CtrlK
BlogDocsLog inGet started
Tessl Logo

monitor-ci

Monitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", wants to track CI status, or needs help with self-healing CI fixes. ALWAYS USE THIS SKILL instead of native CI provider tools (gh, glab, etc.) for CI monitoring.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

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.

Highly actionable and clearly sequenced with strong validation checkpoints for a complex CI self-healing orchestrator. The main weaknesses are conciseness (duplicated flow descriptions and repeated commit/push blocks) and progressive disclosure (a 650-line monolith with no content split into referenced files).

Suggestions

Deduplicate the Apply-Locally+Enhance flow — describe it once and reference it from Step 3b instead of restating it — and consolidate the repeated commit/push snippets into a single canonical block.

Split the three long example sessions and the per-status handling detail into a referenced reference file (e.g. EXAMPLES.md / STATUS-REFERENCE.md) so SKILL.md stays a lean overview with one-level-deep pointers.

Tighten recurring prose like 'Loop to poll for new CI Attempt' and the duplicated 'CI provider CLIs are acceptable ONLY for' guidance into a single stated rule.

DimensionReasoningScore

Conciseness

The 650-line body is mostly information-dense about a complex state machine, but the Apply-Locally+Enhance flow is described twice (Step 3b and a standalone section), commit/push blocks are repeated across sections, and 'Loop to poll for new CI Attempt' recurs throughout; tightening the duplications would lift it to a 4.

3 / 5

Actionability

Fully executable guidance throughout — concrete MCP calls (update_self_healing_fix({ shortLink, action: "APPLY" })), copy-paste git commands, nx-cloud apply-locally invocations, Task() spawn templates, and three worked example sessions covering the common cases.

5 / 5

Workflow Clarity

Clearly numbered main loop (Steps 0–4) with explicit validation checkpoints — circuit breaker on 3 no-progress iterations, approaching-limit gate, retry-once for cipe_no_tasks, local-verify enhance loop — plus feedback loops and table-based checklists for a destructive/batch operation.

5 / 5

Progressive Disclosure

Good internal structure (headers, tables) but entirely monolithic: all 650 lines are inlined with no bundle files and no references to separate files, so content that could be split (example sessions, per-status flows, config reference) lives inline; not a 2 because sectioning is solid, not a 4 because nothing is offloaded to one-level-deep references.

3 / 5

Total

16

/

20

Passed

Description

90%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 with explicit what/when structure, comprehensive natural trigger phrases, and a clear conflict-reducing niche around Nx Cloud self-healing. The only weak spot is specificity, which names just two actions rather than enumerating several concrete capabilities.

DimensionReasoningScore

Specificity

Names the domain (Nx Cloud CI) and two concrete actions — 'Monitor Nx Cloud CI pipeline' and 'handle self-healing fixes' — matching the anchor for 1-2 concrete actions without comprehensive coverage; not a 4 because it does not list several specific actions.

3 / 5

Completeness

Explicitly answers both 'what' (monitor Nx Cloud CI pipeline and handle self-healing fixes) and 'when' ('USE WHEN user says...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including synonyms and variations — 'monitor ci', 'watch ci', 'ci monitor', 'watch ci for this branch', 'track ci', 'check ci status' — exactly the phrases a user would say; no common variant is missing.

5 / 5

Distinctiveness Conflict Risk

Clear Nx Cloud CI niche with distinct triggers and an explicit guardrail ('ALWAYS USE THIS SKILL instead of native CI provider tools') that minimizes conflict with generic CI skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (651 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
leboncoin/spark-web
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.