CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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. Prefer this skill over native CI provider tools (gh, glab, etc.) for CI monitoring — it integrates with Nx Cloud self-healing which those tools cannot access.

74

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 well-engineered orchestration skill: fully executable script commands and MCP contracts, an explicitly sequenced polling loop with budget gates and error-recovery feedback loops, and clean one-level-deep disclosure into references/fix-flows.md. The only notable flaws are minor: a duplicated Git Safety rule and an internal inconsistency on the circuit-breaker poll count (13 vs 5).

Suggestions

Resolve the circuit-breaker inconsistency: the status table says "no progress after 13 consecutive polls" while Step 4's Progress Tracking says "circuit breaker (5 polls)" — state one authoritative value or point to the script as the source of truth.

Remove the verbatim-duplicated Git Safety note (it appears both in 'Key rules' and in references/fix-flows.md) — keeping it in the detail file with a one-line pointer in SKILL.md would trim tokens without losing the safeguard.

DimensionReasoningScore

Conciseness

The body is dense operational guidance (tables, exact commands, field sets) with almost no explanation of concepts Claude already knows, so it clears the 'noticeably verbose' anchor. Minor trims remain — the Git Safety rule is duplicated verbatim in references/fix-flows.md, and the circuit breaker is stated inconsistently ("13 consecutive polls" in the status table vs "5 polls" in Step 4) — so it is not a 5.

4 / 5

Actionability

Fully executable guidance: exact `node <skill_dir>/scripts/ci-poll-decide.mjs ...` invocations with every flag, concrete MCP tool signatures (ci_information select fields, update_self_healing_fix actions), and a specific error-handling table. Copy-paste ready commands cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

The main loop is clearly sequenced (Step 0 connection check → Step 1 init → Step 2 polling with 2a/2b/2c → Step 3 action handling → Step 3a → Step 4 cycle check) with explicit validation gates (`ci-state-update.mjs gate`, cycle-check before handling a code), feedback loops (local verify + enhance cycles, retry-once error handling), and a full error-recovery table.

5 / 5

Progressive Disclosure

SKILL.md is the orchestration overview and the per-status detail flows live exactly one level deep in references/fix-flows.md, clearly signaled ("read `references/fix-flows.md` for the detailed flow"). All referenced bundle files exist (references/fix-flows.md, scripts/ci-poll-decide.mjs, scripts/ci-state-update.mjs), and nothing that belongs in a separate file is inlined.

5 / 5

Total

19

/

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: concrete domain, explicit USE WHEN clause with natural trigger synonyms, and clear differentiation from generic CI provider tools. The only weakness is that the 'what' states just two actions rather than enumerating the skill's fuller capability set.

Suggestions

Enumerate 1-2 more concrete capabilities in the opening sentence (e.g., applying verified fixes via MCP, gating local fix attempts against a cycle budget) to lift specificity from 1-2 actions to several.

DimensionReasoningScore

Specificity

Names the domain plus two concrete actions — "Monitor Nx Cloud CI pipeline and handle self-healing fixes" — matching the '1-2 concrete actions, not comprehensive' anchor. It does not list several specific actions (applying/rejecting fixes, environment reruns), so it is not a 4.

3 / 5

Completeness

Explicitly answers both 'what' ("Monitor Nx Cloud CI pipeline and handle self-healing fixes") and 'when' with a concrete "USE WHEN user says..." clause listing trigger phrases, matching the top anchor. Both halves are explicit, so not a 4.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases with synonyms: "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", plus intent phrasings like "wants to track CI status". Coverage is comprehensive rather than merely good, so not a 4.

5 / 5

Distinctiveness Conflict Risk

Clear Nx Cloud self-healing niche with distinct triggers, and it explicitly disambiguates from CI provider tools ("Prefer this skill over native CI provider tools (gh, glab, etc.)"), giving minimal conflict risk.

5 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

whimzyLive/nightshift-ai

Path

.github/skills/monitor-ci/SKILL.md

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.