Reject is terminal locally."). Every sentence instructs and assumes Claude's competence, matching the anchor-5 ideal of every token earning its place.

5 / 5

Actionability

Guidance is mostly executable: concrete paths (".agents/triage-duty/"), enumerated record fields ("repository, target, source report, ID, timestamp, disposition, reason, confirmed payload, and outcome"), a specific command ("apply --expected-preview"), and a enumerated v1 action list. It falls short of anchor 5 only because there are no worked examples of a record entry or a preview payload for the common cases.

4 / 5

Workflow Clarity

The workflow is clearly sequenced (locate/validate → reject/defer → apply) with explicit validation checkpoints and feedback loops for external writes: "Before any external write, re-read the target and determine whether it materially changed", "Revalidate immediately before execution; changed payloads require a new preview and confirmation", and "mark applied only after verified success". The destructive/batch cap does not apply because validation is explicitly present.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files, and the body is well-organized into clear sections (Locate and validate / Reject or defer / Apply). All cross-references (e.g., [local-state rules], [Label Discovery], [`triage-issue`], the `/label-issue` skill) are one level deep and clearly signaled with descriptive anchors, so the simple-skill guideline for a top score applies.

5 / 5

Total

19

/

20

Passed

Description

87%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: it states concrete actions, an explicit use-when trigger with a concrete gating condition, and a clearly bounded niche. The only weakness is minor — it could enumerate the supported apply actions and a few more natural trigger synonyms for fuller coverage.

DimensionReasoningScore

Specificity

The description lists three concrete actions ("Apply, reject, or defer") on a specific object ("exactly one issue or CI recommendation from a local triage queue report"), but leaves minor gaps — the body shows apply covers five sub-actions (label, create issue, comment, assessment state, close) that are not enumerated, so it falls short of the comprehensive anchor 5.

4 / 5

Completeness

It clearly answers both questions: the "what" ("Apply, reject, or defer exactly one issue or CI recommendation from a local triage queue report") and an explicit, concrete "when" trigger ("Use when the on-duty engineer explicitly supplies an item ID"), matching the anchor-5 pattern of what + explicit trigger phrase.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "triage", "queue", "recommendation", "apply", "reject", "defer", "item ID", "on-duty engineer" — but a few natural phrases users might say (e.g., "triage duty", "queue review", "disposition") are missing, matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche with a tightly gated trigger — acting on exactly one item keyed by an explicit ID supplied by the on-duty engineer — makes it highly distinguishable from general triage or issue-management skills, with minimal wrong-skill trigger risk.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 7 suspicious

Warning

Total

13

/

16

Passed

Repository

NVIDIA/OpenShell

Path

.agents/skills/apply-triage-action/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.