CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-monitor-pr-ci

Monitors a PR's CI checks and review comments until all pass and issues are resolved. Auto-fixes CI failures, addresses inline review comments, replies, and resolves threads. Use when watching CI status, waiting for checks to pass, fixing CI errors, or resolving review feedback on a pull request.

66

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

The content is highly actionable and well-structured with clear sequencing and error handling, but it is somewhat verbose and lacks a mandatory validation checkpoint before destructive push operations, capping workflow clarity.

Suggestions

Add a mandatory pre-push validation step (e.g. run lint/tests locally and only push when green) to lift the workflow_clarity cap for destructive/batch operations.

Consolidate redundant guidance — merge the 'Important Notes' section and the repeated >Note blocks into the relevant steps, and de-duplicate the Step 3g blocked-state report against the Step 4 final report.

Trim explanatory prose around fallbacks and re-run rules to reduce token load without losing the executable commands.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence, but ~360 lines include redundant prose, repeated >Note blocks, and restated rules (e.g. Step 3g vs final report, 'Important Notes' rehashing earlier guidance) that could be tightened.

3 / 5

Actionability

Fully executable guidance throughout — concrete `yarn agent:check` and `gh` commands, exact GraphQL mutations, precise JSON field paths, and copy-paste-ready bash covering the common cases.

5 / 5

Workflow Clarity

Steps are clearly sequenced with feedback loops and per-iteration state checks, but destructive/batch operations (auto-commit, push, resolve threads, request re-review) lack a mandatory pre-push validation checkpoint; the only validation ('if quick to check') is conditional, so the batch/destructive cap of 3 applies.

3 / 5

Progressive Disclosure

Single-file skill with no bundle, organized into clean navigable sections (Usage, Input, Step 0–4, Polling Rules, Important Notes, Error Handling); per the simple-skill guidance this well-organized structure scores 5.

5 / 5

Total

16

/

20

Passed

Description

88%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, complete, and uses third person with explicit trigger guidance, scoring well across all dimensions. Minor room to broaden trigger-term synonyms and sharpen distinctiveness.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Monitors a PR's CI checks and review comments', 'Auto-fixes CI failures, addresses inline review comments, replies, and resolves threads' — giving comprehensive coverage of the PR-monitoring domain.

5 / 5

Completeness

Explicitly answers both 'what' (monitors, auto-fixes, addresses, replies, resolves) and 'when' ('Use when watching CI status, waiting for checks to pass, fixing CI errors, or resolving review feedback on a pull request').

5 / 5

Trigger Term Quality

Natural user-facing phrases like 'watching CI status', 'waiting for checks to pass', 'fixing CI errors', and 'resolving review feedback' are present, but a few common variations (e.g. 'build is red', 'CI is failing') are absent.

4 / 5

Distinctiveness Conflict Risk

A clear niche (PR CI monitoring plus review-thread resolution) with specific triggers; only minor overlap risk with broader CI or review skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
OneKeyHQ/app-monorepo
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.