CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ops-pr-review

Run the shared AI review of an OPRE-OPS pull request — Flexion's code-review-orchestrator, held to the team rubric in docs/REVIEW.md (S0–S3 severities, risk tiers, pre-existing findings, the verdict line). Use whenever someone asks to review an OPS PR or branch ("review PR 6436", "review my PR", "run the shared review", "is this ready for human review", "re-review after my changes"). Prefer this over calling code-review-orchestrator directly in this repo, so every review uses the same bar for "done".

Quality

91%

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.

The body is an unusually executable and well-sequenced process skill: exact commands, complete scripts, explicit validation and fallback paths, and correct delegation of the changing rubric to docs/REVIEW.md. Its only costs are a few long explanatory passages and a single-file layout that carries material a split into reference files might offload.

DimensionReasoningScore

Conciseness

The body is dense with operational specifics and no concept explanations Claude already knows, but a few justification passages could be tightened — e.g. 'Base copies come from the **merge-base**, the commit the PR branched from, not the base branch tip: that is what the PR diff is measured against...' — matching anchor 4 rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Fully executable throughout: exact gh/jq commands, a complete worktree and base-copy bash script, literal verdict strings ('Verdict: BLOCKING (n)'), and the review.json payload schema with side: "RIGHT"/"LEFT" line-placement rules — copy-paste ready guidance covering the common cases.

5 / 5

Workflow Clarity

Six clearly sequenced sections with explicit validation checkpoints and error-recovery loops: plugin availability check, baseline validation via git cat-file -e and merge-base --is-ancestor with a documented full-review fallback, draft-PR and show-before-post gates, exact-match label checks, and worktree prune for interrupted runs — matching anchor 5. No destructive or batch operation lacks validation, so no cap applies.

5 / 5

Progressive Disclosure

With no bundle files, all detail that varies run-to-run is correctly delegated one level deep to a clearly signaled reference ('Read docs/REVIEW.md in full') and an external plugin skill, with clean section organization; however the ~150-line body keeps posting and scratch-directory material inline where a reference file split could help, matching anchor 4 over anchor 5.

4 / 5

Total

18

/

20

Passed

Description

95%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 explicit about both what the skill does and when to use it, with verbatim natural trigger phrases and a clearly bounded niche. Its only weakness is that the capability list is a compact summary rather than a full enumeration of the review's actions.

DimensionReasoningScore

Specificity

Names the domain (OPRE-OPS pull request review) and several concrete actions/artifacts — 'S0–S3 severities, risk tiers, pre-existing findings, the verdict line' — but the action set is summarized rather than comprehensively enumerated, matching anchor 4 over anchor 5.

4 / 5

Completeness

Explicitly answers both 'what' ('Run the shared AI review of an OPRE-OPS pull request — Flexion's code-review-orchestrator, held to the team rubric in docs/REVIEW.md') and 'when' ('Use whenever someone asks to review an OPS PR or branch') with concrete trigger phrases, matching anchor 5.

5 / 5

Trigger Term Quality

Provides verbatim natural trigger phrases users would say — '"review PR 6436", "review my PR", "run the shared review", "is this ready for human review", "re-review after my changes"' — covering both PR and branch variations, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche ('OPRE-OPS pull request', 'in this repo') and directly disambiguates against the nearest competing skill ('Prefer this over calling code-review-orchestrator directly in this repo'), giving minimal conflict risk per anchor 5.

5 / 5

Total

19

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

Repository

HHS/OPRE-OPS

Path

.claude/skills/ops-pr-review/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.