CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

investigation-mode

Orchestrated debugging coordinator. Triggers on frustration signals (stuck, hung, broken, waiting) and systematically triages: runtime logs → workflow status → browser verify → deploy/env. Reports findings at every step.

67

Quality

84%

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.

A well-structured, highly actionable debugging skill with an exemplary triage workflow, explicit stop conditions, and executable commands and code. The main improvement levers are deduplicating the per-step reporting reminders and moving the logging recipes toward a reference.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — no explanation of what logs or DevTools are — and the code examples earn their tokens. Minor redundancy costs the top score: the "Tell the user: ... → share ... → explain next step" reminder is repeated at the end of all four triage sections after the Reporting Contract already established the pattern.

4 / 5

Actionability

Mostly executable: concrete commands (`vercel logs --follow`, `vercel workflow runs list`, `vercel workflow runs get <run-id>`, `vercel inspect <deployment-url>`, `vercel ls`) and two copy-paste-ready TypeScript logging examples. Not a 5 because the browser-verification section is directional ("Check the Network tab for failed requests") with no concrete command, and "agent-browser" is invoked without usage.

4 / 5

Workflow Clarity

Clear 1→4 triage sequence with explicit checkpoints (the three-part Reporting Contract applied at every step), an explicit Stop Condition section, and feedback loops: "If no logs exist: This is the problem. Add logging before continuing" and "Two consecutive triage steps produce no signal — ... ask the user for more context". This matches anchor 5; the stop rules give error-recovery guidance for the no-signal case.

5 / 5

Progressive Disclosure

Good structure with clear section headers, and the cross-reference to the observability and workflow skills is clearly signaled and one level deep. Not a 5 because the skill is fully monolithic (no bundle files exist), and the ~110-line body — particularly the Add Logging code block and Common Hang Causes list — is borderline content that could be split into a reference file for a leaner overview.

4 / 5

Total

17

/

20

Passed

Description

83%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: third-person voice, concrete what-and-when structure, and genuinely natural trigger vocabulary. Its main gaps are trigger synonyms that live only in metadata and a compressed action list.

DimensionReasoningScore

Specificity

The description lists several concrete triage actions — "systematically triages: runtime logs → workflow status → browser verify → deploy/env" — with only the abstract opener "Orchestrated debugging coordinator" being slightly vague. It matches anchor 4 (several specific actions, minor coverage gaps) rather than 5 because the actions are compressed into a single arrow chain and omit reporting/synthesis nuances.

4 / 5

Completeness

Explicitly answers both questions: what — "systematically triages: runtime logs → workflow status → browser verify → deploy/env" — and when — "Triggers from frustration signals (stuck, hung, broken, waiting)". This is equivalent to a 'Use when...' clause with concrete trigger phrases, matching anchor 5; it is not a 4 because the when-clause is explicit rather than implied.

5 / 5

Trigger Term Quality

Natural user phrasings like "stuck, hung, broken, waiting" are exactly what a frustrated user would say. Not a 5 because common variations users actually say — "frozen", "spinning", "timed out", "not loading", "white screen" — appear only in the frontmatter's promptSignals metadata, not in the description text itself.

4 / 5

Distinctiveness Conflict Risk

The debugging-triage coordinator niche with its log→workflow→browser→deploy pipeline is mostly distinct from sibling skills. Minor overlap risk remains with general debugging or observability skills because broad trigger words like "broken" and "waiting" fire on many situations.

4 / 5

Total

17

/

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

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

openai/plugins

Path

plugins/vercel/skills/investigation-mode/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.