CtrlK
BlogDocsLog inGet started
Tessl Logo

babysit-pr

Monitor a PR, fix feedback and CI failures until fully green for 30 min. Run with /babysit-pr <number>

65

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/babysit-pr/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 workflow with strong validation checkpoints, but it is a verbose single-file monolith with inline dated anecdotes and no progressive disclosure to separate reference files. Tightening emphasis and splitting out detailed sub-procedures would improve it.

Suggestions

Move dated incident justifications (2026-05-05 stash, 2026-06-08 PR #1097) into a short "Past failures / lessons" section or trim them to one line, to remove time-sensitive padding from the main flow.

Split the changeset special-case and the merge procedure into referenced files (e.g., CHANGESETS.md, MERGING.md) and link to them from the tick steps to add one-level-deep progressive disclosure.

Reduce repeated bolded emphasis (e.g., "EVERY tick, with no exceptions") to a single clear statement; the surrounding steps already enforce it.

DimensionReasoningScore

Conciseness

The body is dense with genuinely useful operational detail Claude would not know, but it is padded with repeated bolded emphasis, long war-story parentheticals, and inline dated incident references (2026-05-05, 2026-06-08) not placed in a deprecated section, which the rubric penalizes.

2 / 3

Actionability

It provides fully executable, copy-paste-ready commands throughout (git status --short, the gh/jq unaddressed-comments pipeline, gh pr checks, pnpm run prep, a concrete .changeset/*.md shape, gh pr merge --squash --admin), matching the anchor for fully executable guidance.

3 / 3

Workflow Clarity

The tick is a clearly sequenced process (Step 0 through PR checks 1-6) with explicit validation checkpoints (pnpm run prep verify, 30-min/10-min soak timers, the final unaddressed-comments gate), feedback loops for error recovery, and a 5-condition merge checklist.

3 / 3

Progressive Disclosure

It is a single monolithic ~155-line file with no bundle references and no signaled deeper references; detailed sub-procedures (changeset special case, merge procedure) are inline rather than split out, so it has structure but content that could be separate remains inline.

2 / 3

Total

10

/

12

Passed

Description

82%

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, distinct description with natural trigger terms, but it lacks an explicit "Use when..." clause, relying on invocation syntax instead of a stated trigger condition. Adding a one-line use-when trigger would raise completeness.

Suggestions

Add an explicit trigger clause such as "Use when you need to keep a PR green by fixing CI failures and review feedback until it stays green for 30 minutes."

Expand trigger-term coverage with common variations users might say (e.g., "build failures", "review comments", "tests failing").

DimensionReasoningScore

Specificity

"Monitor a PR, fix feedback and CI failures until fully green for 30 min" lists multiple distinct concrete actions (monitor, fix feedback, fix CI failures, time-boxed green target), matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

It clearly states what the skill does, but "when" is only implied via the invocation syntax "Run with /babysit-pr <number>" rather than an explicit "Use when..." trigger, so completeness caps at 2 per the guideline.

2 / 3

Trigger Term Quality

Terms like "PR", "feedback", "CI failures", "green", and "/babysit-pr" are natural phrases a user would say when needing this skill, giving good coverage rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The PR-babysitting niche with a distinct slash-command trigger is clearly distinguishable and unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
BuilderIO/agent-native
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.