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.

70

Quality

85%

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%

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 concise, well-structured overview with clean progressive disclosure via a reference table and a validated workflow, but its actionability is limited by directional guidance rather than concrete, copy-paste spec examples or templates.

Suggestions

Add one short, concrete example of a populated spec snippet or a skeleton spec file so the 'writing spec files' step is executable rather than descriptive.

Provide a minimal concrete command or file-path pattern (e.g. a representative .trellis/spec/<package>.md structure) to anchor the decomposition step.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — each section (Workflow, Reference Routing, Operating Rules, Done Criteria) earns its place with no padding or explanation of basic concepts. Not a 2 because there is no unnecessary explanation to trim.

3 / 3

Actionability

Guidance is directional and concrete in intent ('Fill or reshape the spec files with concrete patterns, file paths, examples, and anti-patterns') but provides no executable, copy-paste specifics such as example spec snippets or concrete file skeletons. Not a 1 because it names concrete deliverables; not a 3 because the instructions describe more than they instantiate.

2 / 3

Workflow Clarity

The five-step workflow has a clear sequence and an explicit verification step ('Verify that the final specs are internally consistent and contain no template placeholders') reinforced by a Done Criteria checklist, providing a feedback loop for the file-writing work. Not a 2 because validation is explicit, not implicit.

3 / 3

Progressive Disclosure

A Reference Routing table clearly signals four one-level-deep references (repository-analysis.md, spec-task-planning.md, spec-writing.md, mcp-setup.md), all of which exist in ./references/, keeping the overview slim and navigation easy. Not a 2 because references are well-signaled and content is appropriately split rather than inlined.

3 / 3

Total

11

/

12

Passed

Description

85%

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 and complete with an explicit Use-when trigger and a clearly bounded niche, but its trigger terms rely on project-internal jargon and tool names rather than phrasing a user would naturally say, slightly weakening trigger-term quality.

Suggestions

Add natural-language trigger phrasing (e.g. 'Use when setting up coding guidelines, code-style rules, or per-package spec docs') alongside the tool names so users can invoke it without knowing GitNexus/ABCoder.

Consider including common synonyms like 'coding standards', 'style guide', or 'spec docs' that a user would actually say.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as 'Bootstrap project-specific Trellis coding specs', 'creating or refreshing .trellis/spec guidelines', and 'writing real codebase-backed spec docs without placeholder text', matching the anchor that names several specific concrete actions.

3 / 3

Completeness

It states what the skill does ('Bootstrap project-specific Trellis coding specs…') and gives an explicit 'Use when…' clause enumerating triggering scenarios, clearly answering both what and when. Not a 2 because the when is explicit rather than implied.

3 / 3

Trigger Term Quality

The explicit 'Use when' clause includes relevant triggers like 'creating or refreshing' and 'analyzing a codebase', but leans heavily on internal jargon (GitNexus, ABCoder, .trellis/spec) that users would not naturally say, so it has some relevant keywords but misses common variations. Not a 3 because natural-term coverage is thin and tool-specific; not a 1 because there are usable trigger phrases.

2 / 3

Distinctiveness Conflict Risk

The niche (Trellis .trellis/spec guidelines) is narrow with distinct triggers tied to a specific spec directory, making conflict with other skills unlikely. Not a 2 because the scope is clearly bounded rather than broadly overlapping.

3 / 3

Total

11

/

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
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.