memory-mining

Authoritative protocol for querying the Memory Core before diagnosing regressions or proposing non-trivial architectural claims. Prevents re-derivation of prior reasoning by surfacing cross-session, cross-harness context via semantic search. Triggers: Use this skill when (1) the user reports a regression symptom ("used to work", "suddenly broken", surprise validation failures, schema mismatches, "additionalProperties" rejections), OR (2) you are about to propose an architectural claim, roadmap, or comparison against external work where prior sessions may have already mapped the territory, OR (3) you are about to begin an implementation or a PR-review — a cheap 3–10-call prior-art sweep before the first design sentence or review verdict.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

100%Weight 40%Scale 1-3

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

An exemplar of progressive disclosure: a minimal, concrete, gated body that delegates all substantive protocol to a single well-signaled reference file that is present in the bundle. No padding, no inferred-only steps.

Dimension	Reasoning	Score
Conciseness	The body is two lean sentences that assume Claude's competence and add no background Claude already knows; every token earns its place.	3 / 3
Actionability	Gives a concrete, executable instruction — 'use the `view_file` tool to read ... `.agents/skills/memory-mining/references/memory-mining-protocol.md`' — with a specific tool and exact path, copy-paste ready rather than vague.	3 / 3
Workflow Clarity	For this single-action skill the action is unambiguous and sequenced with an explicit gating checkpoint: read and adhere to the protocol BEFORE running `git log`, `grep`, the first design sentence, or a review verdict.	3 / 3
Progressive Disclosure	The body is a concise overview that points to exactly one reference file at one level deep via a clearly signaled path; the referenced `references/memory-mining-protocol.md` exists in the bundle, matching the ideal overview-plus-one-level-reference structure.	3 / 3
	Total	12 / 12 Passed

Description

90%Weight 40%Scale 1-3

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, specific description with explicit, multi-condition triggers and natural user phrasing. Its only weakness is second-person voice in the trigger clause, which the rubric penalizes on specificity.

Suggestions

Rewrite the trigger clause in third person to avoid the specificity penalty, e.g. 'Triggers: Use when a regression symptom is reported... OR an architectural claim is about to be proposed... OR an implementation or PR review is about to begin.'

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('querying the Memory Core', 'diagnosing regressions', 'proposing non-trivial architectural claims', 'prior-art sweep'), which would be a 3, but the trigger clause uses second person ('you are about to propose', 'you are about to begin'), which the rubric penalizes by reducing specificity by one.	2 / 3
Completeness	Explicitly answers both 'what' (query the Memory Core before diagnosing/proposing) and 'when' via a labelled 'Triggers: Use this skill when (1)... OR (2)... OR (3)...' clause, matching the anchor for explicit triggers.	3 / 3
Trigger Term Quality	Quotes natural user-facing phrases ('used to work', 'suddenly broken', 'surprise validation failures', 'schema mismatches', 'additionalProperties rejections') alongside situational cues ('roadmap', 'PR-review'), giving good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (memory prior-art sweep before regressions or architectural claims) with distinct, narrow triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: neomjs/neo
Path: .agents/skills/memory-mining/SKILL.md
Commit: c1ce853

Reviewed: 8 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.