ask

Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, follows one SALP-REF hop, files a cited answer back. Not for source code.

Quality

81%

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

75%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 highly actionable, well-sequenced procedural skill body with concrete templates and checkpoints throughout. Its main weakness is conciseness, due to a redundant Honest-Gaps section and a padded dated anecdote that restate guidance already present in the main steps.

Suggestions

Fold the 'Honest-Gaps Rule' section into step 4's existing 'Honest gaps' bullet rather than restating it as a separate section, to remove the duplication.

Trim or move the '(2026-09-06: ask-honest-gap withheld the answer...)' incident parenthetical into a brief rationale clause; the dated narrative padding inflates token cost without aiding execution.

Add an explicit verify step after filing (e.g., confirm the answer file was written and that every SALP REF cited resolves to a real page) to close the workflow's validation gap and lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance, but the standalone 'Honest-Gaps Rule' section duplicates step 4's bullets and the dated '(2026-09-06: ask-honest-gap...)' parenthetical is narrative padding that could be trimmed.	3 / 5
Actionability	Provides fully executable, copy-paste-ready instruction-only guidance: exact file paths, frontmatter templates, log/report string formats, slug derivation rules, and a concrete citation example.	5 / 5
Workflow Clarity	Eight clearly sequenced steps with real checkpoints (resolution fallback, index fallback, gap detection, slug-collision guard, user-gated promotion), but it lacks an explicit validate-the-output feedback loop, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Well-organized into clear sections for a self-contained skill with no external bundle files needed, though the duplicated Honest-Gaps content is a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

87%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, third-person description that clearly states both capability and trigger conditions with explicit boundary guidance. It is highly distinct and complete, with only minor gaps in action comprehensiveness and trigger synonym coverage.

Dimension	Reasoning	Score
Specificity	Names the memex domain and lists several concrete actions ('Reads the index, follows one SALP-REF hop, files a cited answer back'), but synthesis and promotion steps are only implied rather than enumerated, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' ('Reads the index, follows one SALP-REF hop, files a cited answer back') and 'when' ('Use when the user asks a question...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural trigger coverage ('Use when the user asks a question', 'memex'), but it lacks common synonym variations like 'look up' or 'search my notes' that a user might naturally say.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche ('from the project's memex... rather than training data or the live web... Not for source code') with explicit boundaries that minimize overlap with other skills.	5 / 5
	Total	18 / 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: korchasa/flowai-plugins
Path: plugins/flowai-memex/skills/ask/SKILL.md
Commit: ad81ae6

Reviewed: 8 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.