CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

defense-ux-context

Shared operating context for the 8-phase UX spec pipeline — the defense-UX persona, compliance scope, complexity tiers, interaction modes, gate enforcement, output rules, and prompt-injection policy. The orchestrator and every phase agent read this FIRST and treat it as TRUSTED. Replaces what used to live in a project CLAUDE.md.

60

Quality

75%

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/ux-spec-process/skills/defense-ux-context/SKILL.md
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.

A well-built operating-context skill: lean, policy-dense guidance with concrete numbers, labels, and file paths, explicit gates and confirmation checkpoints, and exemplary progressive disclosure that offloads the compliance catalog and registry to an on-demand reference. Minor persona flavor and a few abstract mandates are the only trim opportunities.

DimensionReasoningScore

Conciseness

Nearly all content is project-specific policy Claude cannot know (tier ceilings, gate rules, output destinations, trust boundaries), with no explanations of concepts Claude already knows. Minor persona color could be trimmed ('cynical of over-designed interfaces that fail in low-bandwidth or high-glare field conditions', 'bridging Silicon Valley usability and Warfighter requirements'), keeping it just below level 5's every-token-earns-its-place.

4 / 5

Actionability

Concrete, executable directives throughout: 'Tiered ceilings per round: Tier 1 ≤ 10, Tier 2 ≤ 6, Tier 3 ≤ 4; up to 3 rounds per phase', 'Always create as a draft page — never publish directly', 'Label AI-generated content [AI DRAFT]', 'Tag all externally sourced data as [EXTERNAL — UNVERIFIED]'. A few abstract mandates ('Optimize for faster, more accurate decision-making under pressure') leave minor gaps versus level 5.

4 / 5

Workflow Clarity

Sequence and checkpoints are explicit: confirm tier and interaction mode 'before starting', intake clarification as 'Step 0 before producing any artifact', hard stops at every gate, pause on questions, and double confirmation before any Confluence write or publish. Not level 5 because the 8-phase sequence itself deliberately lives in other files; not level 3 because validation checkpoints are explicit, not implicit.

4 / 5

Progressive Disclosure

Model structure: heavy lookup tables are split out to references/compliance-and-tooling.md (verified present, containing the compliance catalog and agent/skill/template registry), signaled clearly and twice — 'read that on demand, not every turn' — one level deep, with the body itself cleanly sectioned. Matches the level-5 anchor.

5 / 5

Total

17

/

20

Passed

Description

62%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 and highly distinctive, clearly scoping a niche operating-context skill within an 8-phase defense UX pipeline. Its main weakness is the absence of an explicit 'Use when...' trigger clause and natural user-facing trigger phrases, which caps completeness and trigger-term quality at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when running any phase of the UX spec pipeline or when the orchestrator needs the persona, compliance scope, or gate rules that govern spec work.'

Include natural trigger phrases users would actually say ('write a UX spec', 'defense UX spec', 'spec a feature for a defense system') to broaden keyword coverage.

Frame the enumerated contents as governing actions (e.g. 'Defines the defense-UX persona, compliance scope, complexity tiers, ...') to strengthen the what-it-does reading.

DimensionReasoningScore

Specificity

Lists several specific concrete components — 'the defense-UX persona, compliance scope, complexity tiers, interaction modes, gate enforcement, output rules, and prompt-injection policy' — going well beyond the level-3 anchor's 1-2 items. Falls short of level 5 because these are content areas the file contains rather than actions it performs, leaving a minor coverage gap.

4 / 5

Completeness

Has a clear 'what' — a shared operating context enumerating persona, compliance scope, tiers, modes, gates, and output rules — but no explicit 'Use when...' clause; 'The orchestrator and every phase agent read this FIRST' only weakly implies when. Per the judging guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Contains several relevant domain keywords ('8-phase UX spec pipeline', 'defense-UX persona', 'compliance', 'gate enforcement', 'prompt-injection policy') but is missing the natural phrases a user would say when needing this skill ('write a UX spec', 'defense UX', 'spec a feature'). Better than level 2 (keywords are domain-specific, not generic) but short of level 4's good natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — 'the 8-phase UX spec pipeline', 'defense-UX persona', 'Replaces what used to live in a project CLAUDE.md' — with distinct triggers and minimal risk of firing for the wrong skill. It explicitly positions itself as the frame rather than the mechanics, so adjacent skills (clarification-protocol, artifact-frontmatter, dedup) do not collide with it.

5 / 5

Total

15

/

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

mattermost/mattermost-ai-marketplace

Path

plugins/ux-spec-process/skills/defense-ux-context/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.