CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

transitions-agent

Scan a codebase for missing, janky, or inconsistent UI motion and fix it with transitions.dev recipes. ALWAYS use this skill when the user's message is or contains a transitions-agent command (npx transitions-agent, npx transitions-agent fix, any variant) - the command is a request for the full guided flow, not just command execution. Also use when the user asks about UI transitions, animations, motion quality, a motion score, janky or missing transitions, "polish the motion", "fix the animations", or whether the motion is good after UI changes.

Quality

89%

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

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.

An exceptionally actionable skill body: every step is a copy-paste command, validation and error-recovery loops are explicit, and nothing wastes tokens teaching known concepts. The only tightening available is consolidating the repeated never-touch-main and fix-approval rules, and optionally moving CI setup into a reference file.

Suggestions

State the never-push-to-main and fix-needs-approval rules once (in Rules) and reference them elsewhere, trimming the repeats in Workflow steps 2 and 4 and the CI setup section.

Consider moving the CI setup section into a one-level-deep reference file (e.g., ci-setup.md) to keep SKILL.md a lean overview of the core scan/fix flow.

DimensionReasoningScore

Conciseness

Dense, instruction-only prose with no explanations of concepts Claude already knows; every command line earns its place. Minor redundancy keeps it below anchor 5: the never-touch-main rule appears three times ("it never touches the main branch", "never straight to main", "Never push to the main branch") and the fix-approval gate is stated both in the intro ("every fix step needs the user's go-ahead first") and in Rules.

4 / 5

Actionability

Fully executable copy-paste commands cover every common case: "npx transitions-agent@latest --json", "fix --yes", "fix --mode revamp --yes", "signup", "init-ci --yes", "--license <key>" fallback, "--pr", per-PR labels, and "--no-auto-fix". Failure modes get concrete handling too (sandbox network symptoms with ETARGET/ENOTFOUND/EAI_AGAIN signatures and the exact remediation).

5 / 5

Workflow Clarity

Clear numbered sequence (Scan → Present options → License → Verify) with an explicit validation step ("re-run the scan and report the score change") and error-recovery loops: unsaved license key → "--license <key>" on every fix; sandbox network failure → re-run with network access; CI → "Finish when it says 'CI is fully set up'". Gating fixes on explicit user choice satisfies the destructive/batch-operation validation requirement.

5 / 5

Progressive Disclosure

A single-file skill with no bundle files (no references/, scripts/, or assets/ exist) and well-organized sections (Workflow, CI setup, Network, Rules). The body runs ~66 lines, just over the under-50-line simple-skill case where sections alone earn a 5, and CI setup is a distinct sub-workflow that could live in a one-level-deep reference file — good structure with a minor organization question, matching anchor 4.

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 with explicit what/when structure and excellent trigger-term coverage including quoted user phrasings and exact commands. Its only weakness is capability coverage: it names just scan-and-fix while the skill also handles CI setup and verification, costing it specificity points.

Suggestions

Mention the init-ci/CI setup capability (e.g., "set up GitHub Actions workflows for automatic motion fixes") so the description covers what the skill body actually does.

Include the post-fix verification behavior (re-running the scan and reporting the score change) as a concrete capability to round out coverage.

DimensionReasoningScore

Specificity

Names two concrete actions — "Scan a codebase for missing, janky, or inconsistent UI motion and fix it with transitions.dev recipes" — matching anchor 3's 1-2 concrete actions. Coverage has real gaps (CI setup via init-ci, verification/PR flows are capabilities never mentioned), keeping it below anchor 4's "minor gaps".

3 / 5

Completeness

Explicitly answers both: what ("Scan a codebase for missing, janky, or inconsistent UI motion and fix it with transitions.dev recipes") and when ("ALWAYS use this skill when the user's message is or contains a transitions-agent command... Also use when the user asks about UI transitions..."). Clear what + when with concrete trigger phrases, matching the anchor 5 example.

5 / 5

Trigger Term Quality

Comprehensive natural-language coverage: "UI transitions, animations, motion quality, a motion score, janky or missing transitions, 'polish the motion', 'fix the animations', or whether the motion is good", plus the exact commands ("npx transitions-agent, npx transitions-agent fix, any variant"). This matches anchor 5's comprehensive synonyms plus concrete command triggers.

5 / 5

Distinctiveness Conflict Risk

The transitions-agent/transitions.dev command triggers create a clear niche with minimal conflict, but natural phrases like "animations" and "fix the animations" have minor overlap with generic CSS-animation skills. Mostly distinct with minor overlap risk — anchor 4.

4 / 5

Total

17

/

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

Jakubantalik/transitions.dev

Path

agent/skill/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.