issue-triage

Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%

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

A tight, well-structured instruction skill that assumes Claude's competence and supplies only novel domain knowledge — specific endpoints, statuses, and a clear classify-then-act workflow with explicit guardrails and a completion checklist.

Dimension	Reasoning	Score
Conciseness	The ~60-line body is lean with no concept-explanation Claude already knows; every section (When to use, When not to use, Inputs, classifications, heuristics, don't-do, Output) is novel Paperclip-specific operational guidance that earns its place; not a 2 because there is no padding to tighten.	3 / 3
Actionability	Gives exact endpoints ('GET /api/agents/me/inbox-lite', 'GET /api/issues/{issueId}/heartbeat-context'), exact status transitions, and exact interaction types to create ('request_confirmation', 'ask_user_questions', 'request_board_approval'); not a 2 because guidance is concrete and complete, not pseudocode.	3 / 3
Workflow Clarity	Clear sequence (fetch inbox-lite → fetch heartbeat-context per issue → classify into one of six → act → summarize) with explicit checkpoints: the one-minute escalation fallback, the don't-do guardrails, and the completion-bar output checklist; not a 2 because checkpoints are explicit, not implicit or missing.	3 / 3
Progressive Disclosure	Single-purpose, self-contained skill with well-organized section headers and no external bundle references needed (and none referenced), satisfying the simple-skill note that well-organized sections alone warrant a 3; not a 2 because content is appropriately sectioned rather than an inline monolith.	3 / 3
	Total	12 / 12 Passed

Description

82%

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 specific, well-scoped description with concrete actions and good trigger-term coverage, but it lacks an explicit 'Use when...' invocation clause, leaving the 'when' implied rather than stated.

Suggestions

Add an explicit trigger clause such as 'Use when reviewing a noisy Paperclip inbox of stale, blocked, in-review, or stalled assignments, or when a manager wants a status read without asking each agent.'

Mirror a natural user phrasing in the trigger (e.g. 'Use when the user asks to triage their inbox or unblock stalled issues') to make the when-to-invoke intent explicit rather than implied by the target-issue list.

Dimension	Reasoning	Score
Specificity	Names the domain and five concrete next actions in parentheses — 'resume, reassign, unblock, escalate, or close' — matching the 'lists multiple specific concrete actions' anchor; not a 2 because the action set is comprehensive rather than partial.	3 / 3
Completeness	The 'what' is explicit (triage issues and decide a next action) but there is no 'Use when...' trigger clause; the issue-state list characterizes targets rather than an explicit when-to-invoke trigger, and the guideline caps completeness at 2 without one.	2 / 3
Trigger Term Quality	Natural state terms a manager would actually say — 'stale, blocked, in-review, or assigned-but-not-progressing' — give good coverage of the trigger states; not a 2 because common variations of the triage triggers are present.	3 / 3
Distinctiveness Conflict Risk	The narrow 'Paperclip inbox' niche combined with specific issue states makes it clearly distinguishable and unlikely to fire for the wrong skill; not a 2 because the domain framing is distinct rather than overlapping.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: paperclipai/paperclip
Path: packages/skills-catalog/catalog/bundled/paperclip-operations/issue-triage/SKILL.md
Commit: 14f20be

Reviewed: 4 days 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.