CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

incident

Triage recurring PsychSift canary, CI, runtime, scheduled-task, and provider failures into reproducible causes, impact, containment, and next actions. Use for regressions, outages, flaky jobs, alerts, or repeated nightly or weekly failures.

Quality

88%

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

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 exceptionally token-efficient with a clear sequenced workflow and appropriate validation gates, but as an instruction-only skill its guidance stops short of executable specificity — no commands, file locations, or worked examples for the triage steps it directs.

Suggestions

Add concrete starting points for step 1, e.g., the specific log directories, artifact paths, or a command that surfaces recent canary/CI/scheduled-task runs.

Include a brief worked example of one triaged failure (timeline -> classification -> smallest reproduction -> containment) to make the workflow executable rather than directional.

Spell out the fix-and-retry loop in step 4 (what to do when verification of the failure path fails or the reproduction doesn't reproduce).

DimensionReasoningScore

Conciseness

Six lean numbered steps with zero padding or explanation of concepts Claude already knows; every token earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

The classification taxonomy ('deterministic code, fixture/data drift, schedule, concurrency, environment, quota, provider, or observability') and the gated-systems list are concrete, but there are no commands, paths, or examples for how to build the timeline or locate logs/artifacts/workflow definitions — key execution details are missing.

3 / 5

Workflow Clarity

A clear 1-6 sequence with real checkpoints (reproduce offline before editing, verify the exact failure path) but no explicit fix-and-retry feedback loop, fitting the 'most checkpoints present, minor validation gaps' anchor.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and needs no external references; the short well-ordered numbered list under a single heading qualifies for the simple-skill exception.

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.

A strong description: it names concrete triage outputs, scopes to a specific system's failure domains, and provides an explicit 'Use when' clause with natural trigger terms. Only minor keyword variations are missing.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ('Triage... failures into reproducible causes, impact, containment, and next actions') scoped to specific failure domains (canary, CI, runtime, scheduled-task, provider), matching the comprehensive-coverage anchor.

5 / 5

Completeness

It explicitly answers both 'what' (triage failures into causes, impact, containment, next actions) and 'when' ('Use for regressions, outages, flaky jobs, alerts...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

'regressions, outages, flaky jobs, alerts, or repeated nightly or weekly failures' are natural phrases users would say, but a few common variations (e.g., 'incident', 'broken build', 'test failures') are missing, fitting the good-but-not-comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The PsychSift-specific scope and distinct failure-mode triggers (canary, nightly/weekly job failures) establish a clear niche with minimal conflict risk against generic debugging or CI skills.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

BigSimmo/PsychSift

Path

.agents/skills/incident/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.