paperclip-dev-workspace-run-verify-fix

Run, verify, reseed, and repair Paperclip isolated dev workspace services. Use when asked to start or fix a managed project/worktree service and prove health, login readiness, cloned data, runtime visibility, and correct port ownership.

Quality

88%

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

77%

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

The body is a highly actionable operational runbook with strong workflow sequencing and verification loops for risky operations. Its main weaknesses are redundancy of the port-squat theme and a monolithic single-file structure that could benefit from progressive disclosure.

Suggestions

Consolidate the port-squat/identity-check guidance into one authoritative section and have other sections cross-reference it instead of re-explaining, to tighten conciseness.

Move 'Common failures and fixes' and 'Recurring gotchas' into a reference file referenced from the main runbook to improve progressive disclosure and keep SKILL.md a lean overview.

Trim restated success conditions that appear both in the opening checklist and the final comment template to reduce token redundancy.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is full of novel domain knowledge, but the port-squat/identity-check theme recurs across 'Hard rules', 'Port conflicts and workspace identity', 'Common failures', and 'Recurring gotchas' with enough repetition that it could be tightened; not the level-3 'every token earns its place'.	2 / 3
Actionability	Provides copy-paste-ready, executable commands throughout (curl managed start/stop/restart, lsof/readlink identity checks, pnpm reseed, vitest), fully meeting the level-3 anchor rather than pseudocode.	3 / 3
Workflow Clarity	The 10-step 'Normal run sequence' is clearly sequenced with explicit validation checkpoints (identity check before and after every repair, 'loop back to the narrowest repair step'), matching the level-3 anchor with feedback loops for the destructive/database operations.	3 / 3
Progressive Disclosure	It is a single ~500-line file with no external references and clear sectioning, but the 'Common failures and fixes' and 'Recurring gotchas' blocks are inline content that could be split into a reference file; it is not the level-3 'well-signaled one-level-deep references' and exceeds the simple-skill carve-out.	2 / 3
	Total	10 / 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, third-person, and explicitly couples concrete capabilities with a clear Use-when trigger for a distinct Paperclip niche. It hits the strong anchors on all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Run, verify, reseed, and repair' plus 'prove health, login readiness, cloned data, runtime visibility, and correct port ownership'), matching the level-3 anchor of several specific concrete actions rather than the level-2 partial list.	3 / 3
Completeness	Explicitly answers both what (run/verify/reseed/repair the dev workspace service) and when via an explicit 'Use when...' clause, satisfying the level-3 anchor and exceeding the level-2 'when implied' cap.	3 / 3
Trigger Term Quality	Includes natural trigger phrasing a user would say ('Use when asked to start or fix a managed project/worktree service'), giving good coverage of the domain's common verbs rather than only technical jargon.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to 'Paperclip isolated dev workspace services' with distinct port-ownership/worktree triggers, creating a clear niche unlikely to fire for unrelated 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
skill_md_line_count	SKILL.md is long (518 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: paperclipai/paperclip
Path: .agents/skills/paperclip-dev-workspace-run-verify-fix/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.