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

82%

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

65%

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

The body is highly actionable with executable gh commands and clear phases, but it is over-long for a single file and lacks verification checkpoints before destructive batch actions.

Suggestions

Add a validation/checkpoint step before destructive batch actions (e.g., dry-run or confirm that disposition counts reconcile with fetched totals before applying labels, closing, or merging).

Split the reusable prompt template and the full example triage report into separate reference files to reduce the inline length and improve progressive disclosure.

Trim the redundant restatement of the philosophy table and disposition set in the reusable prompt template section, linking to the canonical tables instead.

Dimension	Reasoning	Score
Conciseness	Largely efficient and instruction-dense, but ~260 lines with redundancy: the reusable prompt template re-states the philosophy and disposition set already covered, and the example report/suggested comments duplicate the phase guidance. It could be tightened; not the lean top anchor.	2 / 3
Actionability	Fully executable gh commands (issue list/view/edit/close, pr list/view/review/merge), concrete classification decision trees, and copy-paste report and suggested-comment templates match the fully-executable top anchor.	3 / 3
Workflow Clarity	A clear five-phase sequence exists, but the Quick-Action Commands perform batch destructive mutations (closing issues, merging, rejecting, labeling) with no validation/checkpoint step before acting — the rubric caps workflow clarity at 2 for destructive/batch operations lacking verification.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is a single well-sectioned file, but at ~260 lines content that could be split out (reusable prompt template, full example report) is kept inline, matching the anchor for content that should be separate being inline.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and answers both what and when with natural trigger terms. It is a strong, conflict-resistant description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "audit open issues and PRs", "classify each item", "infer maintainer ideology from comments", "produce an actionable disposition report" — matching the top anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (audit, classify, infer, produce report) and when via the dedicated "Trigger:" clause, satisfying the top anchor for clear what-and-when with explicit triggers.	3 / 3
Trigger Term Quality	Natural user phrasing is well covered — "triaging the backlog", "reviewing contributor submissions as a maintainer", "applying triage to any GitHub repo" — terms a maintainer would actually say when they need this skill.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (backlog triage protocol for Engram/maintainer review) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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: Gentleman-Programming/engram
Path: skills/backlog-triage/SKILL.md
Commit: 763a6ba

Reviewed: 3 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.