nx-ci-monitor
Monitor Nx Cloud CI pipeline status and handle self-healing fixes automatically. Use when user says "watch CI", "monitor pipeline", "check CI status", "fix CI failures", or "self-heal CI". Requires Nx Cloud connection. Do NOT use for local task execution (use nx-run-tasks) or general CI debugging outside Nx Cloud.
85
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific capabilities, includes a comprehensive 'Use when' clause with natural trigger terms, clearly defines its scope with both positive and negative boundaries, and explicitly distinguishes itself from related skills by name. The negative boundary clauses are particularly effective for reducing misselection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: monitor CI pipeline status, handle self-healing fixes automatically. Also specifies what NOT to use it for (local task execution, general CI debugging), which adds clarity. | 3 / 3 |
Completeness | Clearly answers both 'what' (monitor Nx Cloud CI pipeline status, handle self-healing fixes) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also includes negative boundaries ('Do NOT use for...') which further strengthens completeness. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'watch CI', 'monitor pipeline', 'check CI status', 'fix CI failures', 'self-heal CI'. These are phrases users would naturally say. Also includes domain-specific terms like 'Nx Cloud' and 'pipeline'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Nx Cloud CI monitoring and self-healing). Explicitly differentiates from related skills by naming the alternative ('use nx-run-tasks' for local execution) and excluding general CI debugging, minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at actionability and workflow clarity — every status, decision path, and error condition is mapped to concrete actions with explicit commands and validation steps. However, it is extremely verbose and would benefit enormously from compression and splitting detailed sub-flows into referenced files. The monolithic structure forces Claude to process ~350+ lines of context when much of it could be progressively disclosed.
Suggestions
Significantly compress the document by removing redundant explanations (e.g., 'Apply via MCP' is described in at least 3 places) and consolidating decision tables — aim for at least 50% reduction in token count.
Extract detailed sub-flows (Fix Available Decision Logic, Apply Locally + Enhance Flow, No-New-CIPE Handling) into separate referenced markdown files, keeping only summary decision tables in the main SKILL.md.
Remove the example sessions or move them to a separate EXAMPLES.md file — they consume significant tokens and Claude can generate appropriate output formatting from the status reporting table alone.
Consolidate the multiple tracking/state tables into a single compact reference, as the current repetition across 'Step 3a', 'Main Loop', and 'Progress Tracking' sections is redundant.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~350+ lines. It includes extensive tables, repeated explanations of flows, and detailed state machine logic that could be significantly compressed. Many sections restate information (e.g., 'Apply via MCP' is explained in multiple places), and the level of detail around tracking variables and subagent prompts is excessive for an agent that can infer orchestration patterns. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: specific git commands, exact MCP call signatures, precise subagent prompt templates, clear decision trees with specific field names (failedTaskIds, verifiedTaskIds, couldAutoApplyTasks), and package manager detection logic. Every action path has explicit commands to run. | 3 / 3 |
Workflow Clarity | The multi-step workflow is exceptionally well-sequenced with explicit validation checkpoints, feedback loops (local verify → enhance → retry up to N attempts → push to CI), circuit breakers (3 consecutive no-progress → exit), and clear decision trees for every status. The main loop steps are numbered and state tracking is explicit with reset conditions. | 3 / 3 |
Progressive Disclosure | The content is structured with clear sections and tables, but it's essentially a monolithic document with no references to external files for detailed sub-flows. The Fix Available Decision Logic, Apply Locally + Enhance Flow, and other complex sub-workflows could be split into separate reference documents. The document tries to contain everything inline, making it very long. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tech-leads-club/agent-skills
- Commit
81e7e0d
- 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.