CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr

Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/pr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An exceptionally lean, well-structured instruction skill: a concrete template, decision rules for each section, and honest constraints on evidence sourcing, all with no wasted tokens. The only real gap is the absence of a worked example showing a completed PR body.

DimensionReasoningScore

Conciseness

The body is telegraphic throughout — "Consume the verify protocol's output... Present before/after pairs: the exact check that failed before and passes after, quoted from the output itself" — with zero padding and no explanation of concepts Claude already knows. The single sentence of framing ("the PR body is the one artifact a reviewer outside the session reads") earns its place by justifying the constraint, matching the lean-and-efficient anchor.

5 / 5

Actionability

The template block is copy-paste ready and the visual-matching list ("logic or an algorithm → pseudocode", "UI structure → a component tree") plus the ADR test's three questions give concrete decision rules. It is not 5 because there is no worked example of a filled-out PR body, and a few directives ("the smallest view that makes the point") depend on judgment the skill never grounds in a sample.

4 / 5

Workflow Clarity

The section order (Summary → Evidence → Reversibility → Language) mirrors the template and defines a coherent drafting sequence, with embedded checkpoints like "Never re-collect evidence here and never claim evidence the verify pass did not produce" and the three-question ADR test gating the rollback classification. It is not 5 because the steps are never enumerated as a sequence and there is no explicit verify/retry loop for the drafted body.

4 / 5

Progressive Disclosure

A single well-sectioned SKILL.md with no bundle files to split — the skill is appropriately self-contained, and its external pointers ("Terms come from `GLOSSARY.md` where a glossary exists") are one level deep and clearly signaled. Every section is short and navigable; nothing that belongs in a separate file is inlined.

5 / 5

Total

18

/

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.

A specific, distinctive description that clearly states what the skill produces, undermined by the complete absence of when-to-use guidance and by reliance on internal jargon ("OMC's paper trail", "ADR test") over natural trigger phrases like "pull request". The what is strong; the when is missing.

Suggestions

Add an explicit trigger clause, e.g. "Use when a session opens or updates a pull request, or when landing work that will be reviewed through a PR" — the Triggers section already contains this guidance; surfacing it in the description would lift completeness from 3 to 5.

Spell out "pull request" at least once and add natural variations such as "PR description" or "pull request body" so users who phrase the request differently still match.

Replace or gloss internal jargon ("OMC's paper trail", "verify protocol", "ADR test") with at least one plain-language phrase, since outside readers cannot map these terms to a need.

DimensionReasoningScore

Specificity

Quotes like "Draft a PR body" and "the smallest visual that proves the change", "reversibility from the ADR test on the diff" name the domain and several concrete components of the deliverable. It falls short of 5 because coverage is partial (no mention of the summary section's claim structure or output format) but well above 3, which expects only 1-2 concrete actions.

4 / 5

Completeness

The "what" is clear ("Draft a PR body from OMC's paper trail" with its three components), but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description, capping completeness at 3 per the judging guidelines. It is not 2 because the "what" is concrete and multi-part, not vague.

3 / 5

Trigger Term Quality

"PR body", "Draft", "reversibility", "evidence" are natural terms a user requesting a pull-request description would say, matching the anchor for good keyword coverage with a few natural terms missing. It is not 5 because "pull request" is never spelled out and common variations like "PR description" or "review" are absent; it is above 3 because the core natural phrase "PR body" is exactly what users ask for.

4 / 5

Distinctiveness Conflict Risk

"Draft a PR body" carves a clear niche (PR descriptions assembled from a session's verify evidence and ADRs) that few skills occupy, with only minor overlap risk against commit-message or general writing skills. It is not 5 because "PR" is a broad surface and the description does not state its triggers, leaving modest ambiguity against adjacent code-review/summary skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 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

Total

14

/

16

Passed

Repository

Yeachan-Heo/oh-my-claudecode

Path

skills/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.