CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

73

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

88%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 tightly structured, highly actionable debugging skill with a clear triage workflow and real feedback checkpoints. It is mostly token-efficient; the main lever is collapsing the repeated reporting-contract template and extracting the larger code/list blocks into reference files.

Suggestions

Collapse the four repeated "Tell the user: ... → share ... → explain next step" lines into a single stated contract referenced once, instead of restating it per triage step.

Move the Common Hang Causes list and the Add Logging code examples into a separate reference file (e.g. references/debugging-patterns.md) and link to it from the body to improve progressive disclosure.

Trim editorializing sentences like "The user is already frustrated — silence makes it worse" and "you cannot debug what you cannot see" that restate what the workflow already implies.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence without explaining basics, but the repeated "Tell the user: ... → share ... → explain next step" template across four sections and editorializing lines ("The user is already frustrated — silence makes it worse") could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready commands (vercel logs --follow, vercel workflow runs list, vercel inspect <deployment-url>, vercel ls) and complete TypeScript logging examples covering the common cases.

5 / 5

Workflow Clarity

Clear sequenced triage (runtime logs → workflow → browser → deploy/env) with an explicit stop condition and a genuine feedback loop (two empty steps triggers escalation to the user), plus an Add-Logging recovery path.

5 / 5

Progressive Disclosure

Well-organized into labeled sections with clearly signaled one-level cross-references to the observability and workflow skills; minor gaps where the Common Hang Causes list and Add Logging code could be split out, but no nested references.

4 / 5

Total

18

/

20

Passed

Description

95%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, well-targeted description that clearly states both purpose and trigger conditions using natural user language. Minor room to broaden the explicit capability list, but it capably distinguishes itself and fires on realistic signals.

DimensionReasoningScore

Specificity

Names the debugging-coordinator domain and several concrete triage actions ("runtime logs → workflow status → browser verify → deploy/env", "Reports findings at every step"), but stops short of comprehensively enumerating what the skill does beyond triage order.

4 / 5

Completeness

Explicitly answers both what ("Orchestrated debugging coordinator... systematically triages") and when ("Triggers on frustration signals (stuck, hung, broken, waiting)") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Triggers on frustration signals (stuck, hung, broken, waiting)" are exactly the natural phrases a frustrated user says, giving comprehensive natural-term coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (orchestrated debugging triage) with distinctive frustration-signal triggers, making overlap with other skills minimal.

5 / 5

Total

19

/

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.

Validation14 / 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
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.