rerun-docs

Where the Rerun documentation and code snippets live on disk and how to search them. Read this before answering a question about how Rerun works, what an archetype or view does, how to log or query data, or when you need a copy-pastable example in Python, Rust, or C++.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 body is an efficient, well-structured navigation guide that tells Claude exactly where Rerun docs and snippets live and how to search them, with concrete commands and path patterns. The only small gap is the absence of an explicit search-refinement recovery loop in the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence ("Read them instead of guessing."), with no padding or explanation of what Rerun is; every token earns its place, matching the level-5 anchor.	5 / 5
Actionability	It gives a concrete executable command (`rg -l "<term>" docs/content docs/snippets/all`) and precise per-task path patterns, but most guidance is path-template direction (e.g. `docs/snippets/all/archetypes/<x>.py`) rather than fully copy-paste-ready steps, leaving a small gap below level 5.	4 / 5
Workflow Clarity	The numbered "How" sequence (search first, open the right file pair per question type, give the website URL, WebFetch off-disk refs) is clearly ordered and well-scoped; as a read-only search skill it needs no validation checkpoints, but it lacks an explicit "if not found, broaden/refine" recovery loop.	4 / 5
Progressive Disclosure	Under 50 lines with no bundle files needed, it is well-organized into Where/Layout/How sections with a clear navigation table; per the simple-skill scoring note, this earns a 5 with just well-organized sections.	5 / 5
	Total	18 / 20 Passed

Description

87%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 strong: it clearly states both what the skill covers (locating/searching Rerun docs and snippets on disk) and when to invoke it, using natural user phrasing tied to a specific named product. Minor room to widen the concrete action vocabulary and add a few more trigger synonyms.

Dimension	Reasoning	Score
Specificity	"Where the Rerun documentation and code snippets live on disk and how to search them" names the domain and several concrete actions (locate on disk, search), but the action set is narrow rather than comprehensive, sitting just below the level-5 anchor.	4 / 5
Completeness	It explicitly answers both what ("where the Rerun documentation and code snippets live on disk and how to search them") and when ("Read this before answering a question about how Rerun works...") with concrete trigger phrases, matching the level-5 anchor.	5 / 5
Trigger Term Quality	Natural user phrases like "how Rerun works," "what an archetype or view does," "how to log or query data," and "copy-pastable example in Python, Rust, or C++" give strong keyword coverage with language variants, though a few common terms (e.g. blueprint, recording) are absent.	4 / 5
Distinctiveness Conflict Risk	"Rerun" is a specific named product with distinctive triggers (archetype, view, log/query), giving it a clear niche and minimal overlap with other skills.	5 / 5
	Total	18 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: rerun-io/rerun
Path: skills/rerun-docs/SKILL.md
Commit: 3efde05

Reviewed: 2 hours 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.