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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/skills-catalog/catalog/bundled/paperclip-operations/issue-triage/SKILL.md

Quality

Content

83%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.

The skill body is lean, highly actionable, and well-structured, giving Claude exact endpoints, fields, status transitions, and decision rules for every triage case. The main gap is the lack of validation/verification feedback loops for the batch, semi-destructive status changes, which caps workflow clarity.

Suggestions

Add an explicit validation/verification checkpoint after taking action on each issue (e.g., confirm the status change or reassignment took effect before moving on; retry or escalate on API failure), which would lift workflow clarity above the batch/destructive cap of 3.

Add a worked example of a completed triage pass output (one filled-in per-issue summary line) so the "Output of a triage pass" format is unambiguous and copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what triage, an inbox, or issue statuses are, and every section (When to use, Inputs, decisions, heuristics, don't-do, output) earns its place with no padding.	5 / 5
Actionability	Guidance is fully executable for an instruction-only skill: concrete API endpoints ("GET /api/agents/me/inbox-lite", "GET /api/issues/{issueId}/heartbeat-context"), named fields (blockerAttention, executionState), specific status values, interaction types, and concrete decision criteria covering all six classifications.	5 / 5
Workflow Clarity	The sequence (fetch inbox -> per-issue context -> classify -> act -> summarize) is present with a completion bar, but this is a batch operation making destructive changes (close/cancel/reassign) with no validate->fix->retry feedback loop, which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Content is well-organized into clearly headed, self-contained sections with no nested references and nothing that belongs in a separate file, but the body is slightly over the 50-line simple-skill threshold and there is no reference structure to evaluate, so it sits at "good structure, appropriately placed" rather than the reference-split 5.	4 / 5
	Total	17 / 20 Passed

Description

75%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.

The description is specific, concrete, and tightly scoped to a distinct Paperclip triage niche, with strong action coverage and low conflict risk. Its main weakness is the absence of an explicit "Use when..." trigger clause, leaving the invocation conditions only weakly implied.

Suggestions

Add an explicit "Use when..." clause naming the triggering situations (e.g., "Use when reviewing a stale or noisy Paperclip inbox, or when an in-progress/in-review/blocked issue has stalled"), which would lift completeness above 3.

Broaden trigger-term coverage with natural synonyms a user might say (e.g., "stuck", "backlog", "review queue", "no-progress assignments") so the skill surfaces for a wider range of phrasings.

Dimension	Reasoning	Score
Specificity	Lists five concrete next actions — "resume, reassign, unblock, escalate, or close" — plus the triage action and the qualifying issue states (stale, blocked, in-review, assigned-but-not-progressing), giving comprehensive coverage of the decision space.	5 / 5
Completeness	The "what" is clear (triage issues and decide a single next action), but there is no explicit "Use when..." clause; the "when" is only weakly implied through the listed issue states, which caps completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	Natural domain terms like "triage", "inbox", "stale", "blocked", and "in-review" are phrases a manager would actually say, but common synonyms (e.g., stuck, backlog, review queue) are missing.	4 / 5
Distinctiveness Conflict Risk	It targets a clear niche — Paperclip inbox triage with specific issue-state triggers — making it highly distinguishable from other skills with minimal conflict risk.	5 / 5
	Total	17 / 20 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: 890ab9a

Reviewed: about 16 hours 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.