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

85%

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%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 exceptionally actionable and its workflows are clearly sequenced with validation and error-recovery loops throughout — every command is copy-paste ready. Its weaknesses are repetition of the port-identity and reseed themes across sections and the absence of any progressive-disclosure structure, with 500+ lines of reference-grade material inlined in SKILL.md.

Suggestions

Move the 'Common failures and fixes' catalog, 'Recurring gotchas', and the final issue-comment template into one-level-deep reference files (e.g. references/failures.md, references/comment-template.md), keeping SKILL.md to the success conditions, hard rules, and run sequence with clearly signaled links.

Deduplicate the port-squat identity guidance: state the /proc/<pid>/cwd check once in 'Port conflicts and workspace identity' and have 'Hard rules' and the failure catalog reference that section instead of restating the rationale.

Consolidate the full-reseed guidance, which currently appears in four sections (Hard rules, Normal run sequence, Full database reseed, and three failure entries), into the single 'Full database reseed' section with pointers.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely non-obvious operational knowledge, but the port-squat / /proc/<pid>/cwd identity theme is restated in Hard rules, Port conflicts and workspace identity, and two failure-catalog entries, and full-reseed guidance recurs across four sections. This matches 'mostly efficient but could be tightened' rather than the minor-trim 4 anchor.	3 / 5
Actionability	Guidance is fully executable throughout: copy-paste curl commands with exact headers and payloads, the exact reseed CLI (npx paperclipai worktree reseed --from-instance default --seed-mode full --yes), concrete probes (lsof -nP -iTCP:… -sTCP:LISTEN, readlink /proc/$pid/cwd), named env vars, targeted test commands, and a fill-in issue-comment template.	5 / 5
Workflow Clarity	The 10-step run sequence, success checklist, explicit verification after every start/restart, error-recovery loops ('loop back to the narrowest repair step'), and the symptom/cause/fix/verify failure catalog provide clear sequencing with explicit validation and feedback loops, matching the top anchor; the destructive-operation validation cap does not apply since verification is pervasive.	5 / 5
Progressive Disclosure	The single 517-line SKILL.md is well-sectioned but has no bundle files at all, and content that clearly belongs in separate one-level-deep references (the common-failures catalog, recurring gotchas, final comment template) is inlined. This fits 'some structure but content that should be separate is inline', not the 4 anchor where most content is appropriately placed across files.	3 / 5
	Total	16 / 20 Passed

Description

92%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 names concrete actions and outcomes, uses third-person imperative voice, and pairs a clear capability statement with an explicit 'Use when…' trigger clause. The only gap is modest keyword coverage of failure-mode phrasings users might actually say.

Dimension	Reasoning	Score
Specificity	"Run, verify, reseed, and repair Paperclip isolated dev workspace services" plus the enumerated proofs ("health, login readiness, cloned data, runtime visibility, and correct port ownership") list multiple specific concrete actions with comprehensive coverage, matching the top anchor; no coverage gaps justify a 4.	5 / 5
Completeness	It explicitly answers both what ("Run, verify, reseed, and repair Paperclip isolated dev workspace services") and when ("Use when asked to start or fix a managed project/worktree service") with concrete trigger phrases, exactly matching the 5 anchor rather than the less-explicit 4 anchor.	5 / 5
Trigger Term Quality	"Use when asked to start or fix a managed project/worktree service" provides good natural keyword coverage (start, fix, worktree service, dev workspace), but common user phrasings like restart, broken, not healthy, or login failures are missing, so it falls short of the synonym-saturated 5 anchor.	4 / 5
Distinctiveness Conflict Risk	"Paperclip isolated dev workspace services" carves out a clear product-specific niche with distinct triggers (worktree service, managed runtime, port ownership), so the risk of firing for an unrelated skill is minimal.	5 / 5
	Total	19 / 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
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: 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.