CtrlK
BlogDocsLog inGet started
Tessl Logo

api-proposal

Create prototype-backed API proposals for dotnet/runtime. Use when asked to draft an API proposal, write an api-suggestion issue, refine a vague API idea into a complete proposal, or improve a proposal marked api-needs-work. Covers the full pipeline from research through prototyping, ref source generation, and publishing. DO NOT USE FOR bug fixes, code review, performance benchmarking, or internal API changes that don't affect public surface area.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced procedural skill with explicit blocking validation checkpoints and clean one-level-deep references to real bundle files. Its only notable weakness is conciseness — the publishing and iteration phases contain enumeration and detail that could be trimmed.

Suggestions

Tighten Phase 5's three publishing options and Phase 6's three push strategies into more compact lists; the per-option prose and bash snippets repeat structure that could be condensed.

Consider moving the detailed 'Common Pitfalls' and 'Usage in dotnet/runtime' adoption-catalog format into a reference file, keeping SKILL.md focused on the phased workflow.

A few rationale paragraphs (e.g., Phase 0 step 5 workaround trade-offs) restate ideas already implied by checkpoints; trim to the action.

DimensionReasoningScore

Conciseness

The body largely assumes Claude's competence and avoids explaining basic concepts, but at ~380 lines it carries genuine padding in places — verbose Phase 5 publishing-option enumeration, Phase 6 push-strategy detail, and some explanatory redundancy — that could be tightened without losing clarity.

2 / 3

Actionability

Provides concrete, executable commands ('dotnet msbuild /t:GenerateReferenceAssemblySource', 'gh issue create --label api-suggestion --body-file proposal.md') and complete code examples (PriorityQueue, JsonNamingPolicy declarations) that are copy-paste ready, not pseudocode.

3 / 3

Workflow Clarity

Six numbered phases sequenced in order with explicit, labeled BLOCKING validation checkpoints (Phase 3, Prototype Validation 'all steps required', Phase 6 re-running Phase 2/3 validation), giving clear feedback loops for error recovery.

3 / 3

Progressive Disclosure

Main skill is a clear process overview with well-signaled one-level-deep references to real bundle files (references/proposal-examples.md, references/api-proposal-checklist.md) and external repo docs; content is appropriately split with easy navigation.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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

A strong, third-person description that names concrete capabilities, provides explicit natural-language triggers, and adds an exclusion clause for disambiguation. It cleanly answers both what the skill does and when to use it within a narrow, well-defined niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'draft an API proposal', 'write an api-suggestion issue', 'refine a vague API idea', 'improve a proposal marked api-needs-work', plus the pipeline of 'research through prototyping, ref source generation, and publishing'.

3 / 3

Completeness

Explicitly answers what (create prototype-backed API proposals covering the full pipeline) and when (an explicit 'Use when' clause enumerating multiple triggering situations).

3 / 3

Trigger Term Quality

Natural trigger phrasings a user would say ('draft an API proposal', 'write an api-suggestion issue', 'refine a vague API idea') with good coverage, reinforced by an explicit negative-trigger list ('DO NOT USE FOR bug fixes, code review, performance benchmarking').

3 / 3

Distinctiveness Conflict Risk

Highly niche scoping to dotnet/runtime with repo-specific labels (api-suggestion, api-needs-work) and an explicit exclusion list, making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
dotnet/runtime
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.