CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-adr-migrator

Use when planning an ADR-driven migration from adoption tooling through stacked batch implementation and cleanup.

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/create-adr-migrator/SKILL.md

The canonical home for this skill is create-adr-migrator in primer/react

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 body presents a well-sequenced, token-efficient facilitation workflow with a genuine feedback loop during tooling iteration, and it is cleanly sectioned. Its weaknesses are the abstract execution details for the tooling and migrator the skill is supposed to produce, and the absence of any per-batch validation checkpoint in a batch/stack-driven process.

Suggestions

Add an explicit per-batch validation checkpoint, e.g. 'Before stacking the next batch, confirm migration-status.yml reports zero unmigrated files in the batch's scope and all stacked PRs pass checks,' to lift workflow clarity past the batch-operation cap.

Make the tooling directives executable: give a concrete detection pattern (e.g. an eslint rule invocation or a sample migration-status.yml snippet) and a sample 'gh stack' usage instead of 'Author code that will identify files that are not migrated yet'.

Move the batching methodology and journey details into a reference file (e.g. references/batching.md) and link it from Step 4, keeping SKILL.md as a tighter overview.

DimensionReasoningScore

Conciseness

The body is lean and procedural — a numbered journey, requirement questions, and four step sections with no explanation of concepts Claude already knows. Minor instances of over-explanation remain ('The goal of the migrator is to complete the journey at the beginning of this skill (although some steps may already be done)'), matching 'Efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean anchor 5.

4 / 5

Actionability

Concrete anchors exist ('migration-status.yml', 'gh stack', eslint/jscodeshift prompts, specific requirement questions), but the central directives stay abstract — 'Author code that will identify files that are not migrated yet' and 'create a skill and other necessary artifacts' give no commands, examples, or detection approach. This fits 'Some concrete guidance but incomplete... missing key details', below 4 whose guidance is mostly executable.

3 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced and Step 3 includes an explicit user feedback loop ('apply the feedback to the tooling and repeat the process until the user is satisfied'), but this is a batch-operation skill (stacked batches via 'gh stack') with no per-batch validation checkpoint — nothing verifies a batch migrated cleanly before the next is stacked. The rubric caps batch workflows without validation at 3, which takes precedence over the sequence quality that would otherwise suggest 4.

3 / 5

Progressive Disclosure

No bundle files exist or are referenced, and the ~85-line body is well organized under clear step headings with nothing that demands splitting. This matches 'Good structure; most content is appropriately placed; minor organization gaps'; it does not reach 5 because the body exceeds the under-50-line simple-skill exception and the promised batching methodology ('The method for batching should be included in this skill') would naturally live in a reference file.

4 / 5

Total

14

/

20

Passed

Description

48%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 has an explicit, well-formed trigger clause and occupies a distinct niche, but it never states what the skill actually does — the capability list exists only by implication inside the 'Use when' phrase. Concrete action verbs and synonym coverage for key terms (ADR, codemod, stacked PRs) are the main gaps.

Suggestions

State the 'what' explicitly alongside the trigger, e.g. 'Facilitates creating an ADR, migration-status tooling, codemods, and a batch migrator delivered as a gh stack. Use when planning an ADR-driven migration...' so completeness reaches both what and when.

Replace abstract nouns with concrete actions ('document the decision', 'build codemods with eslint/jscodeshift', 'track unmigrated files in migration-status.yml', 'deliver batches as stacked PRs') to raise specificity from domain-naming to action-listing.

Add natural synonym terms users would say — 'architecture decision record', 'codemod', 'stacked PRs', 'refactor migration' — to widen trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ('ADR-driven migration') and sketches an arc ('from adoption tooling through stacked batch implementation and cleanup') but never states a concrete action. This matches the anchor 'Names the domain but actions are minimal or generic' — it is above 1 because the domain is specific, but below 3 because no concrete actions like 'create an ADR' or 'generate codemods' are listed.

2 / 5

Completeness

The 'when' is explicit ('Use when planning an ADR-driven migration...') but the 'what' is never separately stated — it is only implied by the trigger phrase, mirroring anchor 2's 'Use when working with documents' shape. It lands at 3 rather than 2 because the when-clause names the full journey (adoption tooling through batches to cleanup), carrying an implied what; it cannot be 4 since no explicit what/when pairing exists.

3 / 5

Trigger Term Quality

'ADR', 'migration', and 'stacked batch' are terms a user would naturally say, but common variations are absent ('architecture decision record', 'codemod', 'refactor', 'stacked PRs'). This fits 'Some relevant keywords but missing common variations or synonyms', below 4 whose keyword coverage includes the natural synonyms users actually use.

3 / 5

Distinctiveness Conflict Risk

'ADR-driven migration' is a distinct niche unlikely to trigger the wrong skill, though the generic word 'migration' creates minor overlap risk with broader migration/refactoring skills. This matches 'Mostly distinct; minor overlap risk with closely related skills', below 5 because 'migration' alone is not a fully distinctive trigger.

4 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

primer/react

Path

.agents/skills/create-adr-migrator/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.