CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

posthog-digest

Reads recent project insights and events from the posthog MCP server (read-only) and writes what it found into a Markdown digest in this repo, then opens a pull request with that change. Runs unattended: it asks no questions and makes no writes to posthog.

Quality

82%

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

86%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.

An exemplary single-file automation skill: copy-paste executable commands, explicit defaults and failure paths, and tight structure. The only gaps are minor — a small duplication of the read-only constraint and no verification step between writing the digest and opening the PR.

Suggestions

Add a verification checkpoint after the write/push, e.g. confirm the digest rendered N items (or is non-empty) before opening the PR, and check that git push succeeded before running gh pr create.

Trim the duplicated read-only/unattended constraint — state it once (e.g. keep the Notes invariant) rather than in both the intro and Notes.

DimensionReasoningScore

Conciseness

The body is very lean — "Read posthog, write a doc, open a PR. Nothing else." — with no explanation of concepts Claude already knows and only non-obvious operational detail. Minor trims exist: the read-only/unattended constraint is stated both at the top ("Never prompt for confirmation and never write to posthog") and again in Notes ("Read-only. The only write is the digest file in the PR"), fitting anchor 4 rather than 5.

4 / 5

Actionability

Fully executable: an exact bash block for branch/commit/push/gh pr create, explicit input defaults ({{DIGEST_FILE}} -> docs/posthog-digest.md, {{LIMIT}} -> 20), a precise digest format spec, and concrete error paths. Matches anchor 5 (copy-paste ready commands covering the common cases).

5 / 5

Workflow Clarity

A clear 1-2-3 sequence with explicit precondition checkpoints (list MCP tools first, check credentials, "stop and report which one", "An empty result is a valid outcome"). It lacks verification after the digest write and after git push/PR creation, matching anchor 4 ("most checkpoints present; minor validation gaps") rather than 5. The destructive/batch cap does not apply since the operation is read-only toward posthog and the single file write is an explicitly idempotent generated artifact.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed — the ~74-line body is operational detail that splitting would hurt. Sections (Inputs, Procedure, Notes) are well organized and easy to navigate, which per the simple-skill guidance merits a 5; there are no inlined blocks that belong in separate files.

5 / 5

Total

18

/

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 strong, concrete, third-person description of a narrow automation niche with excellent distinctiveness. Its main weakness is the complete absence of any "when to use this" trigger clause, which both caps completeness and limits discoverability.

Suggestions

Add an explicit trigger clause such as "Use when the user wants a summary or digest of posthog insights/events, or asks to refresh the posthog digest document" to satisfy the 'when' half of completeness.

Include a few natural synonyms users might say (e.g. "product analytics", "posthog dashboard/insights summary") to broaden trigger term coverage.

DimensionReasoningScore

Specificity

Uses third person and lists several concrete actions — "Reads recent project insights and events", "writes what it found into a Markdown digest", "opens a pull request" — with minor gaps (no mention of saved queries or where the digest lives). Anchor 5 requires comprehensive coverage; anchor 3 covers only 1-2 actions.

4 / 5

Completeness

The "what" is clearly and concretely stated, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3. Anchor 4 requires both what and when to be present.

3 / 5

Trigger Term Quality

Good natural keyword coverage anchored by "posthog", "insights", "events", "MCP server", "Markdown digest", and "pull request", but misses common variations users might say such as "product analytics", "dashboards", or "trends". Anchor 5 requires synonyms/extensions.

4 / 5

Distinctiveness Conflict Risk

A clear niche with distinct triggers — posthog MCP server, Markdown digest, unattended PR creation — that would not plausibly fire for any other skill. Matches anchor 5 ("clear niche with distinct triggers; minimal conflict risk").

5 / 5

Total

16

/

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

drew-tessl/repo-schedules-test

Path

plugins/mcp-digests/skills/posthog-digest/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.