chatto-architecture-inventory

Maintain Chatto's current runtime architecture inventory in docs/architecture/. Use when adding, changing, removing, auditing, or documenting runtime components, projections or snapshots, NATS and JetStream resources, subject namespaces and event types, runtime-state keys, durable effects, ConnectRPC or Operator API mounts, or realtime delivery architecture. By default, inspect the codebase, apply all in-scope inventory fixes, and validate them; report without editing only when the user or parent workflow explicitly requests an audit, review, report, or propose-only result.

Quality

96%

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

92%

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

A lean, file-anchored instruction-only skill with concrete actionable guidance, clear sequenced workflows, and explicit validation checkpoints. Its main weakness is progressive disclosure: all detail lives inline in one file with no separate reference materials to offload the per-category guidance.

Suggestions

Move the per-category inspection guidance (the eight "Category routing" subsections) into one-level-deep reference files (e.g., docs/architecture inventory reference per category) and keep SKILL.md as a routing overview that links to them, satisfying the "appropriately split" anchor.

Extract the Validation checklist into a short referenced file or a clearly delimited appendix so the main body stays a lean overview while the full checks remain discoverable.

Confirm referenced bundle paths resolve to real files; currently no references/ or scripts/ bundle exists, so any "See X" pointers should either be added as bundle files or rephrased as in-repository targets rather than skill-bundle references.

Dimension	Reasoning	Score
Conciseness	Assumes Claude's competence throughout (never explains what NATS, JetStream, projections, or ConnectRPC are) and stays file-path-anchored and directive; a few reinforcing policy sentences exist but the body is lean relative to its scope. Not score 2 because there is no concept padding and most tokens earn their place.	3 / 3
Actionability	Provides concrete, specific guidance for an instruction-only skill: exact source files (cli/internal/core/core.go, cli/internal/evtstream/subjects.go), methods to find (CreateOrUpdateStream, API.Handlers()), and validation commands (mise license-check). Not score 2 because guidance is specific and actionable rather than pseudocode or abstract direction.	3 / 3
Workflow Clarity	Clear sequenced workflows ("Start here" 5 steps; Action mode 4 steps) plus a dedicated Validation checklist with explicit feedback loops ("fix inventory drift immediately; report a suspected source-registration defect separately"). Not score 2 because validation checkpoints are explicit rather than missing or implicit.	3 / 3
Progressive Disclosure	Well-organized with clearly signaled per-category "File:" references and easy navigation, but all detailed per-category inspection guidance and the validation checklist are inline in a single ~195-line SKILL.md with no separate reference/bundle files. Not score 3 because content is not appropriately split across files (the under-50-line simple-skill exemption does not apply); not score 1 because references are clearly signaled and not deeply nested.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 highly specific, third-person description that explicitly states both what the skill does and when to use it, with rich natural trigger terms and a distinct niche that minimizes conflict risk. It is concise yet comprehensive and avoids vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Maintain", "adding, changing, removing, auditing, or documenting", "inspect the codebase, apply all in-scope inventory fixes, and validate them") in third-person voice, matching the anchor that lists several specific concrete actions rather than vague language.	3 / 3
Completeness	Explicitly answers both what ("Maintain Chatto's current runtime architecture inventory in docs/architecture/") and when ("Use when adding, changing, removing, auditing, or documenting...") with explicit triggers, satisfying the highest anchor.	3 / 3
Trigger Term Quality	Covers natural trigger terms a user would say ("adding, changing, removing, auditing, or documenting", "audit, review, report, or propose-only"), giving good coverage rather than jargon-only or generic terms.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Chatto runtime architecture inventory) with highly specific triggers (NATS/JetStream, ConnectRPC/Operator, projections, snapshots), making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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: chattocorp/chatto
Path: .agents/skills/chatto-architecture-inventory/SKILL.md
Commit: 65f65c3

Reviewed: 5 days 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.