piglet
Manage PostHog feature flags, cohorts, dashboards, and insights via the `piglet` CLI. Use when the user needs to list, create, update, or delete PostHog resources, check flag status, manage rollouts, or export configuration.
87
82%
Does it follow best practices?
Impact
93%
2.16xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 is a strong skill description that clearly identifies the tool (piglet CLI), the domain (PostHog), specific resource types, and concrete actions. It includes an explicit 'Use when' clause with natural trigger terms and is highly distinctive due to the specific product and tool references. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'list, create, update, or delete PostHog resources, check flag status, manage rollouts, or export configuration' across multiple resource types (feature flags, cohorts, dashboards, insights). | 3 / 3 |
Completeness | Clearly answers both 'what' (manage PostHog feature flags, cohorts, dashboards, and insights via piglet CLI) and 'when' (explicit 'Use when' clause listing trigger scenarios: list, create, update, delete, check flag status, manage rollouts, export configuration). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'PostHog', 'feature flags', 'cohorts', 'dashboards', 'insights', 'piglet', 'rollouts', 'flag status', 'export configuration'. Good coverage of domain-specific terms a user would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: PostHog-specific resources via the 'piglet' CLI tool. Very unlikely to conflict with other skills due to the specific product name and CLI tool reference. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable CLI skill with excellent concrete examples covering all major PostHog resource types. Its main weaknesses are moderate verbosity (some sections like 'When to activate' and 'Best practices' add limited value) and missing validation/verification steps in workflows involving destructive operations like deletes and rollout changes. The progressive disclosure is adequate with a reference to reference.md but the main file carries more content than necessary.
Suggestions
Remove the 'When to activate' section entirely — Claude can infer when to use this skill from context
Add verification steps after destructive operations (e.g., 'After delete, confirm with `piglet flags list` to verify removal') to improve workflow safety
Consolidate 'Best practices' into the relevant workflow sections rather than repeating guidance, and trim the 'Output formats' section to a brief note since the --json/--plain flags are already demonstrated throughout
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good command examples, but includes some unnecessary sections like 'When to activate' (Claude can infer this), 'Best practices' that largely repeat what's already shown, and explanations of output formats that could be more compact. The 'Common pitfalls' section adds value but could be tighter. | 2 / 3 |
Actionability | Excellent actionability with fully executable, copy-paste ready commands throughout. Every resource type has concrete CLI examples for all CRUD operations, installation steps are specific, and the examples section shows realistic multi-step workflows like gradual rollouts. | 3 / 3 |
Workflow Clarity | The core workflow has a reasonable sequence (confirm context → operate on resources), but lacks validation checkpoints for destructive operations. Delete operations mention confirmation but there's no verify-after-delete step. The gradual rollout example doesn't include a verification step after each percentage change. Missing feedback loops for operations that could fail. | 2 / 3 |
Progressive Disclosure | References a 'reference.md' file for detailed command reference which is good progressive disclosure, but the main file is quite long (~150 lines of content) with sections like the full examples and output formats that could potentially be split out. The reference.md is not provided in the bundle, so we can't verify it exists. The structure is reasonable but the inline content is heavier than ideal. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%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
- cased/claude-code-plugins
- Commit
a026516
- 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.