CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

od-code-migration

Default reference pipeline for the code-migration taskKind — code-import → design-extract → token-map → rewrite-plan → patch-edit ↔ build-test devloop → diff-review → handoff.

60

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/scenarios/od-code-migration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 is a tight, well-structured pipeline definition with an explicit convergence loop and typed input declarations; it scores especially well on workflow clarity and organization. Its only weaknesses are minor jargon-laden asides and the absence of guidance on how the atoms are executed beyond the declarative config.

Suggestions

Trim the spec-bookkeeping asides ('promoted into the spec §22.4 vocabulary by the `build-test` atom') that restate the `until` condition without adding operational guidance.

Add one line on how the `until` failure path behaves in practice (e.g. what to do when iterations>=8 is hit) to round out the feedback loop's error-recovery story.

DimensionReasoningScore

Conciseness

The body is lean with no tutorial filler or concepts Claude already knows, but the 'promoted into the spec §22.4 vocabulary' sentence and 'cannot ship an `accept` decision' line partly restate the `until` condition already encoded in the config — minor over-explanation that could be trimmed, matching anchor 4 rather than 5.

4 / 5

Actionability

The JSONC pipeline is concrete and copy-paste-ready within its plugin system (exact stage ids, atom names, `repeat`/`until` expressions) and inputs declare names, types, and required flags — mostly executable guidance, but there is no guidance on how any atom is actually invoked, keeping it below anchor 5.

4 / 5

Workflow Clarity

The stage sequence (import → tokens → plan → verify → review → handoff) is explicit and the verify stage is a concrete validation feedback loop ('repeat': true with 'until': '(build.passing && tests.passing) || iterations>=8'), including an iteration bound for error recovery — matching the anchor requiring explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

The body is under 50 lines, no bundle files exist or are needed, and content is organized into two clear sections ('## Default pipeline', '## Required user inputs') with nothing inlined that belongs in a separate file — the rubric's simple-skill exception explicitly permits a 5 here.

5 / 5

Total

18

/

20

Passed

Description

58%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 states a concrete, domain-specific 'what' via its named pipeline stages, but has no 'when to use' guidance and uses internal system jargon ('taskKind', 'devloop') instead of natural user trigger phrases. It is distinguishable but would rarely be surfaced by a user's natural request wording.

Suggestions

Append an explicit trigger clause, e.g. 'Use when migrating or porting a codebase to a new stack, framework, or language.'

Replace or gloss internal jargon ('taskKind', 'devloop') with natural synonyms users would say: 'migrate', 'port', 'rewrite', 'rebuild and test until green'.

Briefly state the outcome in plain language (e.g. 'imports the repo, maps old-stack tokens, rewrites, and loops patch/build/test until the build passes') so the value is legible without knowing the stage names.

DimensionReasoningScore

Specificity

Names the domain ('code-migration taskKind') and lists several concrete stage actions ('code-import', 'design-extract', 'token-map', 'rewrite-plan', 'patch-edit', 'build-test', 'diff-review', 'handoff') — matches 'lists several specific actions; minor gaps' rather than 5, since it never says what each stage actually does.

4 / 5

Completeness

The 'what' is clear (the default pipeline and its stages), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3; it is not 2 because the 'what' is concrete and specific.

3 / 5

Trigger Term Quality

'code-migration' plus 'build'/'test' are somewhat natural, but the description leans on internal jargon ('taskKind', 'devloop', 'token-map', 'diff-review') and omits the phrasings a user would naturally say ('port', 'migrate codebase', 'new framework/stack'), matching 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

'code-migration' plus a distinctive stage vocabulary gives a mostly distinct niche with only minor overlap risk against a generic code-migration or refactoring helper; it lacks the fully distinct natural trigger phrases of a 5.

4 / 5

Total

14

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

nexu-io/open-design

Path

plugins/_official/scenarios/od-code-migration/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.