CtrlK
BlogDocsLog inGet started
Tessl Logo

incident-management

Orchestrate the ConfigHub side of a live production incident — triage, decide stabilize-and-mitigate vs rollback vs drift reconciliation, route to the right mutation skill. Use for "we have an outage", "prod is crashing", "mitigate or roll back?", "post-incident cleanup". Not for planned releases (use promote-release).

76

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly written, highly actionable incident orchestrator with clear sequencing and validation for destructive paths. The main weakness is progressive disclosure: the body points to reference files that are not actually present in the bundle.

Suggestions

Add the missing referenced files (references/changesets.md, references/revisions.md, references/cub-cli.md) to the bundle, or remove the References entries and inline the small amount of needed detail (ChangeSet lifecycle, restore-target syntax, --change-desc discipline).

If the reference files are intentional, link them as markdown links (e.g. [changesets.md](references/changesets.md)) rather than bare backtick paths so the navigation is explicit and verifiable.

Consider moving the symptom→mitigation table and the close-out checklist into a reference file to shorten the SKILL.md body, keeping only the triage flow and path-selection logic inline.

DimensionReasoningScore

Conciseness

Dense and purposeful: assumes Claude already knows ConfigHub/kubectl/ArgoCD and devotes tokens to decision logic, executable commands, and hand-off templates rather than background concepts. Every section earns its place for an orchestrator of this complexity.

3 / 3

Actionability

Copy-paste-ready `cub` commands with `--where` filters and jq output formatting, a symptom→mitigation→skill table, literal fill-in `--change-desc` templates, and specific restore-target syntax — fully executable guidance rather than abstract direction.

3 / 3

Workflow Clarity

Sequenced triage (five ordered questions, "Stop at the first one that routes clearly") → path selection (A/B/C) → hand-off → numbered close-out and verify-chain, with explicit validation checkpoints (confirm hand-off success; verify-apply) and stop-conditions for the destructive rollback misuse case.

3 / 3

Progressive Disclosure

The body is well-sectioned and signals one-level-deep references in a References block, but the three cited files (references/changesets.md, references/revisions.md, references/cub-cli.md) do not exist in the bundle, so the signaled navigation is broken.

2 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities, supplies natural-language triggers, and disambiguates from sibling skills. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "triage, decide stabilize-and-mitigate vs rollback vs drift reconciliation, route to the right mutation skill" — matching the anchor for listing several specific actions.

3 / 3

Completeness

Explicitly answers both what (orchestrate/triage/decide/route the ConfigHub side of an incident) and when (a "Use for ..." clause with concrete triggers, plus a "Not for planned releases" negative trigger).

3 / 3

Trigger Term Quality

Quoted natural phrases users would actually say — "we have an outage", "prod is crashing", "mitigate or roll back?", "post-incident cleanup" — giving good coverage of real trigger terms.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche — the ConfigHub side of a live incident — and explicitly disambiguates from the adjacent promote-release skill, making a wrong-skill trigger unlikely.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

13

/

16

Passed

Repository
confighub/confighub-skills
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.