help

Get unstuck with Watt without leaving Claude — ask what you can do and how, figure out why something isn't working, see what's changed and whether you're on the latest, or tell the team something — report a bug, request a signal or feature, reach a human, and track what you've filed. It answers your question first and gets you to a result fast — pointing you to /watt:explore, /watt:audience, or /watt:configure when that's the quicker path. Use when you type /watt:help, or say "what can Watt do", "how do I build an audience", "why is X failing", "Claude is blocking my export", "something's broken", "I need a signal for Y", "I need a human", "what's new", or "what have I filed".

Quality

89%

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

73%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, highly actionable instruction-only help skill with an explicit sequenced flow and strong validation around its outward-facing filing step. Its main weakness is conciseness — repeated guidance across sections inflates the body — and minor abstraction in the filing tool's call details.

Suggestions

Consolidate the intent-vs-keyword guidance into one authoritative statement in the Language section and reference it from Entry and the flow steps rather than restating it; do the same for 'stand alone' (Purpose vs. How to behave) and the 'never file without confirm' / 'never invent' rules.

Specify the ticket-filing tool's call signature concretely (tool name plus the action/save_ticket params and accepted type values) so the draft→confirm→file loop is fully executable rather than alluded to.

Consider extracting the per-lane render-format examples (ticket-list row, ticket-detail, draft card) into a short references file so the SKILL.md overview stays lean, which would also lift progressive_disclosure toward a clean overview-to-detail split.

Dimension	Reasoning	Score
Conciseness	Mostly efficient prose with no over-explanation of known concepts, but several points are restated across sections — intent-vs-keyword appears ~4 times, 'stand alone' in both Purpose and How to behave, 'never file without confirm' and 'never invent' repeated — leaving notable tightening room.	3 / 5
Actionability	Concrete URLs, a shell command, a draft-ticket example, and explicit ticket-list/detail render formats give mostly executable guidance; minor gap is the filing tool's call signature, which is deliberately kept abstract ('action', 'save_ticket') rather than fully specified.	4 / 5
Workflow Clarity	A clearly sequenced 6-step flow with an explicit confirm-gate validation before filing, feedback loops (Edit/Cancel, retry-on-failure keeping the draft), and error-recovery guidance for the outward-facing filing operation.	5 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with one-level-deep live-doc URLs that are explicitly signaled, but the ~160-line body is entirely self-contained with no internal bundle split, so it stops short of the clean overview-to-separate-files model.	4 / 5
	Total	16 / 20 Passed

Description

100%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, comprehensive description that names concrete capabilities, provides extensive natural trigger phrases, and explicitly covers both what and when in a distinct, conflict-resistant niche. Voice is third person throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'ask what you can do and how', 'figure out why something isn't working', 'report a bug, request a signal or feature, reach a human, and track what you've filed' — plus three named handoff commands, giving comprehensive coverage.	5 / 5
Completeness	Clearly answers 'what' (the capability list) and 'when' (concrete 'Use when...' trigger phrases), both explicit and specific.	5 / 5
Trigger Term Quality	The explicit 'Use when...' clause covers many natural user phrases — 'what can Watt do', 'how do I build an audience', 'why is X failing', 'something's broken', 'I need a human', 'what's new', 'what have I filed' — including synonyms and variations.	5 / 5
Distinctiveness Conflict Risk	Tightly scoped to the Watt plugin via '/watt:help' and the named /watt:explore, /watt:audience, /watt:configure commands, giving a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 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: wattdata/plugin
Path: skills/help/SKILL.md
Commit: 880e260

Reviewed: 4 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.