CtrlK
BlogDocsLog inGet started
Tessl Logo

trellis-spec-bootstrap

Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder text.

72

Quality

91%

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

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.

A well-structured, efficient skill body: clear sequenced workflow with explicit verification and done criteria, and exemplary progressive disclosure through a routing table to real one-level-deep reference files. Weakest points are minor — a redundant intro sentence and method-level specifics deferred entirely to references.

Suggestions

Trim or merge the introductory sentence that restates the workflow ('analyze the repository, choose the spec boundaries, write the docs, and verify the result') since the Workflow section immediately below lists the same steps.

Inline one concrete verification command (e.g., the placeholder grep `grep -R "To be filled\|TODO: fill\|placeholder" .trellis/spec` from spec-writing.md) into step 5 or Done Criteria so the final check is immediately executable from the body.

Add a brief explicit recovery loop after step 5 (e.g., 'if placeholders or inconsistencies remain, fix the offending spec files and re-verify') to close the last workflow gap.

DimensionReasoningScore

Conciseness

A lean 41-line body with terse, non-padded sections ('Treat templates as starting points, not contracts'), but the intro paragraph ('analyze the repository, choose the spec boundaries, write the docs, and verify the result') restates the Workflow section below it. Not 5: that duplication is a token cost; not 3: everything else earns its place.

4 / 5

Actionability

Concrete guidance for an instruction-only skill: named tools ('GitNexus, ABCoder, language tooling'), the exact tree ('.trellis/spec/'), a routing table, and a grep-style done state — though the executable specifics (e.g., the placeholder grep in spec-writing.md) live in references rather than the body. Not 5: steps like 'Analyze the repository architecture with the best available tools' leave method choice implicit. Not 3: the guidance is specific and executable via its references, not pseudocode-level.

4 / 5

Workflow Clarity

Clear 5-step sequence with an explicit validation step ('Verify that the final specs are internally consistent and contain no template placeholders') and a Done Criteria checklist; the reference files add a final-pass verification loop. Not 4: all checkpoints are present, not just 'most' — validation, consistency check, and completion criteria are all explicit.

5 / 5

Progressive Disclosure

Body is a concise overview with a clear routing table; all 4 referenced files exist, are one level deep (no nested references), and are appropriately sized (59–90 lines) with no content inlined that belongs in references. Matches the well-signaled one-level-deep anchor exactly.

5 / 5

Total

18

/

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.

A strong description: concrete multi-action capability statement in third person, with an explicit 'Use when' clause and distinctive, niche-specific trigger terms. Only minor room to grow on natural synonym coverage.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'Bootstrap project-specific Trellis coding specs', 'creating or refreshing .trellis/spec guidelines', 'analyzing a codebase with GitNexus, ABCoder, or source inspection', 'decomposing package/layer spec work', 'writing real codebase-backed spec docs without placeholder text' — with comprehensive coverage and third-person voice. Not 4: there are no gaps in action coverage.

5 / 5

Completeness

Explicitly answers both: what ('Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow') and when ('Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase...'). Matches the 5 anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'Trellis', '.trellis/spec', 'spec guidelines', 'GitNexus', 'ABCoder', 'package/layer spec work'. Not 5: common synonyms users might say — 'coding conventions', 'style guide', 'coding standards' — are absent. Not 3: the included terms are exactly what a Trellis user would say, not just jargon.

4 / 5

Distinctiveness Conflict Risk

Clear niche anchored by unique tokens (.trellis, GitNexus, ABCoder) that no other plausible skill shares; minimal conflict risk. Not 4: it is not merely 'mostly distinct' — the triggers are unambiguous.

5 / 5

Total

19

/

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
mindfold-ai/Trellis
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.