CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

74%

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

Fix and improve this skill with Tessl

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

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.

An unusually strong operational skill: the compression workflow is fully executable with mandatory dual verification gates, revert thresholds, and feedback loops. Its weakness is token economy — roughly a third of the body is A/B eval evidence and literature justification, plus scattered version/date references, that should live in a one-level-deep reference file.

Suggestions

Move the A/B eval tables, 'What the data shows' narrative, methodology caveats, and prior-work citations into a bundled reference file (e.g. references/eval-results.md), keeping only a one-line pointer and the decision-relevant takeaways (dispatcher clause is load-bearing; pin gbrain v0.32.3.0+) in the body.

Consolidate the scattered version/date references (v0.31.7, v0.32.3.0, v0.33.x follow-ups, 2026-05-11 receipts) into the existing Changelog or a dedicated Versioning section so time-sensitive details are isolated from the operational steps.

DimensionReasoningScore

Conciseness

The operational core (Steps 1-7, Anti-Patterns, Maintenance) is lean and assumes competence, but ~90 lines of A/B eval tables, "What the data shows" narrative, methodology caveats, and arXiv citations are inline justification that belongs beside the evals README it already points to, and time-sensitive version/date references (v0.31.7, v0.32.3.0, v0.33.x, 2026-05-11, Opus 4.7) are scattered rather than isolated in a deprecated/version section. Not 2 because nothing explains concepts Claude already know — the padding is domain-specific evidence, not fluff; not 4 because the eval-evidence sections could clearly be trimmed out of the loaded body.

3 / 5

Actionability

Copy-paste-ready commands throughout: `gbrain routing-eval --json`, the full harness invocation with `--variants-dir`, `--variants my-edit`, `--model opus --parallel 3` plus the two-step cost-approval flow, concrete thresholds (12KB gate, 95% accuracy floor), and an exact area-entry template. Fully executable guidance covering the common cases, matching the anchor-5 example.

5 / 5

Workflow Clarity

Steps 1-7 are explicitly sequenced with preconditions (refuse below 12KB, clean git tree), a MANDATORY dual verification gate, a 95% revert threshold, enumerated common failure causes to tune against, and explicit user-approval checkpoints before staging — a textbook validate → fix → retry loop for a batch rewrite operation. This exceeds the anchor-5 example's feedback-loop structure.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so all content is inline in a single ~330-line SKILL.md; section headers make it navigable, but the eval results, methodology caveats, and prior-work citations are content that clearly belongs in a separate reference file. Fits anchor 3 (good structure, but content that should be separate is inline) rather than 2, since the body is well-sectioned and easy to navigate.

3 / 5

Total

16

/

20

Passed

Description

62%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 specific, well-mechanized description for a clearly distinct niche, weakened by the absence of an explicit 'Use when...' clause and by keeping natural trigger phrases out of the description body (they live in a separate triggers list). The what is excellent; the when is only implied.

Suggestions

Add a 'Use when...' clause to the description (e.g. "Use when RESOLVER.md or AGENTS.md grows past ~12KB and routing rows eat the context budget") so the trigger condition is explicit in the always-loaded text.

Fold one or two natural user phrasings from the triggers list ("resolver too big", "shrink routing table", "slim down agents.md") into the description itself so common synonyms ride along with the description rather than living only in the separate triggers field.

DimensionReasoningScore

Specificity

Quotes like "Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers" and "Each area lists sub-skills in a '(dispatcher for: ...)' clause" name the domain and several concrete actions with the exact mechanism. Not 5 because operational actions (precondition gates, verification, maintenance workflow) are absent from the description; not 3 because it goes beyond 1-2 actions to specify the dispatcher-clause mechanism.

4 / 5

Completeness

The "what" is clear and concrete (compress routing file into functional-area dispatchers with dispatcher-for clauses), but there is no "Use when..." clause or equivalent explicit trigger guidance — when to use it is only implied by the problem framing. Per the judging guideline, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

The description carries domain keywords ("compress", "routing file", "RESOLVER.md", "AGENTS.md", "functional-area dispatchers") but omits the natural user phrasings like "resolver too big", "shrink routing table", "slim down agents.md" that exist only in the separate triggers list. Fits anchor 3 (relevant keywords, missing common variations) rather than 4, since the natural-language trigger phrases a user would actually say are not in the description itself.

3 / 5

Distinctiveness Conflict Risk

This is a clear niche — compressing RESOLVER.md/AGENTS.md routing tables into dispatcher entries — with distinct, targeted triggers that no other skill would plausibly claim. Minimal conflict risk with other skills, matching the anchor-5 example of a distinct niche with distinct triggers.

5 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

garrytan/gbrain

Path

skills/functional-area-resolver/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.