CtrlK
BlogDocsLog inGet started
Tessl Logo

lightrun-runtime-aware-pr-review

Use when reviewing a pull request with runtime or production evidence — for example to review a PR with runtime verification, gather production evidence, or simulate a patch on live samples. Reviews a pull request by diffing against the PR merge base, collecting live samples, and simulating the patch on captured production inputs.

82

1.38x
Quality

85%

Does it follow best practices?

Impact

98%

1.38x

Average score across 2 eval scenarios

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 well-structured orchestration skill: clear phased workflow with explicit checkpoints and feedback loops, and clean one-level-deep reference navigation from the body. The main weaknesses are minor redundancy between the Checkpoints section and the phase references, and clutter from duplicate/leftover reference files in the bundle.

Suggestions

Remove the duplicate/leftover reference files in references/ (e.g. phase-2-runtime-profile.md, phase-3-sampling-plan.md, phase-4-execute-snapshots.md, phase-5-patch-simulation.md) that are not referenced from SKILL.md, to keep the bundle navigable.

Consider trimming the Checkpoints section to only the gate condition per phase, since full exit criteria already live in each phase reference, reducing redundancy.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence without explaining known concepts, but the Checkpoints section restates each phase's exit criteria that already live in the phase references, and 'coming soon' noise recurs — minor trim opportunities keep it just below the top anchor.

4 / 5

Actionability

Concrete, specific guidance throughout — named artifacts (pr_base_sha, deployed_sha), explicit prohibitions ('Never use deployed_sha → pr_head_sha as the PR review diff'), and ordered phases — though the executable detail is delegated to references rather than inline, leaving minor gaps.

4 / 5

Workflow Clarity

A clearly sequenced Phase 0–6 process with an explicit per-phase Checkpoints checklist, validation gates ('Do not advance a phase until its exit criteria are satisfied'), and feedback loops ('loop back to the prior phase', Phase 5 Sampling Request resume), matching the top anchor.

5 / 5

Progressive Disclosure

SKILL.md is a clean overview pointing one level deep to references/*.md with a well-signaled numbered list, and every referenced file exists; however the references/ bundle contains leftover duplicate phase files (e.g. phase-2-runtime-profile.md alongside phase-3-runtime-profile.md, phase-3/4-sampling-plan.md, phase-4/5-execute-snapshots.md, phase-5/6-patch-simulation.md), a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

88%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, third-person description with an explicit 'Use when' trigger and several concrete capabilities. It is slightly repetitive (live sampling / production evidence appear twice) and the opening 'reviewing a pull request' trigger is broad enough to risk overlap with generic PR-review skills.

Suggestions

De-duplicate the capability phrasing — 'collecting live samples' / 'gather production evidence' / 'simulate a patch' each appear twice in slightly varied form; state each once.

Tighten the trigger so it foregrounds the runtime/production-evidence qualifier (e.g. 'Use when reviewing a PR that has runtime or production evidence available') to reduce overlap with generic PR-review skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'diffing against the PR merge base, collecting live samples, and simulating the patch on captured production inputs' plus 'gather production evidence, or simulate a patch on live samples' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both — a clear 'Use when reviewing a pull request with runtime or production evidence' trigger clause and a concrete 'what' ('Reviews a pull request by diffing... collecting live samples... simulating the patch'), satisfying the top anchor.

5 / 5

Trigger Term Quality

Good natural keywords ('reviewing a pull request', 'runtime verification', 'production evidence', 'live samples') but the terms skew technical and a few common synonyms are missing, so it sits just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The runtime/production-evidence niche is distinctive, but the lead trigger 'reviewing a pull request' is broad and could overlap with other PR-review skills, leaving minor conflict risk.

4 / 5

Total

18

/

20

Passed

Validation

100%

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
lightrun-platform/lightrun-ai
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.