CtrlK
BlogDocsLog inGet started
Tessl Logo

triage-prs

Use this skill to triage the open PR queue before a release. Classifies every open PR into must-merge, candidate, superseded, or deferred; writes a working triage doc; and runs the merge loop end-to-end. Designed for the pre-release "PR speedrun" pass where a solo maintainer wants to clear the inbound backlog in a single session.

70

Quality

86%

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

81%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 workflow with strong validation checkpoints and a session-state triage doc. Conciseness is the weak spot due to repeated warnings, a duplicated command reference, and several repo-specific gotchas that pad the token budget.

Suggestions

Consolidate the main..HEAD warning to one canonical location (e.g., Gotchas) and reference it rather than restating it in step 5b and Notes.

Remove or generalize repo-specific gotchas (FastAPI route ordering, Apple -weak_framework, cpal !Send, PyTorch nightly) that are not relevant to generic PR triage, or move them to a per-repo reference file.

Drop the 'Canonical commands reference' section or replace it with a one-line pointer, since the commands already appear inline in the workflow steps.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands, but the main..HEAD warning is repeated three times (step 5b, Gotchas, Notes), the 'Canonical commands reference' duplicates commands already shown in steps, and several repo-specific gotchas (FastAPI route ordering, Apple -weak_framework, cpal !Send, PyTorch nightly) are tangential to generic PR triage.

3 / 5

Actionability

Fully executable throughout — concrete gh/git commands, jq filters, bash merge loops, heredoc commit trailers, and copy-paste patterns covering batch merge, rebase-and-push-to-fork, partial-apply, and supersede-close.

5 / 5

Workflow Clarity

Clear 11-step sequence with explicit validation checkpoints (step 6 'Verify afterward that each landed cleanly', step 8 'Check the diffs first'), a triage-doc template acting as a checklist, and a feedback loop (rebase if behind, retry merge on UNKNOWN).

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear section headers and appropriately inline operational commands, but no bundle files exist and the duplicated 'Canonical commands reference' is a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

92%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, third-person description that clearly states both what the skill does and when to use it, with a distinct pre-release triage niche. Trigger-term coverage is good rather than comprehensive.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person — 'Classifies every open PR into must-merge, candidate, superseded, or deferred; writes a working triage doc; and runs the merge loop end-to-end' — with comprehensive coverage of the skill's purpose.

5 / 5

Completeness

Explicitly answers both what (classify/write doc/run merge loop) and when ('Use this skill to triage the open PR queue before a release', 'Designed for the pre-release "PR speedrun" pass') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keywords a maintainer would say ('triage the open PR queue before a release', 'clear the inbound backlog', 'PR speedrun'), but the synonym set is modest and lacks broader variations.

4 / 5

Distinctiveness Conflict Risk

Clear niche — pre-release PR triage and merge loop — with distinct triggers and minimal overlap risk; explicitly pairs with draft-release-notes and release-bump.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
jamiepine/voicebox
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.