process-discussions

Facilitate Open Notebook's GitHub Discussions queue — qualify Ideas, decompose them into distinct needs, verify claims in code, propose outcomes (exploring / graduated / parked / combined), draft replies, and graduate small gaps into ready Issues. Use when processing, triaging, or responding to Discussions, or when the user says "process discussions" / "vamos fazer as discussions".

Quality

90%

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

Quality

Content

88%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 facilitation playbook with executable commands and strong validation gates. Its main weakness is progressive disclosure: a long single-file body that could offload reference material (GraphQL ID regeneration, the outcome table) into separate files.

Suggestions

Move the GraphQL category-id regeneration snippet and the outcomes table into a reference file (e.g. references/outcomes.md), keeping SKILL.md as a lean overview that links one level deep.

Relocate calibration provenance dates (2026-08-16, 2026-09-02) into a short 'Calibration history' note or memory pointer so the main flow stays evergreen.

Trim editorializing lines like 'The single highest-value step' and 'Cluster detection across the queue is what makes individual replies good' to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense with calibrated, domain-specific practice rather than concepts Claude already knows, but carries mild editorializing and embedded calibration dates (2026-08-16, 2026-09-02) that could be tightened or moved to a provenance note.	4 / 5
Actionability	Provides copy-paste-ready GraphQL queries, concrete gh CLI commands, a precise outcome table with required reply contents, and an ordered 8-step reply structure covering the common cases.	5 / 5
Workflow Clarity	Phases 0–4 plus Session close are clearly sequenced, with an explicit approval gate before any post/close/open and verification-before-replying as a feedback loop for the batch/destructive GitHub operations.	5 / 5
Progressive Disclosure	Section headers organize the phases well, but this is a ~200-line monolithic file with all detail inline and no bundle files; the under-50-line simple-skill exception does not apply, so it stops short of clean one-level-deep reference splitting.	4 / 5
	Total	18 / 20 Passed

Description

92%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, specific description that concretely states what the skill does and when to invoke it, with a distinct trigger including a non-English phrase. The only minor gap is synonym coverage in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — qualify Ideas, decompose into distinct needs, verify claims in code, propose named outcomes, draft replies, graduate gaps into ready Issues — giving comprehensive coverage rather than just naming the domain.	5 / 5
Completeness	Explicitly answers both 'what' (the facilitation action list) and 'when' via a 'Use when...' clause with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases ('processing, triaging, or responding to Discussions') plus explicit trigger quotes ('process discussions', 'vamos fazer as discussions'), but does not enumerate a fuller set of synonyms a user might say.	4 / 5
Distinctiveness Conflict Risk	Scoped to Open Notebook's GitHub Discussions queue with a distinct bilingual trigger, giving it a clear niche and minimal overlap with other skills.	5 / 5
	Total	19 / 20 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: lfnovo/open-notebook
Path: .claude/skills/process-discussions/SKILL.md
Commit: 8297bb2

Reviewed: 4 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.