diagnose-why-work-stopped

Diagnose stalled, looping, or over-recovered Paperclip issue trees and propose a no-code product-rule plan. Use when asked why work stopped, why it looped, or how to prevent a tree from going too deep.

Quality

92%

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

85%

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

A well-structured, actionable diagnostic procedure with strong workflow sequencing, approval gates, and a verification checklist; the main weakness is repetition of the invariants and no-code rule across multiple sections.

Suggestions

Consolidate the three invariants into one authoritative statement and reference it by name elsewhere instead of restating it in Procedure step 4 and Pitfalls.

Merge the recurring 'no code before approval' reminders into a single gate in the Procedure and let the checklist enforce it, removing the duplicate framing in Pitfalls.

Trim 'the user has said / the user has explicitly called this out' preambles to the concrete instruction they support.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific (no generic-concept padding), but the three invariants and the 'no code before approval' rule are restated across invariants, Procedure step 4/5, Pitfalls, and the checklist, and several 'the user has said ...' framings could be tightened.	2 / 3
Actionability	Highly concrete for an instruction-only skill: specific interaction types, an idempotency-key format ('confirmation:{issueId}:plan:{revisionId}'), named fields (blockedByIssueIds, request_confirmation), classification categories, and assignee suggestions.	3 / 3
Workflow Clarity	A clearly numbered Procedure (steps 0–8) with explicit approval/confirmation gates, re-confirmation feedback when a plan is superseded, and a pre-post Verification checklist with checkpoints.	3 / 3
Progressive Disclosure	No skill-internal bundle files exist, but the body is organized into clearly navigable sections and appropriately defers detailed semantics to the source-of-truth doc (doc/execution-semantics.md) rather than duplicating it.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 concise, specific, and complete: it names the domain and concrete actions, provides natural trigger phrases, and answers both 'what' and 'when' in third person.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Diagnose stalled, looping, or over-recovered Paperclip issue trees and propose a no-code product-rule plan'), each tied to a specific domain rather than vague language.	3 / 3
Completeness	Clearly states what it does (diagnose trees and propose a product-rule plan) and gives an explicit 'Use when asked ...' clause covering multiple trigger conditions.	3 / 3
Trigger Term Quality	Natural trigger phrases a user/manager would say are present: 'why work stopped', 'why it looped', 'how to prevent a tree from going too deep', plus 'stalled, looping, over-recovered'.	3 / 3
Distinctiveness Conflict Risk	Highly niche — 'Paperclip issue trees', 'over-recovered', liveness/recovery domain — with triggers unlikely to collide with other skills.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 19 suspicious	Warning

	Total	15 / 16 Passed

Repository: paperclipai/paperclip
Path: .agents/skills/diagnose-why-work-stopped/SKILL.md
Commit: 81f47e7

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.