CtrlK
BlogDocsLog inGet started
Tessl Logo

trellis-meta

Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents under .trellis/agents/, selectable workflow templates, registry-backed spec refresh, cross-session memory (trellis mem) generated by trellis init, or AI-facing bundled skills (trellis-channel, trellis-session-insight, trellis-spec-bootstrap) and bundled-skill auto-dispatch flow.

69

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

The canonical home for this skill is trellis-meta in mindfold-ai/Trellis

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-structured, actionable overview with strong progressive disclosure and concrete commands/paths, though it runs long due to inline platform enumeration and some repeated detail between the intro and 'Current Rules'.

Suggestions

Collapse the inline platform-directory list (e.g. '.claude/, .codex/, .cursor/, ...') into a pointer to references/platform-files/platform-map.md to reduce token cost while keeping platform-specific notes inline.

De-duplicate the bundled-skill name list and workflow-template enumeration, which appear in both the intro paragraph and the 'Current Rules' section — state each once and reference the other.

Add an explicit validate→fix→retry checkpoint in 'How To Use' for editing flows (e.g. after editing, re-read the file and confirm the change against the active workflow template / template-hashes) to lift workflow clarity.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept-explanation padding, but the long inline platform-directory enumeration (17+ platforms) and repeated bundled-skill lists in both the intro and 'Current Rules' add length beyond what Claude needs inline.

3 / 5

Actionability

Provides concrete commands ('trellis workflow --template <id>', 'task.py create --parent <slug>', 'trellis mem search|extract|context') and exact paths ('~/.trellis/channels/<project>/<channel>/events.jsonl', '.trellis/.template-hashes.json') plus a precise step-by-step routing sequence to named reference files.

5 / 5

Workflow Clarity

'How To Use' gives a clear 5-step conditional sequence with an authoritative-source checkpoint (step 5: 'treat local content as authoritative') and a cross-check guard in 'Do Not', but lacks an explicit validate→fix→retry feedback loop for editing operations.

4 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep references organized into three named subsections; all referenced files exist in ./references/ and the body appropriately stays an overview while detail lives in the bundle.

5 / 5

Total

17

/

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.

The description is specific, complete, and clearly distinct, with an explicit 'Use when' clause covering a comprehensive set of concrete customization surfaces. It is slightly heavy on internal terminology, which keeps trigger-term naturalness just short of perfect.

DimensionReasoningScore

Specificity

Enumerates many concrete customization surfaces — '.trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents... selectable workflow templates, registry-backed spec refresh, cross-session memory (trellis mem)... bundled-skill auto-dispatch flow' — giving comprehensive coverage of what the skill touches.

5 / 5

Completeness

Explicitly answers both 'what' ('Understand and customize the local Trellis architecture inside a user project') and 'when' ('Use when modifying .trellis plus...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong keyword coverage including tool-specific triggers users would say ('modifying .trellis', 'trellis channel', 'trellis mem', bundled skill names), but the trigger list leans on internal nouns and omits some natural phrasings/synonyms a user might say.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (local Trellis architecture) with highly specific, Trellis-only trigger nouns (.trellis, trellis channel, trellis mem, bundled skill names), minimizing overlap with other skills.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 27 deeper-than-1-level

Warning

Total

15

/

16

Passed

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.