CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-style

PR formatting reference — title, body template, label mapping, assignment, and draft policy. Invoked by pr/create and pr/update-desc commands to ensure consistent PR formatting.

Quality

76%

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 ./.claude/skills/pr-style/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 a minimal auto-generated redirect stub: maximally token-efficient, but it delegates 100% of the skill's substance to an external file (~/.agents/skills/pr-style/SKILL.md) that is not part of the bundle and does not exist in this environment, leaving the skill non-functional as shipped. Without the target file or any inline fallback content, actionability, workflow clarity, and progressive disclosure all bottom out at the pointer level.

Suggestions

Ship the referenced formatting content inside the skill bundle (e.g., a references/ file with the title format, body template, label mapping, assignment rules, and draft policy) instead of relying solely on the external absolute path ~/.agents/skills/pr-style/SKILL.md, which resolves only on machines where that shared skill happens to be installed.

Add a fallback/validation checkpoint to the one-step workflow: state what to do if the shared skill file is missing (e.g., fall back to the bundled reference, or fail with a clear message) so the delegation step has an error-recovery path.

Inline a minimal summary of the core rules (a title-format example and a body-template skeleton) in SKILL.md so the skill remains actionable when read in isolation, keeping the full detail in the external or referenced file.

DimensionReasoningScore

Conciseness

The body is two lines: a provenance comment and one directive ("Load and follow the shared skill at ~/.agents/skills/pr-style/SKILL.md"). Nothing pads or over-explains; every token serves the redirect, matching anchor 5 ("lean and efficient; every token earns its place"). It is clearly above anchor 4, which still expects some trimmable over-explanation.

5 / 5

Actionability

The single directive is concrete and unambiguous (an exact action and path), so it clears anchor 2's "high-level hints". But it stops at a pointer: none of the actual formatting guidance (title format, body template, label mapping, assignment, draft policy) exists in the body or the bundle, and the referenced file "~/.agents/skills/pr-style/SKILL.md" is not present, so as shipped the skill delivers no executable value — below anchor 4's "concrete code or commands with minor gaps".

3 / 5

Workflow Clarity

The single action ("Load and follow the shared skill") is unambiguous, which under the simple-skill exception could score 5. However the one-step workflow dead-ends: the delegation target is missing from the bundle, and there is no checkpoint or fallback for that case (e.g., what to do if the file cannot be found), matching anchor 3's "sequence present but checkpoints missing or implicit".

3 / 5

Progressive Disclosure

The reference is one level deep and clearly signaled — the entire body is the pointer — but it points to an absolute home-directory path outside the skill bundle (no references/, scripts/, or assets/ directories exist), and that path does not resolve in this environment. The body also offers no overview of what the referenced material contains, fitting anchor 3 ("some structure but could be better organized") rather than anchor 4's "most content is appropriately placed".

3 / 5

Total

14

/

20

Passed

Description

78%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: it states a concrete, well-scoped purpose with explicit command-based invocation triggers, and stays lean without fluff or over-claims. The main residual gaps are the absence of spelled-out natural-language triggers ("pull request", "use when creating a PR") and topic-noun phrasing instead of action verbs.

DimensionReasoningScore

Specificity

Enumerates five concrete coverage areas — "title, body template, label mapping, assignment, and draft policy" — plus an explicit purpose ("ensure consistent PR formatting"), which exceeds anchor 3's "1-2 concrete actions, but not comprehensive". It falls short of anchor 5 only because the items are topic nouns rather than named actions (no "formats", "applies", "maps" verbs), leaving the actual operations implied.

4 / 5

Completeness

Both parts are present: the "what" is the enumerated formatting reference (title, body template, label mapping, assignment, draft policy), and the "when" is explicit — "Invoked by pr/create and pr/update-desc commands" — so the missing-trigger cap of 3 does not apply. Not anchor 5 because the "when" is stated descriptively ("Invoked by...") rather than as concrete "Use when..." trigger phrases, and no natural-language invocation conditions are given.

4 / 5

Trigger Term Quality

Contains good natural keyword coverage: "PR formatting", "title", "body template", "label", "assignment", "draft", plus the concrete command triggers "pr/create" and "pr/update-desc". Anchor 5 (comprehensive synonyms/extensions) is not met because "pull request" is never spelled out and no natural-language trigger phrases (e.g., "when creating a PR") are given, but coverage is clearly above anchor 3's "missing common variations".

4 / 5

Distinctiveness Conflict Risk

Clear niche (PR formatting policy) with distinct triggers: the binding to the two named commands "pr/create" and "pr/update-desc" plus domain-specific terms ("label mapping", "draft policy") minimize conflict risk with neighboring git/PR skills, matching anchor 5's "clear niche with distinct triggers; minimal conflict risk". Anchor 4's "minor overlap risk with closely related skills" would require a less tightly scoped trigger than the explicit command binding.

5 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.claude/skills/pr-style/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.