create-issue-interaction-ui

Add a new Paperclip issue-thread interaction kind end-to-end. Use when repo work introduces or extends interaction cards like request_confirmation, checkbox confirmations, ask_user_questions, or suggest_tasks.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

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

An exemplary maintainer-guide body: precise, actionable, and sequenced with real validation checkpoints. The only refinements are trimming the duplicated warnings and potentially moving per-layer file touch lists into reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense and imperative, driven by exact file paths and invariants with no padding or explanation of known concepts. Minor duplication ('Do NOT install this on production Paperclip agents' appears twice, and 'Developer/maintainer skill' is repeated) keeps it just below the leanest anchor.	4 / 5
Actionability	Fully executable guidance throughout: exact per-layer file touch lists, copy-paste vitest and git commands, a concrete idempotency-key format ('<kind>:<issueId>:<decisionKey>:<revisionId>'), and a specific troubleshooting note for the 'act is not a function' failure.	5 / 5
Workflow Clarity	An explicit 'Order of operations' section with rationale, five clearly numbered layers, a dedicated pre-review test section with runnable commands, a pre-merge checklist, and error-recovery guidance — validation checkpoints are explicit and well placed.	5 / 5
Progressive Disclosure	Well-sectioned single-file skill with no bundle files, so all in-repo pointers (e.g. skills/paperclip/references/api-reference.md, PR #7649) resolve to real targets. The ~275-line per-layer touch lists could be split into references/ files, which places it at 'good structure; minor organization gaps' rather than the ideal split.	4 / 5
	Total	18 / 20 Passed

Description

82%Weight 40%Scale 1-5

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 well-crafted, niche description with an explicit 'Use when' trigger clause and concrete sibling-kind examples. Its only weakness is that the 'what' is a single broad action rather than a list of concrete capabilities.

Suggestions

Enumerate 2-3 concrete actions in the description (e.g. 'define the shared payload/validator contract, wire server routes and UI cards, add CLI/MCP/plugin helpers') to raise specificity.

Add one or two colloquial synonyms users might say, such as 'approval card' or 'new card kind', to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain precisely ('Paperclip issue-thread interaction kind') and gives one concrete action ('Add ... end-to-end'), but does not enumerate the concrete sub-actions the skill covers (contract, validators, routes, UI wiring, docs). It sits at the 'names domain and 1-2 concrete actions' anchor rather than 'lists several specific actions'.	3 / 5
Completeness	It explicitly answers both what ('Add a new Paperclip issue-thread interaction kind end-to-end') and when ('Use when repo work introduces or extends interaction cards like ...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good keyword coverage with natural terms a contributor would say: 'interaction cards', 'checkbox confirmations', and the four kind names (request_confirmation, ask_user_questions, suggest_tasks). A few natural variations (e.g. 'approval card', 'new card kind') are missing, placing it just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche — repo work on a named product's issue-thread interaction kinds, with four specific sibling kinds listed — making it highly distinguishable from any other skill with minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: paperclipai/paperclip
Path: .agents/skills/create-issue-interaction-ui/SKILL.md
Commit: 1c07b59

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.