CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-status-triage

Triage CI failures and PR review comments using scripts/pr-status.js. Use when investigating failing CI jobs, flaky tests, or PR review feedback. Covers blocker-first prioritization (build > lint > types > tests), CI env var matching for local reproduction, and the Known Flaky Tests distinction.

Quality

88%

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 highly actionable, well-sequenced triage skill body with concrete commands, a validation checkpoint, and a retry feedback loop. Its main weaknesses are minor duplication of the prioritization rule and references to bundle files that are absent from the supplied bundle.

Suggestions

De-duplicate the blocker-first prioritization rule: keep it in the workflow and reference it from CI Analysis Tips rather than restating it verbatim.

Ship the referenced bundle files (workflow.md, local-repro.md, and scripts/pr-status.js with its results/ output) so the References section's links resolve, or inline the essential bits and drop the dangling links.

Drop the opening restatement of the frontmatter description ("Use this skill when the user asks about PR status, CI failures, or review comments...") to save tokens, since the description already covers it.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence, but the blocker-prioritization rule is stated twice (workflow step 3 and again under CI Analysis Tips) and the opening line restates the frontmatter description, giving minor trim opportunities.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands throughout — `node scripts/pr-status.js [PR] --comments-only`, `pnpm test-dev-turbo test/path/to/test.ts`, `cargo fmt -- --check`, `gh run rerun <run-id> --failed`, and the reply/resolve-thread invocations — covering the common cases.

5 / 5

Workflow Clarity

A clear 7-step sequence with an explicit validation checkpoint (step 4: treat failures as real until disproven, check Known Flaky Tests before calling anything flaky) and an explicit error-recovery feedback loop (step 7: rerun failed jobs, wait 5 minutes, return to step 1, repeat up to 5 times).

5 / 5

Progressive Disclosure

Well-organized into clear sections with a References block pointing one level deep to workflow.md and local-repro.md, each clearly signaled with a description; however, neither referenced file (nor scripts/pr-status.js) is present in the bundle, so the navigation points to files that do not exist, preventing full marks.

4 / 5

Total

18

/

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, specific description that clearly states both capability and trigger conditions with natural user-facing terms. The only mild weakness is that part of the capability list is topic-oriented rather than action-oriented.

DimensionReasoningScore

Specificity

Names the domain and several concrete capabilities — "Triage CI failures and PR review comments", "blocker-first prioritization (build > lint > types > tests)", "CI env var matching for local reproduction", "Known Flaky Tests distinction" — but the trailing "Covers..." clause lists topic areas rather than verb-actions, leaving minor gaps versus a fully comprehensive action list.

4 / 5

Completeness

Explicitly answers both what ("Triage CI failures and PR review comments using scripts/pr-status.js. Covers blocker-first prioritization...") and when ("Use when investigating failing CI jobs, flaky tests, or PR review feedback") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users would say — "failing CI jobs", "flaky tests", "PR review comments", "PR review feedback" — giving good keyword coverage, though a few common synonyms (e.g. "checks", "build failures") are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — PR-status triage via a specific script with blocker-first ordering and a Known Flaky Tests distinction — with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

75%

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

Validation — 12 / 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: 2 missing

Warning

referenced_paths_exist

Referenced path issues: 12 missing, 2 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

vercel/next.js

Path

.agents/skills/pr-status-triage/SKILL.md

Revision

ec8ddcd

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill