html-reports-description

Guide for understanding the structure and content of HTML reports generated by the tool

Quality

18%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/html-reports-description/SKILL.md

Quality

Discovery

14%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is too vague to be effective for skill selection. It fails to specify which tool generates the reports, what concrete actions the skill enables, and when Claude should select it. The phrase 'the tool' is particularly problematic as it provides no distinguishing information.

Suggestions

Specify the exact tool that generates the HTML reports (e.g., 'pytest', 'Lighthouse', 'coverage.py') to make the description distinctive and searchable.

Add a 'Use when...' clause with explicit trigger terms, e.g., 'Use when the user asks about interpreting report output, navigating HTML report sections, or understanding test/coverage results.'

List concrete actions the skill enables, such as 'Explains report sections, interprets metrics and summaries, identifies key findings in generated HTML output.'

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'understanding the structure and content' without listing any concrete actions. It doesn't specify what kind of understanding, what structures, or what content is involved.	1 / 3
Completeness	The 'what' is weak (vaguely 'understanding structure and content') and there is no 'when' clause or explicit trigger guidance at all. The missing 'Use when...' clause would cap this at 2 regardless, but the weak 'what' brings it to 1.	1 / 3
Trigger Term Quality	It includes 'HTML reports' which is a somewhat relevant keyword, but 'the tool' is completely unspecified, and it lacks natural variations users might say (e.g., report analysis, parsing reports, reading HTML output, report format).	2 / 3
Distinctiveness Conflict Risk	The phrase 'the tool' is completely ambiguous—it could refer to any tool. 'HTML reports' is somewhat specific but 'understanding structure and content' is so generic it could overlap with many documentation or analysis skills.	1 / 3
	Total	5 / 12 Passed

Implementation

22%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads more like informal developer notes than a structured skill file. It is verbose with explanatory prose that Claude doesn't need, lacks a clear workflow sequence, and mixes descriptive content with scattered actionable commands. The hardcoded user-specific path and lack of validation steps further weaken its utility.

Suggestions

Restructure into a clear workflow: 1) ensure tool is in PATH, 2) locate JSON files in .fpc_logs/, 3) run fpc-create-report, 4) verify output exists at ./fpc-report/index.html

Remove descriptive prose about what HTML reports and JSON files are—Claude already understands these concepts. Focus on the specific structure (Events, Rounding Error, Errors Per Line) with concrete details about template placeholders.

Replace the hardcoded user path with a generic placeholder like $FPCHECKER_ROOT/build/install/bin and note it should be set per environment

Add explicit validation steps (e.g., verify the report was generated, check for expected sections) and consolidate the scattered code references into a single 'Key files' section with clear paths

Dimension	Reasoning	Score
Conciseness	The content is verbose with unnecessary explanations (e.g., explaining what JSON reports are, what HTML reports are, what each section does in plain English). It includes hardcoded user-specific paths (/Users/lagunaperalt1/...) and redundant descriptions that Claude doesn't need. Many sentences describe rather than instruct.	1 / 3
Actionability	There are some concrete commands (fpc-create-report, export PATH, ls .fpc_logs/) but much of the content is descriptive rather than instructional. The commands shown are real but the skill reads more like documentation than actionable guidance—it tells Claude about the report structure rather than giving clear instructions on what to do with it.	2 / 3
Workflow Clarity	There is no clear sequenced workflow. The sections are loosely organized topics (how reports are generated, where JSON files are, code locations, templates) but lack a coherent step-by-step process. There are no validation checkpoints or error recovery steps despite involving build/install operations.	1 / 3
Progressive Disclosure	There are references to other files and directories (report_templates, line_highlighting.py, fpc_create_report.py) and a reference to 'the skill to build the tool,' but these are not clearly signaled with links. The content mixes overview-level and detail-level information inline rather than appropriately splitting them.	2 / 3
	Total	6 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: llnl/FPChecker
Commit: 875a03e

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.