functional-area-resolver

Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/functional-area-resolver/SKILL.md

Quality

Content

77%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.

The body is highly actionable with a well-sequenced, validation-gated workflow, but it is verbose and inlines eval-data and citation material that belongs in the already-referenced evals README. Splitting that detail into a local reference file would improve both conciseness and progressive disclosure.

Suggestions

Move the A/B eval tables, methodology caveats, and prior-work/citations into a local references/ file (e.g. EVAL.md) and keep SKILL.md to a one-paragraph summary plus a pointer, raising both conciseness and progressive_disclosure.

Add a short 'Quick start' or 'TL;DR' block at the top with the single canonical command sequence so the core workflow is reachable without scrolling past the eval section.

Convert the external evals/functional-area-resolver/ references into clearly-signaled local links or note explicitly that they live in a separate gbrain repo checkout, so navigation expectations are unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and evidence-backed, but the A/B eval tables, methodology caveats, and prior-work/citations sections are lengthy and largely duplicated by the referenced evals/functional-area-resolver/README.md, so several sections could be trimmed or moved out of SKILL.md.	3 / 5
Actionability	It provides copy-paste-ready, executable guidance throughout: exact commands ('gbrain routing-eval --json', 'node harness.mjs --variants-dir ...'), a concrete area-entry template, a before/after example, and reproduce commands covering the common cases.	5 / 5
Workflow Clarity	Steps 1-7 form a clear sequence with explicit validation checkpoints (Gate 1 structural verification, Gate 2 LLM A/B verification), preconditions gating, and feedback loops ('If accuracy drops below 95%, revert and tune'), which matches the anchor-5 example for destructive operations.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent), and the body inlines bulk eval-results and citation content rather than splitting it out; the only references point to external gbrain-repo paths rather than local one-level-deep files, so structure is present but not cleanly progressed.	3 / 5
	Total	16 / 20 Passed

Description

67%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.

The description is specific and distinctive about what the skill does, but omits an explicit 'when to use it' clause and under-specifies natural trigger terms within the description string itself. Moving a representative trigger phrase or 'Use when...' clause into the description would lift completeness and trigger_term_quality.

Suggestions

Add an explicit 'Use when...' clause to the description (e.g. 'Use when a RESOLVER.md/AGENTS.md routing file exceeds ~12KB and skills can be grouped into functional areas') to raise completeness above the 3 cap.

Surface 2-3 natural user trigger phrases ('resolver too big', 'shrink routing table', 'agents.md too large') inside the description so trigger_term_quality does not depend solely on the separate triggers field.

Keep the third-person voice but consider a one-line concrete outcome ('13KB from 25KB at equal or better routing accuracy') to sharpen specificity further.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('converting granular skill-per-row tables into functional-area dispatchers', 'lists sub-skills in a (dispatcher for: ...) clause', 'reads one area entry and routes to the correct sub-skill') with comprehensive coverage of the transformation.	5 / 5
Completeness	It clearly states the 'what' but provides no 'Use when...' clause or equivalent explicit trigger guidance within the description; that guidance is split into the separate triggers frontmatter field, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	The description contains some relevant keywords ('compress', 'routing file', 'RESOLVER.md', 'AGENTS.md') but the natural trigger phrases a user would say live in the separate triggers field, and common synonyms like 'shrink'/'too big' are absent from the description string itself.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (routing-file compression via functional-area dispatchers) with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: garrytan/gbrain
Path: skills/functional-area-resolver/SKILL.md
Commit: 7b7921d

Reviewed: ~12 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.