Name: ingestion-pipeline-doctor-nodejs
Rating: 68 (1 reviews)
Author: PostHog

ingestion-pipeline-doctor-nodejs

Ingestion pipeline architecture overview and convention reference. Use when you need a quick orientation to the pipeline framework or want to know which doctor agent to use for a specific concern.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, high-signal reference: terse conventions, concrete file paths and API names, and clean one-level-deep pointers to detail files. Its only weakness is that, as a reference rather than a procedural workflow, it lacks explicit validation/feedback-loop checkpoints.

Suggestions

For the 'Running all doctors' usage, add a short validation checkpoint (e.g., 'After running, confirm each doctor reported no convention violations before considering the review complete') to give the one procedural flow a feedback loop.

Break the dense fan-out/fan-in paragraph into a short labeled structure (e.g., bullet sub-conditions) so the contract rules are scannable without re-reading the prose.

Dimension	Reasoning	Score
Conciseness	The body is dense but every token is domain-specific detail Claude would not already know (specific step names, invariants, contracts); it avoids explaining generic concepts and uses terse tables and bullets, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	It gives concrete, actionable guidance — real file paths, specific API names (ok(), dlq(), drop(), concurrentlyPerGroup, fanOut().via().fanIn()), and a concern-to-agent table — so an instruction/reference skill of this kind meets the 'fully executable ... specific examples' bar.	3 / 3
Workflow Clarity	This is a reference/orientation skill rather than a multi-step task workflow; the agent-selection table is structured and the closing 'run all pipeline doctors' action is unambiguous, but there are no explicit validation checkpoints or feedback loops, which caps it at the 'steps listed but validation gaps' level.	2 / 3
Progressive Disclosure	The overview is concise and points one level deep to well-signaled real files ('See ... for the real implementation', 'Details: .../14-batching.test.ts', 'Details: .../17-fan-out-fan-in.test.ts') and the agent directory, with detail appropriately deferred rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly communicates both purpose and trigger conditions and occupies a distinctive niche, but its action language is orientation-focused rather than listing concrete capabilities and its trigger terms lean on codebase jargon.

Suggestions

Replace the abstract 'architecture overview and convention reference' framing with concrete actions a user would recognize (e.g., 'Navigate PostHog's ingestion pipeline steps, pick the right doctor agent, and apply step/result/composition conventions').

Add common natural-language trigger variations users might actually say, such as 'ingestion steps', 'pipeline result handling', or 'which pipeline doctor to use'.

Dimension	Reasoning	Score
Specificity	Names the domain ('ingestion pipeline architecture overview and convention reference') and a couple of purposes ('quick orientation', 'know which doctor agent to use'), but these are orientation verbs rather than a list of multiple concrete transformative actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states both what the skill provides ('architecture overview and convention reference') and when to use it via an explicit 'Use when you need a quick orientation ... or want to know which doctor agent to use' trigger, satisfying the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	Terms like 'pipeline framework', 'doctor agent', and 'convention reference' are usable by the target audience but lean toward codebase jargon and miss common variations, so it sits at the 'some relevant keywords but missing common variations' level rather than full natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	The skill targets a narrow niche (PostHog ingestion pipeline doctor agents) with triggers tied to that specific framework, making it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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: PostHog/posthog
Path: .agents/skills/ingestion-pipeline-doctor-nodejs/SKILL.md
Commit: d1dd198

Reviewed: about 14 hours ago

Table of Contents

Discovery Implementation Validation

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.