CtrlK
BlogDocsLog inGet started
Tessl Logo

signals-scout-mcp-tool-calls

Signals scout for PostHog MCP tool calls. Watches `$mcp_tool_call` telemetry for tools that need improvement — broad-reach failure rates, retry hammering, slow or context-bloating responses — grouped by owning product category, each with a fix suggestion.

57

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-mcp-tool-calls/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 dense, highly actionable, well-structured scout body that offloads the SQL cookbook to a reference and sequences the workflow with validation checkpoints. It is somewhat verbose with repeated emphasis, and the referenced queries.md bundle is not present to verify.

Suggestions

Consolidate the "edit an existing report rather than authoring a new one" guidance, which is restated in several sections, to reduce length.

Tighten dense prose blocks (e.g. the signal-vs-noise discriminator and Decide rails) into scannable lists where possible without losing the nuance.

DimensionReasoningScore

Conciseness

Mostly efficient and information-dense with genuinely novel domain knowledge, but the ~198-line body repeats several points (e.g. the "edit not new report" rule) and could be tightened in places.

3 / 5

Actionability

Concrete HogQL access patterns, exact field names, specific tool names, and exact memory-key formats give mostly executable guidance; the full SQL lives in the offloaded cookbook, leaving minor gaps.

4 / 5

Workflow Clarity

A clearly sequenced workflow (close-out → orient → probe → grain → lenses → memory → decide → fix loop → close out) with decision rails and validation checkpoints (probe first, search inbox, disqualifiers); minor checkpoint gaps keep it below 5.

4 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled one-level-deep reference to references/queries.md and baked-in deep-dive skills; good structure with minor organization gaps, and the referenced bundle file is not present in the review directory to fully verify.

4 / 5

Total

15

/

20

Passed

Description

70%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 specific, third-person, well-scoped description that clearly conveys what the scout does, but it lacks an explicit "Use when..." trigger clause, capping completeness. Adding when-to-invoke guidance would raise the score.

Suggestions

Add an explicit trigger clause, e.g. "Use when monitoring PostHog MCP tool quality, investigating MCP tool failure/latency/struggle signals, or when asked about $mcp_tool_call telemetry."

Include a couple of natural synonym phrasings (e.g. "MCP tool quality", "tool-call health") to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain (PostHog MCP tool calls) and lists several concrete detection actions — "broad-reach failure rates, retry hammering, slow or context-bloating responses" grouped by category with a fix suggestion; short of a fully exhaustive action list.

4 / 5

Completeness

Clearly states what the scout does, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Good keyword coverage with natural terms an agent would say ("MCP tool calls", "PostHog", "telemetry", "failure rates", "retry hammering"); a few common synonyms or phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

A sharply scoped niche — PostHog $mcp_tool_call telemetry quality scout — with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

20

Passed

Validation

75%

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

Validation — 12 / 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

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

12

/

16

Passed

Repository
PostHog/posthog
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.