Tessl • The package manager for agent skills

SkillPublic

adding-personhog-rpc

Guide for adding a new RPC to personhog-replica and personhog-router. Covers eligibility checks, proto definition, code generation for Python and Node.js clients, Rust implementation (storage trait, postgres queries, service handler, router wiring), and index compatibility validation. Use when adding a new gRPC endpoint to personhog, migrating a Django ORM query to personhog, or extending the personhog service API.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

96%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 end-to-end workflow: concrete commands, exact paths, compiler- and test-driven feedback loops, and a checklist, with essentially no wasted tokens. The only defect is that both files referenced from the body are absent from the skill bundle, leaving its progressive-disclosure structure unverifiable and its links broken.

Suggestions

Ship references/database-indexes.md and references/proto-conventions.md in the skill bundle — both are cited as required reading (index validation in Step 0, proto conventions in Step 1) but are missing, so the links are dead ends.

The leader-idempotency section defers the operation-identity contract to "personhog-leader's README" with no path or link; add a reachable reference (or inline the one-line summary) so the detail is discoverable from the skill.

Dimension	Reasoning	Score
Conciseness	Every section earns its tokens with project-specific facts Claude cannot know: the routing table, exact file paths ("rust/personhog-replica/src/storage/traits/<domain>.rs"), metric names ("DB_QUERY_DURATION and DB_ROWS_RETURNED"), and the at-least-once delivery contract. No filler or explanation of known concepts.	5 / 5
Actionability	Commands are copy-paste ready ("bin/generate_personhog_proto.sh", "cd nodejs && pnpm run generate:personhog-proto", the per-crate cargo build/test list) and every step names the exact files to edit, down to "keeping the list sorted" in KNOWN_METHODS and the SERVICE_DEFAULTS entry in client.test.ts.	5 / 5
Workflow Clarity	A clear Step 0–4 sequence with an explicit verification step, built-in feedback loops ("cargo build errors tell you exactly which trait methods are missing"; "known_methods_is_sorted ... fail until the list matches service.proto"), an upfront stop condition for ineligible tables, and a closing checklist — the anchor-5 pattern.	5 / 5
Progressive Disclosure	The body is a well-signaled overview with one-level-deep, purpose-stated references ("see [references/database-indexes.md]... to validate it against the available indexes", proto-conventions "for message conventions and a worked example"), but neither referenced file exists in the bundle — the links are dead ends. Not 5 because navigation breaks on the missing files; not 3 because the structure and signaling are otherwise good.	4 / 5
	Total	19 / 20 Passed

Description

100%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.

An exemplary description: it states what the skill covers at each pipeline stage in third person, gives three concrete natural-language triggers, and occupies a distinct niche with no conflict risk. Both the what and when are explicit and specific.

Dimension	Reasoning	Score
Specificity	Enumerates the full pipeline concretely: "Covers eligibility checks, proto definition, code generation for Python and Node.js clients, Rust implementation (storage trait, postgres queries, service handler, router wiring), and index compatibility validation" — every major stage is named with its sub-steps, matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.	5 / 5
Completeness	Both questions are explicitly answered: the what ("Guide for adding a new RPC to personhog-replica and personhog-router... Covers...") and an explicit "Use when..." clause with three concrete triggers, which is the anchor-5 pattern.	5 / 5
Trigger Term Quality	"Use when adding a new gRPC endpoint to personhog, migrating a Django ORM query to personhog, or extending the personhog service API" gives three natural trigger phrasings, and the description covers synonyms (RPC, gRPC endpoint, proto, service API) a user would actually say. Not 4: no common variation of the request is missing for this domain.	5 / 5
Distinctiveness Conflict Risk	The description is anchored to a clear niche (personhog-replica, personhog-router, Django ORM migration) with distinct trigger terms, so it would not plausibly fire for an unrelated skill.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: PostHog/posthog
Path: .agents/skills/adding-personhog-rpc/SKILL.md
Revision: 9afec35

Reviewed: 11 days ago

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.

adding-personhog-rpc

Table of Contents

Is this your skill?