CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-github-pr

Review a GitHub pull request by summarizing its diff and key design decisions. Use when the user wants to review a PR, understand changes in a branch, or get a code review summary. Trigger keywords - review PR, review pull request, summarize PR, summarize diff, code review, review branch, PR summary, diff summary.

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 well-crafted workflow skill: fully executable commands, a clear five-step sequence with explicit fallbacks and decision points, and a concrete output template. The only improvements are trimming minor redundancy and clarifying the two dangling internal references (sync-agent-infra map, crypto architecture path).

Suggestions

Drop the 'Useful Commands Reference' table or fold it into the steps, since every command in it already appears inline with full context.

Give the 'sync-agent-infra maintenance map' an explicit file path (or move it to a references/ file) so the instruction is actionable.

Replace the deeply nested relative link '../../../crates/openshell-crypto/CRYPTO.md' with a stable repo-rooted path.

DimensionReasoningScore

Conciseness

The body is command-driven and dense with skill-specific instructions rather than concepts Claude already knows; the only notable redundancy is the 'Useful Commands Reference' table repeating commands already shown inline. This matches 'efficient; minor instances of over-explanation that could be trimmed' rather than level 5, where every token earns its place.

4 / 5

Actionability

Every step is backed by copy-paste ready commands (gh pr list/view/diff, git fetch/diff, gh api permission check), a concrete summary-format template with placeholders, and two worked usage examples covering the common input cases. This matches the 'fully executable; copy-paste ready; covers common cases' anchor.

5 / 5

Workflow Clarity

Five explicitly sequenced steps with decision branches and error recovery at every fork (multiple PRs found, no PR found, gh diff failure falls back to local git diff, large diffs processed in chunks), plus prerequisite checks up front. This matches the top anchor: clear sequence, explicit checkpoints, and feedback loops for recovery.

5 / 5

Progressive Disclosure

Sections are well-organized with clear headers and no nested references, but there are minor navigation gaps: the 'sync-agent-infra maintenance map' is referenced with no path to locate it, and the crypto architecture link uses a deeply nested repo-relative path ('../../../crates/openshell-crypto/CRYPTO.md'). This fits 'good structure; references mostly clear; minor organization gaps' rather than the clean one-level-deep structure of level 5.

4 / 5

Total

18

/

20

Passed

Description

86%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: third-person voice, explicit 'Use when...' guidance, and a rich set of natural trigger synonyms. The main weakness is specificity — only two concrete capabilities are stated, understating what the skill actually does (metadata fetch, issue-acceptance checks, structured summary output).

Suggestions

Broaden the capability list to 3-4 concrete actions, e.g. 'fetch PR metadata, summarize the diff, highlight key design decisions, and flag potential concerns'.

Qualify the generic 'code review' trigger with PR context (e.g. 'review a PR' rather than bare 'code review') to reduce overlap with local-diff code-review skills.

DimensionReasoningScore

Specificity

Names the domain ('Review a GitHub pull request') with two concrete actions ('summarizing its diff and key design decisions'), matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not reach 4 because it omits several other capabilities the skill performs (fetching PR metadata, issue-acceptance checks, generating concern reports), and stays above 2 because the actions named are concrete rather than generic.

3 / 5

Completeness

Explicitly answers 'what' ('Review a GitHub pull request by summarizing its diff and key design decisions') and 'when' ('Use when the user wants to review a PR, understand changes in a branch, or get a code review summary') with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

The trigger list 'review PR, review pull request, summarize PR, summarize diff, code review, review branch, PR summary, diff summary' comprehensively covers the natural synonyms users would say, including both the abbreviation and the full phrase. It clearly exceeds the level-4 anchor (only a few natural terms missing).

5 / 5

Distinctiveness Conflict Risk

The GitHub PR review niche is clear and most triggers are distinct, but the generic terms 'code review' and 'review branch' create minor overlap risk with general code-review or diff-review skills, matching the 'mostly distinct; minor overlap risk' anchor. It is not 5 because those generic keywords could fire for a non-PR code review request.

4 / 5

Total

17

/

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: 1 missing, 1 suspicious

Warning

Total

13

/

16

Passed

Repository

NVIDIA/OpenShell

Path

.agents/skills/review-github-pr/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.