paperclip-distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.

Quality

88%

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

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.

The content is an excellent instruction-only skill: a clearly sequenced workflow with genuine validation checkpoints, explicit stop-and-surface error paths, and copy-paste-concrete output specifications. Its only real gap is progressive disclosure — everything lives in one long SKILL.md, and the detailed page templates would slot naturally into reference files — plus minor redundancy that could be trimmed for token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely non-obvious domain rules (asset gate, destination-space gate, anti-patterns) and assumes Claude's competence, never explaining what a wiki or Paperclip is. Minor trimmable redundancy exists (current_as_of/datestamp rules restated across Anti-patterns, Workflow, and Verification; Inputs lists standup and index paths separately), which fits anchor 4 rather than 5.	4 / 5
Actionability	Guidance is fully concrete for an instruction-only skill: exact paths like "wiki/projects/<slug>/standup.md", exact section names and ordering, exact frontmatter fields, a copy-paste log-entry template, the explicit prohibition "Never fetch /api/assets/:id/content", and a good/bad prose contrast. This matches anchor 5 per the instruction-skill scoring note.	5 / 5
Workflow Clarity	Ten clearly sequenced steps with explicit validation (Verification checklist before closing the operation issue) and error-recovery feedback loops: wrong spaceSlug "stop and surface the mismatch in a comment", asset requests redirected to the Phase 5 gate, low-signal windows get a logged skip, and warnings set "human_review_required: true". Batch wiki writes with checkpoints match anchor 5.	5 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/ directories) and the body references none; the wiki/... paths and AGENTS.md are runtime artifacts. The single file is well-sectioned with no buried or nested references, but ~120 lines of inlined page-shape templates for four-plus output files could plausibly live in reference files, which fits anchor 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

87%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 strong: it has an explicit 'Use when' clause with the three concrete operation types and a clear, specific statement of what the skill produces. Its only weakness is that trigger vocabulary is entirely internal jargon with no broader synonyms, which slightly limits natural-term coverage.

Dimension	Reasoning	Score
Specificity	"Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing" names several concrete artifact outputs plus a scope constraint. It matches anchor 4 (several specific actions, minor gaps) rather than 5 because it rests on a single action verb and omits patching/log-refresh actions, and it exceeds anchor 3's 1-2 concrete actions.	4 / 5
Completeness	It explicitly answers both parts: "Use when an operation issue is a Paperclip cursor-window, distill, or backfill" (when, with concrete trigger phrases) and the what (turn source-bundled activity into standups, project pages, decisions, and history). This matches anchor 5; the when clause is fully explicit, so it is not the anchor-4 case of a merely adequate when.	5 / 5
Trigger Term Quality	"Paperclip cursor-window, distill, or backfill" and "operation issue" are the natural trigger vocabulary of this system and cover all three operation types. Good keyword coverage matching anchor 4, not 5, because broader natural synonyms (e.g. "wiki", "standup") are absent and the terms are system-specific.	4 / 5
Distinctiveness Conflict Risk	"Paperclip cursor-window, distill, or backfill" carves a clear niche with distinct triggers that will not fire for sibling skills (ingest/query handle other operation types). Minimal conflict risk matches anchor 5.	5 / 5
	Total	18 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: paperclipai/paperclip
Path: packages/plugins/plugin-llm-wiki/skills/paperclip-distill/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.