CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-tour

A skill that provides a guided tour of a pull request, highlighting key changes, walking the developer through the code, and explaining the purpose of each modification.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/pr-tour/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.

A genuinely lean, well-scoped instruction skill: no padding, a clear presentation structure, and appropriate size for its purpose. The main weaknesses are the confusing 'unchanged or even uncommited changes' wording (plus its typo) and the absence of any concrete command for obtaining the PR diff.

Suggestions

Rewrite the confusing first bullet — e.g. "Review the PR's diff plus any uncommitted local changes" — and fix the 'uncommited' typo.

Add one concrete way to obtain the changes, e.g. `gh pr diff` or `git diff main...HEAD`, so the familiarization step is executable rather than implied.

DimensionReasoningScore

Conciseness

Three lean bullets with zero padding, no explanation of concepts Claude already knows, and full assumption of Claude's competence — every token earns its place, matching the anchor-5 example exactly.

5 / 5

Actionability

The guidance specifies a concrete output structure (high-level summary first, then noteworthy changes grouped into context-appropriate categories, kept concise), which is actionable for an instruction-only skill. It misses a 5 because the common case of how to obtain the changes (e.g. `gh pr diff`, `git diff main...HEAD`) is left unspecified.

4 / 5

Workflow Clarity

The two-phase sequence (familiarize with the changes, then present the tour) is clear and needs no validation for this non-destructive task, but the first step's phrase "including unchanged or even uncommited changes" is genuinely ambiguous (what is an unchanged change?), keeping it from the unambiguous single-action 5 that the simple-skill exception would otherwise allow.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references; nothing that belongs in a separate file is inlined, and the three bullets are trivially navigable. Per the simple-skill scoring note this earns a 5 on organization alone.

5 / 5

Total

18

/

20

Passed

Description

55%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 gives a clear, specific, third-person account of what the skill does, but it never says when to use it. Adding an explicit 'Use when...' clause with natural trigger terms (walkthrough, PR, diff, review) would raise both completeness and trigger-term quality substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a walkthrough or tour of a pull request, wants changes explained, or says 'walk me through this PR/diff'."

Include natural synonyms and abbreviations users actually say — "PR", "diff", "review", "walkthrough" — alongside "pull request".

Sharpen the distinction from code-review skills, e.g. noting the tour focuses on understanding/orientation rather than finding defects.

DimensionReasoningScore

Specificity

The description names the domain ("pull request") and several actions ("guided tour", "highlighting key changes", "walking the developer through the code", "explaining the purpose") in third person with no fluff. It falls short of a 5 because those actions are facets of a single activity rather than multiple distinct capabilities with comprehensive coverage.

4 / 5

Completeness

The 'what' is clear (guided tour of a PR highlighting and explaining changes), but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2, because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Relevant terms like "pull request", "guided tour", and "key changes" are present, but common variations users would naturally say are missing: no "PR", "diff", "review", or "walkthrough". This matches anchor 3 (relevant keywords but missing variations/synonyms) rather than anchor 4.

3 / 5

Distinctiveness Conflict Risk

"Guided tour of a pull request" names a real niche, but "highlighting key changes... explaining the purpose of each modification" substantially overlaps code-review and PR-summary skills, and with no explicit trigger terms the boundary between them is unclear. This is more than the 'minor overlap' of anchor 4, fitting anchor 3 instead.

3 / 5

Total

13

/

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

chattocorp/chatto

Path

.agents/skills/pr-tour/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.