resolve-before-asking

Gate on identity questions to the user. Before any "who is X?" (or role / relationship question) reaches the user, exhaust the brain's lookup chain: think → search + page read → mounted sources → timeline/graph → web. If escalation survives the chain, ask WITH a hypothesis, never a bare unknown. Also owns the no-placeholders-at-ingest rule: pages created during bulk ingestion get their relationship/role resolved immediately.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugin-variants/gbrain-coding/skills/resolve-before-asking/SKILL.md

Quality

Content

68%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.

Highly actionable content with a well-signaled structure and an explicit stop-at-first-answer chain, weakened by redundancy across its motivational/contract sections and a batch ingest workflow that lacks a post-write verification step. Both weak points are tightening exercises, not structural failures.

Suggestions

Collapse the repeated no-bare-questions bar (Purpose, The Bug This Kills, Confidence Thresholds, Contract, The Standard) into one statement plus one concrete good/bad example pair; the freed budget would also let the ingest section move to a reference file.

Add a post-write verification step to the ingest pass: after put_page, re-scan the touched pages for placeholder markers and relationship-field presence, mirroring the "Check for placeholders" pre-check, so the batch workflow has a feedback loop.

Show the put_page invocation (or point to the enrich/brain-ops write convention with a one-line command example) so the only un-executable step in an otherwise copy-paste-ready workflow is concrete.

Dimension	Reasoning	Score
Conciseness	There is no basic-concept padding and the commands carry dense signal, but the same no-bare-questions bar is restated across "Purpose", "The Bug This Kills", "Confidence Thresholds", "Contract", and "The Standard", and the anonymized bug examples motivate more than instruct — mostly efficient but could be tightened.	3 / 5
Actionability	Every chain step ships a copy-paste-ready command (gbrain think/search/get/query/timeline/backlinks/graph), plus signal-to-hypothesis mappings, a concrete escalation template, and batch sizing (10–20 pages) — executable guidance covering the common cases.	5 / 5
Workflow Clarity	The six-step lookup chain is clearly sequenced with explicit STOP checkpoints, but the ingest pass is a batch write operation (100+ pages via put_page) with no post-write verification loop, so the rubric's cap on batch operations without validation applies.	3 / 5
Progressive Disclosure	A well-sectioned single-file policy doc whose cross-references (ask-user, query, brain-ops, enrich, brain-first, filing rules) are clearly signaled and one level deep; no bundle files exist to offload into. The ~80-line ingest section and the escalation template could live in a reference file, keeping it below anchor 5.	4 / 5
	Total	15 / 20 Passed

Description

80%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 strong description: concrete, multi-action, with an explicit trigger condition and a clear niche. Its weaknesses are the absence of natural-phrase synonyms inside the description itself and a second scope (ingest placeholders) whose boundary with sibling skills is only defined elsewhere.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Gate on identity questions", "exhaust the brain's lookup chain: think → search + page read → mounted sources → timeline/graph → web", "ask WITH a hypothesis", and resolving "relationship/role" placeholders at ingest — comprehensively covering the skill's behavior.	5 / 5
Completeness	Both "what" and "when" are explicit — "Before any 'who is X?' (or role / relationship question) reaches the user" — but the when is phrased as behavior rather than a directive "Use when..." clause, and the ingest trigger is terser than the gate trigger.	4 / 5
Trigger Term Quality	Natural phrases like "who is X?", "role / relationship question", "bare unknown", and "placeholder" are present, but common variations ("unidentified", "don't know who this is") appear only in the triggers field, not the description itself.	4 / 5
Distinctiveness Conflict Risk	The identity-question gate is a distinct niche, but the description claims ownership of "the no-placeholders-at-ingest rule", which overlaps a sibling enrichment skill; the boundary is drawn in the body's dedup section, not the description.	4 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 8 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: plugin-variants/gbrain-coding/skills/resolve-before-asking/SKILL.md
Commit: e78f1c3

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.