CtrlK
BlogDocsLog inGet started
Tessl Logo

babysit

Drive a PR to a clean review (Greptile 5/5, zero open threads) — ships if needed, keeps it mergeable against staging, re-triggers both Greptile and cubic, fixes real findings, replies to and resolves every thread, and loops until clean

65

Quality

78%

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/babysit/SKILL.md
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.

This is a high-quality, executable workflow skill with concrete commands, explicit validation, and well-structured sections. The only real weakness is heavy cross-referencing of `/ship`'s step internals rather than self-contained sync guidance, plus minor redundancy in the push-sync warnings.

DimensionReasoningScore

Conciseness

The body is dense and operational, assuming Claude's competence (no explanations of PRs, GraphQL, or merge conflicts), but the sync-check guidance repeats across steps 6, 7, and the hard rules, leaving minor redundancy.

4 / 5

Actionability

Copy-paste-ready `gh` and GraphQL commands with exact trigger strings ('@greptile', '@cubic-dev-ai review this PR') cover the common cases including conflicts, stale rounds, and false positives.

5 / 5

Workflow Clarity

A clear 10-step sequence with explicit validation checkpoints (state check in step 1, sync check in step 6, post-push verify in step 7) and a fix → reply → resolve → re-review feedback loop with explicit stop conditions.

5 / 5

Progressive Disclosure

Sections are well-organized with no bundle files to split out, but the skill leans heavily on `/ship`'s internal step numbers ('re-run the full sync check from `/ship` step 2'), which a reader must navigate externally — a minor organization gap.

4 / 5

Total

18

/

20

Passed

Description

67%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 specific and clearly distinct, but it answers 'what' thoroughly without an explicit 'when' trigger clause, and the most natural user phrasings are absent from the description itself. Adding a 'Use when...' sentence with the 'babysit'/'keep working the reviews' phrasing would lift completeness and trigger_term_quality.

Suggestions

Add a 'Use when the user says "babysit this PR" or wants reviews worked until clean' clause to explicitly answer 'when' and surface the natural trigger terms.

Pull the natural phrasings ('babysit', 'keep working the reviews until it's clean') up into the description so trigger_term_quality matches the body.

Consider trimming the long em-dash action list slightly so the trigger guidance is not crowded out.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'ships if needed, keeps it mergeable against staging, re-triggers both Greptile and cubic, fixes real findings, replies to and resolves every thread, and loops until clean' — covering the workflow comprehensively.

5 / 5

Completeness

The 'what' is explicit and detailed, but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Domain keywords like 'PR', 'clean review', 'threads', and 'Greptile 5/5' appear, but the natural user phrasings ('babysit', 'keep working the reviews') live in the body rather than the description, so common variations are missing.

3 / 5

Distinctiveness Conflict Risk

A clear niche — driving a PR to Greptile 5/5 with zero open threads across two named bots — with distinct triggers and minimal overlap with other skills.

5 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
simstudioai/sim
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.