integrate-webapi
This skill should be used when the user asks to "integrate web api", "add web api", "connect to dataverse", "add api integration", "set up web api calls", "integrate api for my tables", "add crud operations", "hook up web api", "add data fetching", "connect frontend to dataverse", or wants to integrate Power Pages Web API into their site's frontend code with proper permissions and deployment. This skill orchestrates the full integration lifecycle: code integration, permissions setup, and deployment.
78
76%
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 ./plugins/power-pages/skills/integrate-webapi/SKILL.mdQuality
Discovery
89%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 excels at trigger term coverage and completeness, providing an extensive list of natural user phrases and clearly stating both what the skill does and when to use it. Its main weakness is that the capability description could be more specific about the concrete actions performed (e.g., generating specific code patterns, configuring specific settings). The description is functional and well-targeted for skill selection.
Suggestions
Replace the high-level 'orchestrates the full integration lifecycle' with specific concrete actions like 'generates Web API fetch calls, configures table permissions and site settings, deploys changes to Power Pages site'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'code integration, permissions setup, and deployment' and references 'crud operations', 'data fetching', and 'Web API integration', but it doesn't list multiple concrete specific actions in detail — it stays at a high level with 'orchestrates the full integration lifecycle' rather than enumerating specific steps like 'generates fetch calls, configures table permissions, creates site settings'. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (integrates Power Pages Web API into frontend code with permissions and deployment) and 'when' (provides a detailed 'Use when' list of trigger phrases and scenarios). The 'when' guidance is front and center. | 3 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger phrases users would say: 'integrate web api', 'connect to dataverse', 'add crud operations', 'hook up web api', 'add data fetching', 'connect frontend to dataverse'. These cover many natural variations of how a user might phrase their request. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to Power Pages Web API and Dataverse integration, which is a clear niche. Terms like 'Power Pages', 'Dataverse', and 'Web API' combined make it very unlikely to conflict with generic API or frontend skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured orchestration skill with clear multi-phase workflows, explicit validation checkpoints, and concrete executable commands throughout. Its primary weakness is extreme verbosity — the content is roughly 4x longer than necessary, with significant repetition (parallelization strategy stated 3+ times, deployment prerequisite mentioned in multiple phases, key decision points listed twice). The monolithic structure with all phases inline rather than split into referenced sub-documents compounds the token cost.
Suggestions
Extract Phases 6.2-6.4 (permissions setup with Path A/B branching) into a separate reference file like `permissions-setup-reference.md` — this section alone is ~150 lines and is self-contained enough to be referenced.
Remove the 'Important Notes' section entirely — it restates the core principles, key decision points, and progress tracking that are already embedded in the phase descriptions. The progress tracking table duplicates the workflow section.
Consolidate repeated statements: the 'first table sequential, then parallel' principle is stated in Core Principles, Phase 4.2, and Important Notes. State it once in Phase 4.2 where it's actionable.
Trim explanatory prose that Claude can infer — e.g., 'These two agents are independent — invoke them in parallel using two Task calls simultaneously' can be reduced to just showing the two parallel Task invocations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It over-explains orchestration logic that Claude can infer (e.g., 'These two agents are independent — invoke them in parallel'), repeats information across phases (deployment prerequisite mentioned multiple times), and includes extensive tables and templates that could be condensed. The 'Important Notes' section at the end largely restates what was already covered in the phases. | 1 / 3 |
Actionability | The skill provides fully executable PowerShell and Node.js commands with specific flags, concrete prompt templates for sub-agents, exact file paths to check, and specific script invocations with all required arguments. The guidance is copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | The 7-phase workflow is clearly sequenced with explicit validation checkpoints (Phase 5 build verification, file inventory checks, deployment prerequisite gates). It includes feedback loops (fix and re-validate on build failure), decision branching (Path A vs Path B for permissions), and explicit ordering constraints (first table sequential, then parallel). Destructive/batch operations have verification steps. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (framework-conventions.md, skill-tracking-reference.md, agent files), but the main SKILL.md itself is monolithic — all 7 phases with full detail are inline rather than being split into separate reference files. The permissions section (6.2-6.4) alone is massive and could be extracted. However, references that do exist are one-level deep and clearly signaled. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (553 lines); consider splitting into references/ and linking | Warning |
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 | 8 / 11 Passed | |
- Repository
- microsoft/power-platform-skills
- Commit
66a61c6
- 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.