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, triggers Greptile/Cursor Bugbot, fixes real findings, replies to and resolves every thread, and loops until clean

62

Quality

72%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced review-loop workflow with strong validation checkpoints, weakened only by verbose justifications that pad the body and a monolithic single-file structure that keeps detail inline rather than offloaded to references.

Suggestions

Tighten the prose justifications in steps 1, 6, and 7 to one line each — keep the gotcha, drop the elaboration — to lift conciseness toward 3.

Consider moving the detailed command pitfalls (paging logic, `--reverse`, `--force-with-lease` rules) into a references/GOTCHAS.md and signaling it from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient with copy-paste commands, but the multi-paragraph justifications in steps 1, 6, and 7 (e.g. the `[.comments[]] | last | .body` vs `tail -1` aside and the `--reverse` rationale) could be tightened without losing the gotcha; not level 1 because it avoids generic concept explanations Claude already knows, and not level 3 because several passages are padded.

2 / 3

Actionability

Provides fully executable, copy-paste-ready `gh` CLI and GraphQL snippets for every operation (state check, replies, resolve, re-trigger), matching the anchor for executable code and specific examples.

3 / 3

Workflow Clarity

A clearly sequenced 10-step loop with explicit validation checkpoints (mergeable check before action, full /ship sync check before every push, post-push commit-list verify) and feedback loops (fix → reply → resolve → re-review), matching the clear-sequence-with-validation anchor for risky force-push/rebase operations.

3 / 3

Progressive Disclosure

Well organized into named sections but monolithic — all content (including long gotcha explanations) is inline in one file with no bundle references to split detail into, so it stops at 'some structure, content that should be separate is inline' rather than the one-level-deep reference pattern of level 3.

2 / 3

Total

10

/

12

Passed

Description

67%

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, action-rich description that carves out a distinct niche, but it lacks an explicit 'when to use' trigger clause and leans on internal jargon (Greptile/Cursor names, 5/5 scoring) rather than the natural phrasing a user would utter.

Suggestions

Add a 'Use when...' clause with natural trigger phrasing (e.g. 'Use when the user says "babysit this PR" or wants reviews worked until clean') to lift completeness and trigger-term quality to 3.

Soften internal jargon by pairing 'Greptile 5/5, zero open threads' with user-facing terms like 'review bots', 'open comments', and 'clean PR'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "ships if needed", "keeps it mergeable against staging", "triggers Greptile/Cursor Bugbot", "fixes real findings", "replies to and resolves every thread", "loops until clean" — matching the anchor for multiple specific concrete actions rather than the partial domain-only level 2.

3 / 3

Completeness

It thoroughly answers "what" but provides no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 rather than 3.

2 / 3

Trigger Term Quality

Contains relevant keywords ("PR", "review", "clean review", "threads") but is dense with technical jargon ("Greptile 5/5", "Cursor Bugbot", "zero open threads") and omits the natural phrasing a user would actually say (e.g. "babysit this PR"), so it does not reach full natural-term coverage; not level 1 because PR/review are genuinely user-spoken terms.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — driving a Greptile/Cursor review loop to 5/5 with zero open threads — with distinctive triggers unlikely to overlap with unrelated skills, matching the clear-niche anchor.

3 / 3

Total

10

/

12

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.