ci-monitor

Use when changing CI readiness, forge check collection, reruns, CI timeouts, or PR lifecycle monitoring.

Quality

45%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/ci-monitor/SKILL.md

Quality

Content

43%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 body is rich in non-obvious domain contracts and correctly delegates ownership to specific source/docs files, but it reads as a dense reference wall rather than a navigable, sequenced workflow. Tightening prose and adding explicit checkpoints would materially improve it.

Suggestions

Break the long run-on bullets into shorter rules or a short numbered sequence with explicit validation checkpoints, especially around the rerun budget and the orphan-abort reap operations.

Split the dense collapse-ordering and rerun-lifecycle material into a referenced file (e.g. references/ci-checks.md) and keep SKILL.md as a concise overview with one-level-deep links.

Promote the few actionable commands (e.g. the abort invocation, the test names to run) into a short "How to verify" or "Commands" section so executable guidance is easy to find.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and does not pad with basic concepts, but the bullets are long run-on sentences crammed with parenthetical asides and inline regression-test lists that could be tightened for clarity.	3 / 5
Actionability	It gives one concrete command ("no-mistakes axi abort --run <id>") and many specific file pointers, but most of the body is declarative contract/rule documentation rather than executable step-by-step guidance.	3 / 5
Workflow Clarity	The content is declarative domain rules rather than sequenced multi-step workflows, and the destructive/batch operations (reruns, orphan abort) lack explicit validate-fix-retry checkpoints, capping workflow clarity below 3.	2 / 5
Progressive Disclosure	There are no skill bundle files and the body is a flat, mostly unsectioned bullet list with inlined dense content, though it does signal where detailed truth lives ("AGENTS.md owns the contract", "user-facing semantics owned by docs/...").	3 / 5
	Total	11 / 20 Passed

Description

47%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 provides a clear, specific trigger clause but entirely omits what the skill does, leaving the "what" half of the what/when contract missing. Its keywords are strong and domain-distinctive despite one piece of internal jargon.

Suggestions

Add a "what" clause before the trigger, e.g. "Monitors CI readiness and drives rerun/repair decisions for PR pipelines. Use when...", so both capability and trigger are explicit.

Replace the internal jargon "forge check collection" with a natural phrase like "PR check rollup" or "CI check status" that a user would actually say.

Name one or two concrete actions the skill performs (e.g. "classifies cancelled checks, issues reruns, parks persistent failures") to raise specificity.

Dimension	Reasoning	Score
Specificity	The description is a pure "Use when..." clause naming several CI domains ("CI readiness, forge check collection, reruns, CI timeouts, or PR lifecycle monitoring") but the only action verb is the generic "changing", so it names the domain with minimal/generic actions rather than concrete capabilities.	2 / 5
Completeness	Only the "when" is present ("Use when changing...") with no "what" describing what the skill actually does, matching the anchor for only-when-present-without-what.	2 / 5
Trigger Term Quality	It includes several natural developer-facing terms ("CI timeouts", "reruns", "PR lifecycle monitoring") with good coverage, though "forge check collection" is internal jargon a user would not naturally say, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The triggers target a clear CI-monitoring niche (forge check collection, PR lifecycle monitoring) with minimal conflict risk, though generic terms like "reruns" could overlap with a broader CI skill.	4 / 5
	Total	12 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: kunchenguid/no-mistakes
Path: .agents/skills/ci-monitor/SKILL.md
Commit: 9a464c2

Reviewed: 2 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.