CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-review-triage

Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.

61

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./starters/pr-babysitter-opencode/skills/pr-review-triage/SKILL.md
SKILL.md
Quality
Evals
Security

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 lean, well-structured, and highly actionable via a concrete per-PR template with enum values, but the batch workflow lacks an explicit validation/feedback step and a couple of status-fetch commands are not shown.

Suggestions

Add an explicit validation step after writing pr-babysitter-state.md (e.g. re-read to confirm every PR has a complete entry) since the skill iterates over multiple PRs.

Show the concrete commands for fetching CI and review status (e.g. `gh pr checks <N>`, `gh pr view <N> --json reviews,mergeable`) so the workflow is fully executable.

Make the multi-step sequence explicit with a short ordered list (gather inputs -> assess each PR -> write state -> emit top 3) so checkpoints are unambiguous.

DimensionReasoningScore

Conciseness

Lean and efficient: no explanation of concepts Claude already knows, every rule earns its place, and the output template is tight. Matches the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Provides a concrete copy-paste-ready output template with exact enum values plus `gh pr list`, but does not show the executable command for fetching CI/review status — minor gaps. Not 5 because a couple of key fetch steps are left to inference.

4 / 5

Workflow Clarity

Sequence is clear (inputs -> per-PR assess -> write state -> top 3 actions) with decision rules, but this batch operation over multiple PRs lacks an explicit validation/feedback loop, capping workflow clarity at 3. Not 4 because the validate/verify checkpoint is missing rather than merely minor.

3 / 5

Progressive Disclosure

Under 50 lines with no need for external references and well-organized sections (Inputs, Per-PR Output, Rules), so progressive disclosure scores 5 per the simple-skill note. No bundle files exist to navigate.

5 / 5

Total

17

/

20

Passed

Description

66%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 concrete and well-scoped to PR triage, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 3 and leaves the 'when to use' answer implicit.

Suggestions

Add an explicit trigger clause, e.g. 'Use when monitoring open PRs for blockers, stale reviews, or failing CI.'

Spell out 'pull request' alongside 'PR' and add natural terms like 'stale PRs' or 'failing checks' for broader keyword coverage.

Mention review approvals / review-required state in the action list to make capability coverage comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions ('check CI status, review staleness, merge conflicts, and unanswered review comments', 'Produces a prioritized watchlist'), matching the 'several specific actions; minor gaps' anchor. Not 5 because coverage isn't comprehensive (e.g. approvals/review state not named).

4 / 5

Completeness

The 'what' is clear, but there is no explicit 'when'/'Use when...' trigger clause, so completeness is capped at 3 per the missing-trigger-guidance rule. Not 4 because the 'when' is only weakly implied, not stated.

3 / 5

Trigger Term Quality

Natural terms like 'open PRs', 'CI status', 'merge conflicts', and 'review comments' give good keyword coverage. Not 5 because 'PR' is jargon (no spelled-out 'pull request'), and a few natural variations are missing.

4 / 5

Distinctiveness Conflict Risk

A clear PR-triage niche ('PR babysitter', prioritized watchlist) with distinct triggers and minimal conflict risk. Not 5 because of minor overlap with general code-review skills.

4 / 5

Total

15

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
cobusgreyling/loop-engineering
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.