CtrlK
BlogDocsLog inGet started
Tessl Logo

security-fix

Orchestrates test-driven fixes for Mattermost security tickets (Jira/Atlassian) with a Staff Security Engineer mindset: failing secure-behavior tests first, then implementation, then security review and edge-case loops, then opening a non-draft PR that follows `.github/PULL_REQUEST_TEMPLATE.md` when present, with a vague public description (no exploit detail). Use when the user invokes /security-fix:security-fix with a mattermost.atlassian.net browse URL, MM-* security work, backend permission or authorization bugs, or asks for this security TDD workflow.

75

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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-sequenced, actionable orchestration workflow with explicit validation checkpoints and a Phase 2/3 feedback loop. Its only weakness is redundancy between the phase descriptions and the closing anti-patterns section.

Suggestions

Trim the 'Anti-patterns (orchestrator)' list to only items not already stated in the phases/checklist (e.g., keep the TDD-discipline and 'small fixes still need Phase 3' points) and cross-reference the rest instead of restating.

The 'Orchestrator checklist' repeats the phase spawn order verbatim; consider compressing it to a short reference that points back to the phase sections rather than re-describing each.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence, but the 'Anti-patterns (orchestrator)' section restates four points already made earlier (no direct code edits, public PR vagueness, non-draft default, honoring the PR template), which could be tightened.

2 / 3

Actionability

Gives concrete, executable guidance throughout: a real invocation URL example, exact issue-key parsing, the named 'Atlassian MCP' source, per-phase deliverables, a precise success criterion ('fail for the right reason'), an exact repo path, and an avoid/prefer table. Instruction-only yet fully actionable.

3 / 3

Workflow Clarity

Phases 1–3 are explicitly sequenced with validation checkpoints (tests must fail for the right reason; must pass; if Phase 3 adds failing tests, return to Phase 2) and a feedback loop, plus a numbered orchestrator checklist.

3 / 3

Progressive Disclosure

A single, well-organized SKILL.md with clear section headings and no nested or multi-level references; no bundle files exist and none are needed for this orchestration/policy skill, so the content correctly stays inline at one level.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 concrete, third-person, and gives explicit 'what' and 'when' guidance with natural trigger terms and a distinct, narrowly scoped niche. It is a strong model description with no notable weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'failing secure-behavior tests first, then implementation, then security review and edge-case loops, then opening a non-draft PR' — each tied to a specific artifact (`.github/PULL_REQUEST_TEMPLATE.md`, vague public description).

3 / 3

Completeness

Explicitly answers what (orchestrated TDD fix workflow with named phases) and when (a 'Use when...' clause enumerating invocation URL, MM-* tickets, permission/authorization bugs, and the TDD workflow request).

3 / 3

Trigger Term Quality

Includes natural trigger phrasings a user would actually say: '/security-fix:security-fix', 'mattermost.atlassian.net browse URL', 'MM-* security work', 'backend permission or authorization bugs', 'security TDD workflow'.

3 / 3

Distinctiveness Conflict Risk

Niche is tightly scoped to Mattermost/Atlassian security tickets with a specific slash-command invocation and Jira context, making collision with generic skills very 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
mattermost/mattermost-ai-marketplace
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.