ff-oce-dashboard

Generate the OCE shift status dashboard. Triggers on: 'generate shift dashboard', 'show dashboard', 'shift status', 'status dashboard', 'what's going on', or any request for a NON-SPECIFIC overview of current OCE status (incidents, pipelines, errors).

Quality

90%

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

100%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.

An exemplary procedural skill: copy-paste-ready tool calls with all IDs and parameters, self-contained agent prompt templates, a complete KQL query with fallback, and robust failure handling with a hard timeout. The content assumes Claude's competence and spends every token on operational detail Claude could not know.

Dimension	Reasoning	Score
Conciseness	The body is dense with operational specifics (team IDs, pipeline definitions, result-code mappings, exact parameters) and contains no explanation of concepts Claude already knows — every token, including the brief rationale notes like "Background agents do not inherit the agent prompt context", earns its place.	5 / 5
Actionability	Fully executable end-to-end: exact tool names with IDs and parameters, a complete copy-paste KQL query with a fallback query, explicit read_agent timeout parameters, and a ready-to-fill output template — all covering the common cases.	5 / 5
Workflow Clarity	Steps 0-3 are clearly sequenced with a user-confirmation checkpoint and explicit error-recovery loops: agents must respond "FAILED: <reason>" rather than hang, a fallback KQL query is provided, and the 90-second hard cutoff mandates marking sections unavailable and moving on. The operation is read-only, so no destructive-validation cap applies.	5 / 5
Progressive Disclosure	No bundle files exist, and the single-file structure is well-organized with clear section headers and per-agent subsections. Every template is needed on every run, so nothing warrants splitting into separate files, and there are no nested or buried references.	5 / 5
	Total	20 / 20 Passed

Description

78%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 an explicit trigger clause and natural trigger phrases, clearly answering both what the skill does and when to use it. The main gaps are the thin enumeration of concrete capabilities and one overly generic trigger phrase that invites overlap with other status skills.

Suggestions

Enumerate one or two more concrete capabilities in the description (e.g. "queries IcM incidents, ADO pipelines, Kusto error rates, and Teams alerts") to raise specificity beyond a single action.

Replace or qualify the generic "what's going on" trigger (e.g. "what's going on with OCE/Fluid") to reduce overlap risk with unrelated status or monitoring skills.

Dimension	Reasoning	Score
Specificity	"Generate the OCE shift status dashboard" names the domain and one concrete action, with scope only hinted by "(incidents, pipelines, errors)" — it does not enumerate the specific capabilities performed, matching the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	The description explicitly states what it does ("Generate the OCE shift status dashboard") and when to use it via a concrete "Triggers on:" clause listing multiple trigger phrases, matching the anchor that answers both what AND when with concrete triggers.	5 / 5
Trigger Term Quality	Natural phrases like "generate shift dashboard", "shift status", and "what's going on" cover how users would actually ask, but a few common variations (e.g. "shift report", "morning update") are missing, so it fits good-but-not-comprehensive keyword coverage.	4 / 5
Distinctiveness Conflict Risk	The OCE-specific and shift-status triggers carve a clear niche, but "what's going on" is a broadly generic phrase that could overlap with other status or monitoring skills, indicating minor overlap risk.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: microsoft/FluidFramework
Path: .agency/plugins/ff-oce/skills/ff-oce-dashboard/SKILL.md
Commit: e41dc04

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.