readout

Produce a polished, self-contained HTML "readout" document under ~/.readouts (with an auto-maintained index page), either by snapshotting the findings accumulated in the current conversation or — when invoked fresh, e.g. "/readout on how github webhook events are processed" — by sharpening scope with clarifying questions and researching the codebase before documenting. The work runs in a child agent so the main conversation's context stays clean. Use whenever the user invokes /readout, says "write this up", "turn this into a doc/page", "make a readout", or asks for a readable, shareable document capturing findings or explaining how something works.

Quality

91%

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

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.

A well-structured orchestrator skill with an executable child-agent template, clear multi-step workflow with fallbacks, and clean progressive disclosure to a real, one-level-deep bundle. Minor gains available from trimming prose and adding an explicit output-validation checkpoint.

Suggestions

Trim rationale asides like 'A vague brief produces a vague document' and 'Local matters: the document lands on the user's filesystem...' to keep the orchestrator section leaner.

Add an explicit validation checkpoint in step 4 (e.g. confirm the HTML file exists at the path and the index was regenerated) before relaying completion to the user.

Consider condensing the Fallbacks section into a tighter bulleted list to reduce prose without losing the recovery paths.

Dimension	Reasoning	Score
Conciseness	The body is purposeful and assumes Claude's intelligence (no basic-concept padding), with rationale-laden pointers rather than payloads, but runs ~100 lines of prose with a few elaborations ('A vague brief produces a vague document', 'Local matters:...') that could be trimmed.	4 / 5
Actionability	Provides a copy-paste-ready child-agent prompt template with fill-in slots, an exact output path convention (~/.readouts/<YYYY-MM-DD>-<topic-slug>.html), and specific commands (date +%F, open <path>, python3 scripts/embed_snippets.py, python3 scripts/update_index.py) covering the common cases.	5 / 5
Workflow Clarity	A clearly numbered four-step orchestrator sequence with a defined completion protocol and a Fallbacks section for error recovery, but it lacks an explicit validation checkpoint on the produced artifact (e.g. 'confirm the file exists and renders') before reporting back.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview that signals one-level-deep references to real bundle files — references/doc-guide.md, assets/template.html, assets/code-pane.html, scripts/embed_snippets.py and update_index.py — with content appropriately split and easy to navigate; doc-guide points to the assets/scripts as leaf resources, not nested 'see X for details' chains.	5 / 5
	Total	18 / 20 Passed

Description

96%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, specific description that clearly states both what the skill produces and when to invoke it, with natural trigger phrases and a concrete artifact niche. Only slight breadth in the final trigger clause keeps it just below maximal distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Produce a polished, self-contained HTML readout document under ~/.readouts (with an auto-maintained index page)', 'snapshotting the findings', 'researching the codebase', 'sharpening scope with clarifying questions', 'runs in a child agent' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (produce a self-contained HTML readout under ~/.readouts, snapshot or research mode, child-agent execution) and when ('Use whenever the user invokes /readout, says "write this up"...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes the natural phrases users actually say — 'write this up', 'turn this into a doc/page', 'make a readout', plus the /readout invocation and 'readable, shareable document capturing findings or explaining how something works' — covering synonyms and the slash command comprehensively.	5 / 5
Distinctiveness Conflict Risk	The HTML readout-under-~/.readouts niche is distinct with specific triggers, but the trailing clause 'asks for a readable, shareable document capturing findings or explaining how something works' is somewhat broad and could overlap with general explanation/documentation skills.	4 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: warpdotdev/common-skills
Path: .agents/skills/readout/SKILL.md
Commit: 69b4753

Reviewed: 5 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.