papercuts

Log genuine, recurring repository friction to .agents/PAPERCUTS.md — confusing setup, a flaky repo command or script, a misleading in-repo error, stale generated files, or a non-obvious gotcha that will cost the next contributor time. Also use to review, deduplicate, and resolve existing entries. Gate hard before logging: only friction the repository itself can fix counts. Never log the agent's own sandbox/permission errors, shell-scripting mistakes, transient flakiness, or third-party tool quirks the repo can't change.

Quality

91%

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

100%Weight 40%Scale 1-3

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

A tight, actionable skill body with concrete format templates, clearly sequenced workflows, and built-in validation gates. It assumes competence throughout and avoids bloat, exemplifying token-efficient progressive disclosure for a self-contained skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no definitions of basic concepts, every section earns its place (two-question test, Do NOT log, Log proactively, Review or resolve). Not a level below because there is no padding or unnecessary explanation.	3 / 3
Actionability	Provides copy-paste-ready guidance: exact path `.agents/PAPERCUTS.md`, a concrete markdown template `- [ ] \`YYYY-MM-DDTHH:MM:SSZ\` — \`agent\` — <friction...>`, UTC timestamps, and short agent labels. Not a level below because the format is executable as written.	3 / 3
Workflow Clarity	Both flows are explicitly sequenced (4-step logging, 5-step review) with validation checkpoints — the two-question test gate, "Verify each surviving papercut still reproduces," and delete-on-failure feedback. Not a level below because error-recovery and verification steps are explicit.	3 / 3
Progressive Disclosure	Self-contained with no external references needed and well-organized into clearly signaled sections; no nested/deep references. Not a level below because the structure is appropriate for a single-purpose skill of this size.	3 / 3
	Total	12 / 12 Passed

Description

82%Weight 40%Scale 1-3

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-targeted description in third person with strong trigger terms and a distinct niche. Its one weakness is the absence of an explicit "Use when..." trigger clause, leaving the invocation timing implied rather than stated.

Suggestions

Add an explicit "Use when..." clause (e.g., "Use when you hit reproducible, repo-fixable friction during a task, or when asked to review the papercuts log") to lift completeness to 3.

Front-load the invocation trigger before the exclusions so the "when" is immediately visible.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Log genuine, recurring repository friction," "review, deduplicate, and resolve existing entries" — rather than vague language. Not a level below because it goes beyond naming a single domain to enumerating specific behaviors.	3 / 3
Completeness	It clearly answers "what" but lacks an explicit "Use when..." clause; the primary invocation trigger (log friction in the moment) is implied rather than stated, so per the guideline completeness is capped at 2. Not a level above because a 3 requires an explicit when-trigger clause as in the anchor example.	2 / 3
Trigger Term Quality	Natural contributor-facing terms appear throughout — "friction," "confusing setup," "flaky repo command," "misleading error," "stale generated files," "gotcha" — which a user would plausibly say. Not a level below because coverage spans common variations rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — logging repository friction to .agents/PAPERCUTS.md — with distinct triggers unlikely to collide with other skills. Not a level below because the scope is specific and self-contained.	3 / 3
	Total	11 / 12 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: every-app/open-seo
Path: .agents/skills/papercuts/SKILL.md
Commit: f569726

Reviewed: 7 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.