CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

debug-scc

Diagnose OpenShift Security Context Constraint (SCC) violations that prevent pods from being created. Automates multi-step diagnosis: Deployment status, ReplicaSet FailedCreate events, security context field extraction, SCC rejection parsing, and ServiceAccount SCC binding analysis. Use when: - "SCC violation blocking pod creation" - "unable to validate against any security context constraint" - "FailedCreate forbidden" - "pod blocked by SCC" - User mentions "SCC", "security context constraint", "FailedCreate" NOT for pods crashing after creation (use /debug-pod instead).

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

81%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 delivers a highly actionable, well-sequenced diagnostic workflow with strong validation checkpoints and human-in-the-loop safeguards, and properly pushes setup/debugging detail to reference files. Its main weakness is token efficiency: a fully duplicated prerequisites/dependencies section and heavy inline presentation templates inflate the ~440-line body.

Suggestions

Remove the duplicate 'Dependencies' section (or the 'Prerequisites' section) — both list the identical openshift MCP server and the same four MCP tools verbatim.

Move the six per-step presentation markdown templates into a single references file (e.g., references/report-templates.md) and keep only a one-line summary of the UX contract in each step, cutting the body by roughly a third.

Either reference references/selinux-troubleshooting.md from the body (e.g., in Related Skills or error handling for SELinux-denial rejections) or drop it from the bundle, so every bundled file is discoverable.

DimensionReasoningScore

Conciseness

The body is operational rather than tutorial (no padding explaining SCC concepts), but at ~440 lines it duplicates the Prerequisites content verbatim in a later "Dependencies" section (same MCP server and 4 tools listed twice) and inlines six bulky placeholder presentation templates. This fits anchor 3 ("mostly efficient but could be tightened") better than 4, since the duplicated section is more than a minor instance of over-explanation.

3 / 5

Actionability

Every step specifies the exact MCP tool, parameters, expected output, and error handling, and the remediation options provide copy-paste-ready commands (`oc patch ... --type json`, `oc adm policy add-scc-to-user anyuid -z <sa-name>`, `oc rollout undo`). This fully matches the 5 anchor: executable guidance with examples covering the common cases.

5 / 5

Workflow Clarity

Six clearly sequenced steps with a flow diagram, explicit WAIT checkpoints after every step, input validation (RFC 1123 naming rules), prerequisite verification, and feedback loops for error recovery (events expired → check ReplicaSet conditions; SCC listing forbidden → infer from rejection messages). The destructive-operation cap does not apply because human-in-the-loop confirmation is explicitly required before every remediation, matching the 5 anchor's validation-and-recovery profile.

5 / 5

Progressive Disclosure

Good structure with clear section headers and clearly signaled one-level-deep references ([setup](references/prerequisites.md), [references/debugging-patterns.md] with descriptive labels), both of which exist in the bundle. It falls short of 5 because references/selinux-troubleshooting.md is bundled but never referenced from the body, and the same two references are linked from two separate sections (Prerequisites and Dependencies), a minor organization gap matching anchor 4.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: third-person voice, concrete enumerated capabilities, exact trigger phrases including the canonical OpenShift error string, and an explicit out-of-scope boundary. It closely matches the rubric's good overall examples in structure and specificity.

DimensionReasoningScore

Specificity

The description enumerates five concrete actions — "Deployment status, ReplicaSet FailedCreate events, security context field extraction, SCC rejection parsing, and ServiceAccount SCC binding analysis" — comprehensively covering the diagnosis workflow, matching the 5 anchor rather than 4 because coverage of the task domain is complete, not partial.

5 / 5

Completeness

It explicitly answers both "what" ("Diagnose OpenShift Security Context Constraint (SCC) violations that prevent pods from being created" plus the enumerated steps) and "when" (a literal "Use when:" list of concrete trigger phrases), exactly matching the 5 anchor.

5 / 5

Trigger Term Quality

It includes the exact canonical error string users paste ("unable to validate against any security context constraint"), natural phrasings ("SCC violation blocking pod creation", "pod blocked by SCC"), and both acronym and full form ("SCC", "security context constraint", "FailedCreate"). No common variation is missing, so it exceeds the 4 anchor's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (SCC admission rejections at pod creation) with distinct error-string triggers, and adds an explicit negative boundary ("NOT for pods crashing after creation (use /debug-pod instead)") that minimizes overlap with adjacent debugging skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

RHEcosystemAppEng/agentic-plugins

Path

rh-developer/skills/debug-scc/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.