hns-workflow-ci-loop

Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see moai-workflow-loop).

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.

The skill body is actionable, well-sequenced, and rich in validation checkpoints for a destructive/batch CI workflow. The main weakness is progressive disclosure: the body references scripts and rule files that are not present as a bundle, leaving navigation unverified and inline-heavy.

Suggestions

Bundle the referenced scripts (scripts/ci-watch/run.sh, lib/classify.sh, scripts/ci-autofix/*) under scripts/ so the inline references resolve to real one-level-deep files, or move the detailed cadence matrix / handoff schema into references/ and link to them.

Move the OQ2 cadence matrix and protected-files list into a references/ file (e.g. CADENCE.md) with a clear link from SKILL.md to reduce body length and improve progressive disclosure.

Add explicit 'See <path>' navigation links with relative paths for the dev-repo rule files (.claude/rules/local/ci-watch-protocol.md, ci-autofix-protocol.md) so their location is signaled rather than only described in prose.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly assumes Claude's knowledge of gh, CI, and the moai toolchain without re-explaining basics; a few areas (e.g. the repeated HARD-invariant restatements and the absorbed-from comment) are slightly redundant but overall token-efficient.	4 / 5
Actionability	Provides concrete, executable guidance including a copy-paste one-liner ("MOAI_CIWATCH_GH=gh sh scripts/ci-watch/run.sh"), exact exit codes, env vars, commit-message format, and shell/Go file paths; minor gaps where some commands depend on scripts not shown inline.	4 / 5
Workflow Clarity	The two phases are clearly sequenced with explicit validation checkpoints (handoff schema on exit 2, re-invoke watch after push, OQ2 cadence matrix by iteration), plus a Red Flags and Verification checklist that form a feedback loop for destructive/batch operations.	5 / 5
Progressive Disclosure	Content is well-sectioned within SKILL.md but there are no references/, scripts/, or assets/ bundle directories present despite the body referencing scripts (scripts/ci-watch/run.sh, classify.sh) and dev-repo rule files; navigation to those materials is not one-level-deep and verifiable.	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.

The description is specific, trigger-rich, and clearly distinguishes this skill from the adjacent moai-workflow-loop, while explicitly covering both what it does and when to use it. It is concise without vague padding.

Dimension	Reasoning	Score
Specificity	Names the CI-loop domain and lists several concrete actions ("Polls gh pr checks", "classifies required vs auxiliary failures", "attempts safe automated patches (max 3 iterations)", "escalates semantic failures"); minor coverage gaps but no vague fluff.	4 / 5
Completeness	Explicitly answers both 'what' (poll/classify/patch/escalate) and 'when' ("Use for CI loop workflow" after /moai sync PR creation), with concrete trigger phrasing and an explicit anti-trigger pointing to moai-workflow-loop.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ("CI loop workflow", "gh pr checks", "auto-fix", "/moai sync") plus technical synonyms; a few common-surface terms like "CI watch" or "CI monitoring" are present but file-extension-style breadth is missing, so it sits just below 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche scoped to the post-/moai-sync CI watch + auto-fix loop and explicitly disambiguates from the related moai-workflow-loop skill, minimizing wrong-skill triggering.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 13 missing, 9 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: modu-ai/moai-adk
Path: .claude/skills/hns-workflow-ci-loop/SKILL.md
Commit: 2213871

Reviewed: 4 hours 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.