build-monitor

Continuously monitors Buildkite pipeline builds, detects failures, investigates root causes, fixes issues, and pushes fixes. Runs a polling loop that checks build status at configurable intervals for a configurable duration. Use when the user says "monitor builds", "watch pipeline", "watch CI", "continuous monitoring", "keep checking builds", or wants automated build-fix cycles.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A highly actionable, well-sequenced monitoring workflow with strong validation and fail-closed gates around the risky push path. The main costs are duplicated commit-workflow content and a long single-file body that inlines material suited to a reference file.

Suggestions

Remove the re-listed commit workflow steps (Step 6 a–e) and rely on the existing pointer to .opencode/rules/commit-workflow.md — the gate chain is described twice, roughly doubling that section's token cost.

Move the Failure Patterns Reference table (and optionally the authentication prerequisites) into a references/ file, keeping SKILL.md as a concise overview that links to it — this trims ~60 lines from the always-loaded body.

Dimension	Reasoning	Score
Conciseness	The body is command-dense and mostly earns its tokens, but Step 6 first delegates to '.opencode/rules/commit-workflow.md' and then re-lists the entire commit workflow (a–e), and the status-report/summary templates add padding — 'minor instances of over-explanation that could be trimmed' rather than lean throughout.	4 / 5
Actionability	Fully executable guidance: copy-paste invocations of bk-pipeline-status.sh with flag examples, an exit-code/agent-state diagnosis table, an exact 'mvnw test -pl {module} -Dtest={TestClassName}#{testMethodName}' command, and concrete grep patterns for locating failures — common cases are covered with runnable commands.	5 / 5
Workflow Clarity	A clearly sequenced loop (prerequisites → fetch → classify → investigate → fix → adversarial review → commit/push → verify) with explicit validation checkpoints: stop-and-report on auth failure, fail-closed commit gates ('if any gate fails ... do NOT commit'), re-verify after review feedback, and post-push build verification — textbook feedback loops for a destructive push-to-master operation.	5 / 5
Progressive Disclosure	Good structure with clear headers and well-signaled pointers to detail files (scripts/ci/bk-pipeline-status.sh, docs/infrastructure/ci-cd.md, .opencode/rules/*.md), but the ~339-line single-file body inlines the Failure Patterns Reference table and the auth prerequisites that belong in a separate reference file — 'minor organization gaps' rather than an appropriately split overview.	4 / 5
	Total	18 / 20 Passed

Description

96%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: third-person, concrete, comprehensive on what-and-when, with six natural trigger phrases. Only weakness is mild overlap risk between the generic CI/monitoring trigger phrases and broader loop/watch skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'monitors Buildkite pipeline builds, detects failures, investigates root causes, fixes issues, and pushes fixes' — plus a concrete mechanism ('polling loop that checks build status at configurable intervals'), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both questions: the 'what' is the full monitor→investigate→fix→push pipeline, and the 'when' is a literal 'Use when the user says ...' clause with concrete trigger phrases — the exact shape of the 5-anchor example.	5 / 5
Trigger Term Quality	Six natural trigger phrases with genuine synonym coverage — 'monitor builds', 'watch pipeline', 'watch CI', 'continuous monitoring', 'keep checking builds', 'automated build-fix cycles' — all phrasings a user would plausibly say, matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	The Buildkite pipeline niche with fix cycles is clearly distinct, but 'watch CI' and 'continuous monitoring' are phrases that could also match generic CI-watching or recurring-loop skills, so it sits at 'mostly distinct; minor overlap risk' rather than the 5 anchor's minimal conflict risk.	4 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 14 missing, 14 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: mock-server/mockserver-monorepo
Path: .opencode/skills/build-monitor/SKILL.md
Commit: f66c975

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.