ov-session-report

Analyze local Q&A session JSONL files and produce a complete, auditable English Markdown weekly report over consecutive time windows, with all data required for downstream Feishu document and whiteboard rendering. Use for requests such as "analyze the latest week of sessions," "generate a community Q&A weekly report," or "compare with last week." This skill does not ingest other message sources or create/upload online documents.

Quality

85%

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 is highly actionable with a clear, validated workflow, but it is long and monolithic, inlining large template and data-contract blocks that could be split into reference files to improve token efficiency and navigation.

Suggestions

Move the full qa-report.v3 JSON contract and the Markdown template into separate reference files (e.g. references/data-contract.md, references/template.md) and link to them from SKILL.md to reduce inline length and improve progressive disclosure.

Consolidate overlapping guidance between the End-to-End Procedure and the Acceptance Checklist so each step is stated once, cutting redundancy and token cost.

Trim any restated rules (e.g. release-evidence and not-comparable handling appear in multiple sections) to a single canonical location with brief cross-references.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely domain-specific rather than padded with concepts Claude already knows, but at ~660 lines it carries notable redundancy between the qa-report.v3 JSON contract, the Markdown template, the End-to-End Procedure, and the Acceptance Checklist.	3 / 5
Actionability	Provides fully executable guidance: concrete shell commands (`rg --files "$SESSION_ROOT" -g '*.jsonl'`), a complete JSON schema, a copy-paste Markdown template, explicit masking rules with worked examples, and exact percentage-change formulas.	5 / 5
Workflow Clarity	A 13-step End-to-End Procedure sequences the work with an explicit final validation feedback loop ('Reparse the final JSON and validate tables, formulas, ordering...'), supported by invariants and an Acceptance Checklist, satisfying the batch-operation validation requirement.	5 / 5
Progressive Disclosure	Section headers organize the content well, but no bundle/reference files exist and large self-contained blocks (the ~170-line JSON data contract and ~100-line Markdown template) are inlined that could plausibly live in separate reference files.	3 / 5
	Total	16 / 20 Passed

Description

92%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, complete, and distinctive, with concrete capabilities and explicit trigger phrases plus a helpful negative boundary. It is only slightly short of perfect trigger-term breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyze local Q&A session JSONL files', 'produce a complete, auditable English Markdown weekly report over consecutive time windows', and supplying 'all data required for downstream Feishu document and whiteboard rendering' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (analyze JSONL sessions and produce a Markdown weekly report with rendering data) and 'when' (concrete 'Use for requests such as...' trigger phrases), meeting the top anchor.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('analyze the latest week of sessions,' 'generate a community Q&A weekly report,' 'compare with last week') with good coverage, but a few common synonyms or file-extension variants are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (OpenViking community Q&A weekly report from local JSONL) and adds a negative boundary — 'does not ingest other message sources or create/upload online documents' — minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (661 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: volcengine/OpenViking
Path: examples/compile/ov-compile-skills/ov-session-report/SKILL.md
Commit: b2f1f9d

Reviewed: 3 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.