CtrlK
BlogDocsLog inGet started
Tessl Logo

compose-next

Use for multi-step feature work, bug fixes, or refactors where requirements need to settle, a feature document should carry design + tasks + delivery evidence, and the change deserves independent review before merge. Invoked explicitly from Build as `/compose-next` when a Fable/Sol-class model is available. Not for one-shot edits, single-file tweaks, or answering questions — those need no orchestration overhead.

77

Quality

96%

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

92%

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, highly actionable orchestration playbook with strong validation checkpoints and feedback loops across all phases. Its one weakness is progressive disclosure: it is a large single-document monolith where the spec template and worktree/review protocols could be offloaded to reference files.

Suggestions

Extract the full Spec document template (the fenced markdown block with frontmatter and [Sn] anchors) into a referenced file like references/spec-template.md, keeping only the field summary inline in SKILL.md.

Move the detailed Workspace worktree procedure and the Finish 'worktree pitfalls' appendix into references/worktree.md, leaving a concise default-and-edge-case pointer in the body.

Consider references/review-protocol.md for the Review section's reviewer handoff checklist and the three required review conclusions, to shrink the body toward an overview.

DimensionReasoningScore

Conciseness

Lean and directive throughout, with no explanation of concepts Claude already knows (e.g., what a worktree or a failing test is); length reflects a genuinely multi-phase process rather than padding, and every section assumes competence.

3 / 3

Actionability

Concrete executable commands throughout ('git rev-parse --git-dir', 'git check-ignore -q', 'git worktree add "$path" -b "$branch"', 'bun ci', 'uv sync --frozen') plus a copy-paste-ready spec document template with frontmatter anchors.

3 / 3

Workflow Clarity

A clearly sequenced phase pipeline (Orient → Grill → Spec → Workspace → Implement → Verify → Review → Finalize → Finish) with explicit validation checkpoints and feedback loops — 'write a failing test, confirm it fails for the intended reason... confirm it passes', 'After two failed fixes, stop patching', and consent gates for destructive actions.

3 / 3

Progressive Disclosure

Well-organized into clear headers with no nested references, but everything lives in one inline document — the full spec template, the worktree procedure, and the review protocol are content that could be split into one-level-deep reference files; no bundle files are provided.

2 / 3

Total

11

/

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 specific, complete, and distinct, with explicit trigger guidance and exclusion boundaries. It uses the standard imperative skill-description voice rather than first/second person, incurring no specificity penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'multi-step feature work, bug fixes, or refactors', a feature document that 'should carry design + tasks + delivery evidence', 'independent review before merge', and explicit invocation as '/compose-next' from Build.

3 / 3

Completeness

Explicitly answers both what (design+tasks+delivery-evidence document with independent review) and when via the 'Use for multi-step feature work...' trigger clause, plus explicit 'Not for one-shot edits...' exclusions.

3 / 3

Trigger Term Quality

Natural user-facing terms ('feature work, bug fixes, refactors') are well covered, matching how a user would phrase the need; the appended process jargon ('requirements need to settle', 'Fable/Sol-class model') is supplemental rather than replacing common terms.

3 / 3

Distinctiveness Conflict Risk

A clear niche — orchestrated multi-step feature work with a durable document and independent review — scoping via the '/compose-next' invocation and explicit exclusions makes conflict with other skills unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
XiaomiMiMo/MiMo-Code
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.