engram-backlog-triage

Backlog triage protocol for Engram: audit open issues and PRs, classify each item, infer maintainer ideology from comments, and produce an actionable disposition report. Trigger: Auditing open issues or PRs, triaging the backlog, reviewing contributor submissions as a maintainer, or applying triage to any GitHub repo.

Quality

84%

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

76%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 and well-structured triage skill with executable commands and explicit decision trees throughout. Its main weakness is the absence of verification checkpoints before destructive batch actions (closing PRs/issues), which the rubric caps at 3 for workflow clarity.

Suggestions

Add an explicit validation/dry-run checkpoint before executing close or request-changes actions (e.g., 'Review the full disposition table and confirm counts before running any gh issue close / gh pr review commands').

Consider moving the reusable prompt template and report scaffold into separate reference files (e.g., references/prompt-template.md, references/report-template.md) and linking to them from SKILL.md to improve progressive disclosure.

Add a pre-flight check at the start of Phase 1 (e.g., 'gh auth status' and confirming repo access) so the batch workflow fails fast with a clear feedback loop rather than mid-triage.

Dimension	Reasoning	Score
Conciseness	Dense tables, tight lists, and executable commands assume Claude's competence with no padding of known concepts; a few sections (reusable prompt template, full report scaffold) add length but earn their place, keeping it just below fully lean.	4 / 5
Actionability	Fully executable `gh` commands with exact `--json` field lists, concrete disposition decision trees ('Does it link a status:approved issue? → if not → CLOSE'), and copy-paste-ready comment templates covering the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced phases with explicit decision-tree checklists, but this is a batch operation issuing destructive actions (closing issues/PRs) with no verification or dry-run checkpoint before acting — the rubric's batch/destructive cap of 3 applies and takes precedence.	3 / 5
Progressive Disclosure	Single self-contained file with clear section headers and well-organized content; no bundle files exist so no nested references, though the inlined reusable prompt template and report scaffold could plausibly live in separate reference files.	4 / 5
	Total	16 / 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 well-crafted description that concretely states multiple capabilities, supplies explicit trigger phrases, and uses distinct third-person language. Minor trigger-synonym gaps keep trigger quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple specific concrete actions — 'audit open issues and PRs, classify each item, infer maintainer ideology from comments, and produce an actionable disposition report' — with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (audit, classify, infer ideology, produce disposition report) and 'when' via a concrete 'Trigger:' clause listing natural trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keyword coverage — 'Auditing open issues or PRs, triaging the backlog, reviewing contributor submissions as a maintainer, applying triage to any GitHub repo' — but a few natural synonyms (e.g., 'review open PRs') are missing, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — Engram backlog triage with GitHub-repo triggers — making it unlikely to fire for unrelated skills; uses third-person voice throughout with no first/second person.	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: Gentleman-Programming/engram
Path: skills/backlog-triage/SKILL.md
Commit: 47f281c

Reviewed: 6 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.