flame-graph-generator
Flame Graph Generator - Auto-activating skill for Performance Testing. Triggers on: flame graph generator, flame graph generator Part of the Performance Testing skill category.
35
3%
Does it follow best practices?
Impact
94%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/10-performance-testing/flame-graph-generator/SKILL.mdQuality
Discovery
7%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 essentially a title and category label with no substantive content. It fails to describe what the skill actually does (e.g., generates flame graphs from profiling data, visualizes CPU/memory hotspots), lacks natural trigger terms users would use, and provides no guidance on when Claude should select it. The only redeeming quality is that 'flame graph' is a somewhat distinctive term.
Suggestions
Add concrete actions the skill performs, e.g., 'Generates flame graph visualizations from profiling data, analyzes CPU and memory hotspots, parses stack traces from perf, dtrace, or async-profiler output.'
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to create flame graphs, visualize profiling data, analyze performance bottlenecks, or interpret stack trace samples.'
Expand trigger terms to include natural variations like 'flamegraph', 'flame chart', 'CPU profiling visualization', 'stack trace visualization', 'performance hotspot', 'perf data', '.svg flame graph'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the skill ('Flame Graph Generator') and its category ('Performance Testing') but does not describe any concrete actions like generating, analyzing, or visualizing flame graphs. No specific capabilities are listed. | 1 / 3 |
Completeness | The 'what' is essentially absent beyond the name, and the 'when' is not explicitly addressed. There is no 'Use when...' clause or equivalent guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The trigger terms are just 'flame graph generator' repeated twice. Missing natural variations users would say like 'flame graph', 'flamegraph', 'CPU profiling', 'performance profiling', 'stack trace visualization', 'hotspot analysis', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'flame graph' is fairly niche and specific to a particular type of performance visualization, which provides some distinctiveness. However, the vague 'Performance Testing' category could overlap with other performance-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an empty shell with no substantive content. It contains only boilerplate meta-descriptions about what the skill would do, without any actual instructions, code, commands, or technical guidance for generating flame graphs. It fails on every dimension because it teaches Claude nothing actionable about flame graph generation.
Suggestions
Add concrete, executable examples showing the full flame graph generation workflow (e.g., `perf record -F 99 -g -p <PID> -- sleep 30`, `perf script | stackcollapse-perf.pl | flamegraph.pl > output.svg`)
Include specific tool coverage with code snippets for common profilers (perf, async-profiler, py-spy, node --prof) and the flamegraph.pl toolchain
Add a clear multi-step workflow: 1) Profile the application, 2) Collect stack traces, 3) Fold stacks, 4) Generate SVG, with validation at each step (e.g., checking stack trace count, verifying SVG output)
Remove all meta-description sections ('When to Use', 'Example Triggers', 'Capabilities') and replace with actual technical content organized into quick-start and advanced sections
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and meta-description. It explains what the skill does in abstract terms without providing any actual technical content. Every section restates the same vague information about 'flame graph generator' without teaching Claude anything it doesn't already know. | 1 / 3 |
Actionability | There is zero concrete, executable guidance. No code examples, no commands (e.g., perf, flamegraph.pl, async-profiler), no specific tools, no configuration snippets. The content only describes rather than instructs. | 1 / 3 |
Workflow Clarity | There is no workflow whatsoever. No steps for generating flame graphs (profiling → collecting stacks → folding → rendering), no validation checkpoints, no sequenced process. The bullet 'Provides step-by-step guidance' is ironic given none is actually provided. | 1 / 3 |
Progressive Disclosure | The content is a flat, monolithic block of generic placeholder text with no meaningful structure, no references to detailed materials, and no navigation to deeper resources. The sections that exist are all meta-description rather than organized technical content. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
87f14eb
- Reviewed
Table of Contents
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.