pipeline-investigation

Investigates Buildkite pipeline failures to find root causes. Returns structured JSON to the parent for formatting. Triggers when users ask about failing pipelines, build errors, or need help debugging CI/CD issues. Accepts Buildkite build URLs or build numbers and performs deep investigation.

Quality

82%

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

77%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 investigation skill with concrete commands and strong validation feedback loops. Its main weaknesses are repeated boilerplate that bloats the token budget and a monolithic structure that inlines reference-grade material rather than splitting it out.

Suggestions

Factor the `TOKEN=$(bk auth token)` extraction into a single defined snippet and reference it, instead of repeating the full curl+Authorization block in Steps 2, 4, 6, 7, 9, and 10.

Move the Build Scheduling/Queue Behaviour theory and the ASG/Terraform sizing command into a separate reference file (e.g. QUEUE-BEHAVIOUR.md) linked from the main workflow, so the core investigation steps stay lean.

Merge the duplicated `bk build view {build_number} -p {pipeline} --json` guidance from Step 5 back into Step 2, and have Step 5 reference it rather than re-stating the command.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the `TOKEN=$(bk auth token)` boilerplate is repeated verbatim across roughly eight command blocks and `bk build view {build_number} -p {pipeline} --json` is duplicated between Step 2 and Step 5 — real tightening opportunities that keep it below "efficient with only minor trimmable instances".	3 / 5
Actionability	Fully executable, copy-paste-ready commands throughout: exact `bk` CLI invocations with flags, concrete REST URLs with `{org}/{pipeline}/{build_number}` parameters, `jq` filters, and `gh` commands, covering the common investigation cases (view build, list agents, retrieve logs, download artifacts, cancel, rebuild).	5 / 5
Workflow Clarity	A clearly sequenced 13-step workflow with explicit validation/feedback checkpoints — Step 10 re-runs the build to confirm flaky-vs-real before classifying, Step 13 (marked CRITICAL) checks for already-pushed fixes before recommending a fix, and the Notes section reinforces both as a checklist.	5 / 5
Progressive Disclosure	Well-sectioned into Prerequisites, Investigation Workflow, Scheduling, Output, and Notes, but it is a ~330-line monolithic SKILL.md with zero external references; tangential reference material (the ASG/Terraform command and the Build Scheduling theory) is inlined into the main flow where a one-level-deep reference file would reduce load, so the simple-skill exception (under 50 lines) does not apply.	3 / 5
	Total	16 / 20 Passed

Description

87%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, third-person description that explicitly states both capability and activation triggers with concrete natural-language phrases. It is held back only by one generic verb ("deep investigation") and a few missing synonyms, not by any structural gap.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Investigates Buildkite pipeline failures to find root causes", "Returns structured JSON to the parent for formatting", "Accepts Buildkite build URLs or build numbers" — but "performs deep investigation" is generic and "Returns structured JSON" is an implementation detail rather than a user-facing capability, leaving minor gaps in coverage.	4 / 5
Completeness	Clearly answers both what ("Investigates Buildkite pipeline failures to find root causes") and when with an explicit concrete trigger clause ("Triggers when users ask about failing pipelines, build errors, or need help debugging CI/CD issues"), matching the anchor that requires explicit what-and-when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage with "failing pipelines", "build errors", and "debugging CI/CD issues" plus the input formats "Buildkite build URLs or build numbers", but a few common synonyms a user might say (e.g. "build failures", "broken build", "CI failing") are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — Buildkite-specific CI/CD failure investigation — with distinct triggers ("Buildkite", "failing pipelines", "build errors") and minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mock-server/mockserver-monorepo
Path: .opencode/skills/pipeline-investigation/SKILL.md
Commit: 817ee95

Reviewed: 1 day 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.