action-builder
Action Builder integration. Manage data, records, and automate workflows. Use when the user wants to interact with Action Builder data.
72
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/action-builder/SKILL.mdQuality
Discovery
67%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 correctly identifies the tool (Action Builder) and provides an explicit 'Use when' clause, which is good for completeness. However, the capabilities listed are vague ('manage data, records, and automate workflows') and could describe many integration tools. The trigger terms are limited and the description would benefit from more specific actions and natural keywords users would use.
Suggestions
Add more specific concrete actions such as 'create/update records, query activist data, manage tags, configure automated workflows' to improve specificity.
Expand trigger terms to include variations users might naturally say, such as 'Action Builder API', 'activist records', 'action network', 'bulk data operations', or specific entity names.
Differentiate from other data/workflow tools by mentioning what makes Action Builder unique (e.g., the platform it belongs to, the type of data it manages like organizing or advocacy data).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Action Builder) and some actions ('manage data, records, and automate workflows'), but these are fairly generic and not comprehensive — it doesn't specify concrete actions like 'create records', 'update fields', 'trigger automations', or 'query lists'. | 2 / 3 |
Completeness | Answers both 'what' (manage data, records, automate workflows) and 'when' (Use when the user wants to interact with Action Builder data) with an explicit trigger clause, though both parts could be more detailed. | 3 / 3 |
Trigger Term Quality | Includes 'Action Builder' as a key trigger term and mentions 'data', 'records', and 'workflows', but misses common variations users might say such as 'Action Builder API', 'action network', specific entity types, or task-specific terms like 'bulk update', 'import contacts', etc. | 2 / 3 |
Distinctiveness Conflict Risk | 'Manage data, records, and automate workflows' is quite generic and could overlap with CRM tools, database skills, or other workflow automation skills. The 'Action Builder' name provides some distinctiveness, but the rest of the description is broad enough to cause conflicts. | 2 / 3 |
Total | 9 / 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 skill provides solid, actionable CLI commands for interacting with Action Builder through Membrane, with good coverage of the key operations. Its main weaknesses are the unnecessary introductory explanation of Action Builder, the lack of explicit workflow sequencing with validation checkpoints, and the large inline actions table that could be referenced separately. Trimming the preamble and adding clearer step-by-step workflow guidance would improve it significantly.
Suggestions
Remove the opening paragraph explaining what Action Builder is — Claude doesn't need this context. Start directly with the CLI usage.
Add an explicit numbered end-to-end workflow (e.g., '1. Install CLI → 2. Authenticate → 3. Connect → 4. Search actions → 5. Run action') with validation checkpoints at each step.
Move the 'Popular actions' table to a separate ACTIONS_REFERENCE.md file and link to it from the main skill to reduce token usage.
Remove the 'Action Builder Overview' bullet list (Action, Step, Variable, etc.) — it provides no actionable guidance and the terms are never referenced again.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explaining what Action Builder is ('no-code/low-code platform...citizen developers...without extensive coding knowledge') is unnecessary context for Claude. The overview section listing concepts without explanation adds little value. However, the CLI commands and workflow sections are reasonably tight. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands for every operation: installation, authentication, connecting, searching, creating, and running actions. Commands include specific flags (--json, --wait, --connectionId) and are copy-paste ready with clear placeholder conventions. | 3 / 3 |
Workflow Clarity | The multi-step workflows (auth flow, action creation with polling) are present and sequenced, but lack explicit validation checkpoints. The action creation polling workflow mentions checking for error states but doesn't provide a clear feedback loop for recovery. The overall flow from install → auth → connect → search → run is implicit rather than explicitly sequenced. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but the popular actions table is quite long and could be in a separate reference file. The skill links to external docs but doesn't split its own content across files. For its length (~120 lines), the inline approach is borderline acceptable but the actions table bloats the main file. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- membranedev/application-skills
- Commit
56d7336
- 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.