webspec-index

Use webspec-index to query WHATWG, W3C, IETF and TC39 web specifications from the command line

2.59x

Quality

71%

Does it follow best practices?

Impact

83%

2.59x

Average score across 2 eval scenarios

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/webspec-index/SKILL.md

Quality

Content

85%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 a strong, highly actionable CLI reference: executable examples for every subcommand, explicit validation habits, and well-sequenced usage workflows. Its main weakness is that everything lives in one 287-line file — splitting the Gecko usage patterns and PR-preview detail into reference files would shorten the always-loaded context while keeping the overview intact.

Suggestions

Move the 'Usage patterns for Gecko development' section (and optionally the PR-preview detail) into a references/ file (e.g. references/gecko.md) and link to it from a short '## Usage patterns' pointer in SKILL.md.

Trim minor redundancy: the duplicate `webspec-index query 'DOM#concept-tree'` example and the long comparative prose around --detail verbose/edges/compact could be condensed to one line each.

Consider a brief '## When to use which command' decision table so the reader picks query vs refs vs trace vs idl without scanning every section.

Dimension	Reasoning	Score
Conciseness	The body is dense with tool-specific facts Claude cannot know (truncation semantics, on-demand indexing, --detail trade-offs) and nearly every section is a runnable command example rather than padded explanation — matching 'efficient; minor instances of over-explanation that could be trimmed'. Not 5 because there are minor trims available: a duplicated example (`webspec-index query 'DOM#concept-tree'` appears twice in the same block) and some extended prose passages (e.g. the --detail level comparison) that run long.	4 / 5
Actionability	Every section gives fully executable copy-paste commands covering the common cases for all ten subcommands, plus flag-level variants (--pr, --diff, --kind, --detail) — matching 'fully executable; copy-paste ready code or commands; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The 'Usage patterns' section sequences multi-step workflows explicitly (query → read refs → look up referenced concept; two-step query → searchfox-cli hand-off with the 'url' field) and includes explicit validation checkpoints: verifying anchors with `exists` before citing them and reading `Search was truncated` before trusting trace results. No destructive/batch operations are involved, so no cap applies.	5 / 5
Progressive Disclosure	The single-file body is well sectioned but 287 lines — well past the under-50-line simple-skill exception — with no bundle files and no references at all; content that plausibly belongs in a reference file (the ~95-line 'Usage patterns for Gecko development' section and PR-preview detail) is fully inlined. This matches 'some structure but could be better organized; content that should be separate is inline'. Not 4 because there are no clearly signaled external references to point to deeper material.	3 / 5
	Total	17 / 20 Passed

Description

57%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 concrete and distinctive but undersized: it states one action and omits any 'Use when...' trigger guidance, so it would only fire if the user already knows the tool's name. Expanding it to cover the skill's main capabilities and explicit trigger situations would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when a task requires reading what a web spec says — algorithm steps, section content, cross-references, or verifying a spec anchor in WHATWG/W3C/IETF/TC39 specs."

Name more of the skill's actual capabilities in the description (search across specs, check anchor existence, trace cross-spec call chains, query PR previews) instead of only "query".

Include natural synonyms users would say, such as "spec", "spec section", "specification", and "RFC", to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("query WHATWG, W3C, IETF and TC39 web specifications from the command line") and a single concrete action — querying. It is not a score of 4 because only one action is stated, while the skill actually offers search, exists, refs, trace, and list; scoring only what is explicit, this matches 'names domain and 1-2 concrete actions'.	3 / 5
Completeness	There is a clear 'what' (query web specifications from the command line) but no 'when' clause at all — the description never says when to use the skill, which per the judging guidelines caps completeness at 3. Not 2 because the 'what' is concrete, not vague.	3 / 5
Trigger Term Quality	Phrases like "web specifications", the four standards-body names, and "from the command line" are relevant keywords, but common user-natural variations and synonyms ("spec", "spec section", "standard", "RFC") are missing, matching the anchor 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	Naming the specific tool and the four standards bodies carves out a clear niche (web-spec lookup) that is unlikely to trigger for other skills; this matches the anchor 'clear niche with distinct triggers; minimal conflict risk'.	5 / 5
	Total	14 / 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: mozilla/enterprise-firefox
Path: .agents/skills/webspec-index/SKILL.md
Commit: 5e982c1

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.