CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nx-multi-repo-migrate

Migrate several repos to a target nx version (e.g. 23.0.0-beta.25) in one coordinated pass — delegates `nx migrate` + migrations to a Polygraph child agent per repo, then pushes branches and opens linked draft PRs. Use when asked to upgrade/migrate multiple repos to a specific nx version, or when working a Polygraph session whose goal is an nx version bump across repos.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

An operationally rich, highly actionable skill with excellent workflow sequencing and validation for a risky batch operation, built almost entirely from hard-won non-obvious detail. Its weaknesses are stylistic density (very long run-on sentences and some repetition) and a monolithic structure that inlines reference-grade material instead of splitting it into bundle files.

Suggestions

Move the orchestrated-loop protocol (step 7) and "Gotchas from real runs" into references/ files (e.g. references/orchestrated-loop.md, references/gotchas.md), keeping SKILL.md a lean overview with clearly signaled one-level-deep links.

Break up the 150+ word run-on sentences in step 7's bullets into short imperative steps; the mutable-install env-var reminder and NX_MIGRATE_ORCHESTRATOR note each recur across multiple steps and can be stated once.

Extract the child-agent migration instruction (the blockquote in step 2) into its own reference file so it can be handed to children verbatim without loading the parent-facing orchestration context.

DimensionReasoningScore

Conciseness

Nearly all content is non-obvious operational knowledge Claude cannot be assumed to know (release-age gates, sandbox EPERM quirks, crash recovery), so it earns its tokens; however, step 7's 150+ word run-on sentences, repeated mutable-install/`NX_MIGRATE_ORCHESTRATOR` reminders across steps, and the pharmacist analogy in the intro are padding that could be tightened. This matches anchor 3 ("mostly efficient but ... could be tightened") rather than 4, where over-explanation would be only minor.

3 / 5

Actionability

Fully executable guidance throughout: exact commands (`git fetch origin <base> && git checkout -B migrate-nx-<VERSION> origin/<base>`, `node -p "require('./node_modules/nx/package.json').version"`, `NX_MIGRATE_ORCHESTRATOR=true <pm> nx migrate --run-migrations ...`), concrete env-var bypasses, and a complete package-manager cheat-sheet table cover the common cases copy-paste ready.

5 / 5

Workflow Clarity

The multi-step process is clearly sequenced (session setup → parallel child delegation → incremental push/PR), the child procedure is numbered 1–11 with an explicit verification step before declaring done, and it includes a per-repo verification checklist plus error-recovery paths (retry/adopt/skip/unresolved, crash/timeout recovery). This batch operation has explicit validation checkpoints and feedback loops, matching the 5 anchor.

5 / 5

Progressive Disclosure

The body is well-sectioned with headers, but at roughly 100 dense lines it inlines content that clearly belongs in separate reference files — the orchestrated-loop protocol (step 7), the child-agent migration instruction, and "Gotchas from real runs" would each work better as one-level-deep references/ files. This matches anchor 3 ("content that should be separate is inline") rather than 4, where organization gaps would be minor.

3 / 5

Total

16

/

20

Passed

Description

100%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.

An exemplary description: third-person voice, comprehensive concrete actions, explicit "Use when" triggers with two distinct invocation contexts, and natural synonym coverage. It is both specific and clearly distinguishable from adjacent skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the entire workflow: "delegates `nx migrate` + migrations to a Polygraph child agent per repo, then pushes branches and opens linked draft PRs". Coverage is comprehensive with no minor gaps, matching the 5 anchor rather than the 4 anchor.

5 / 5

Completeness

Both what ("Migrate several repos to a target nx version ... in one coordinated pass") and when ("Use when asked to upgrade/migrate multiple repos to a specific nx version, or when working a Polygraph session whose goal is an nx version bump across repos") are explicitly and concretely answered, exactly matching the 5 anchor example's structure.

5 / 5

Trigger Term Quality

Natural trigger phrasing is comprehensively covered with synonyms: "upgrade/migrate multiple repos to a specific nx version", "nx version bump across repos", "Polygraph session". All the ways a user would naturally phrase this need are present, matching the 5 anchor over the 4 anchor ("a few natural terms missing").

5 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — coordinated multi-repo nx version migration via Polygraph child agents — with distinct trigger terms that no general-purpose migration or PR skill would match, so conflict risk is minimal.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

nrwl/nx

Path

.claude/skills/nx-multi-repo-migrate/SKILL.md

Reviewed

Table of Contents

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.