engram-issue-creation

Issue creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a GitHub issue, reporting a bug, or requesting a feature.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/issue-creation/SKILL.md

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.

The body is highly actionable with concrete commands, real template paths, and complete examples, plus a clearly sequenced workflow with validation gates. Its main weakness is redundancy across the Workflow, Decision Tree, and Commands sections and the absence of an explicit rejected-issue recovery loop.

Suggestions

Collapse the redundant sequencing — keep one canonical workflow and have the Decision Tree and Commands sections reference it rather than restating steps.

Add an explicit rejected-issue feedback loop (e.g., 'If maintainer rejects: address the comment, update fields, re-submit; do not open a PR until status:approved') to push workflow clarity toward 5.

Consider moving the per-template field tables into a referenced file if the skill grows, to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concepts Claude already knows, but the same workflow is restated multiple times (numbered Workflow, Decision Tree, Maintainer Approval Workflow, and Commands sections), so it could be tightened — placing it at anchor 3 rather than 4.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: concrete `gh issue create --template ...` commands, real template paths, exact label names, and two complete bug/feature example bodies covering the common cases.	5 / 5
Workflow Clarity	The creation workflow is clearly sequenced (search duplicates → choose template → fill fields → submit → await approval → open PR) with validation checkpoints (duplicate search, the status:needs-review → status:approved gate, and a reject/close path), but lacks an explicit error-recovery feedback loop for rejected issues, so it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	A single self-contained file with well-organized section headers (When to Use, Critical Rules, Workflow, Issue Templates, Label System) and no nested or buried references; scored 4 rather than 5 because it exceeds ~50 lines with no external file split, though the inline reference tables are reasonably placed.	4 / 5
	Total	16 / 20 Passed

Description

70%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.

The description clearly states both purpose and trigger conditions with natural user-facing language and a distinct Engram niche. Its main weakness is the unexplained 'issue-first enforcement system' jargon and trigger-style actions standing in for a fuller capability list.

Suggestions

Replace or briefly gloss 'issue-first enforcement system' with a concrete phrase (e.g., 'requires maintainer approval before any PR') so the 'what' is self-explanatory.

Add common synonyms users say — 'bug report', 'feature request', 'filing an issue' — to widen trigger coverage toward anchor 5.

Expand the capability list beyond triggers (e.g., 'pick the correct template, fill required fields, apply status/priority labels') to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('Issue creation workflow for Engram') and concrete actions ('creating a GitHub issue, reporting a bug, or requesting a feature'), but these read as triggers for a single capability rather than a comprehensive list of distinct actions, so it sits at anchor 3 rather than 4.	3 / 5
Completeness	Both 'what' (issue creation workflow for Engram) and 'when' (an explicit 'Trigger:' clause with concrete triggers) are answered, but the 'what' leans on unexplained jargon ('issue-first enforcement system') that keeps it from the fully concrete anchor 5.	4 / 5
Trigger Term Quality	Natural phrases a user would say are present ('creating a GitHub issue, reporting a bug, requesting a feature'), giving good keyword coverage; a few common synonyms ('bug report', 'feature request', 'filing an issue') are missing, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	The Engram-scoped, issue-creation niche is mostly distinct with clear triggers, but 'creating a GitHub issue / reporting a bug' could overlap with general GitHub or git workflows, so minor overlap risk caps it at 4 rather than 5.	4 / 5
	Total	15 / 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/issue-creation/SKILL.md
Commit: 5d5bf83

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.