work-issues

Autonomously work one task from an issues/ queue end-to-end — explore, implement (TDD when applicable), run feedback loops, commit, update the issue file. Step 3 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Heavyweight (commits code, modifies the issue queue). Use only when explicitly asked: /work-issues, "work the issue queue", "run an AFK iteration", "do one issue end-to-end", OR when another orchestrator skill (e.g. /feature) needs to dispatch an AFK iteration programmatically. Headless loop runner: bin/loop.sh.

Quality

87%

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

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.

A well-crafted, dense workflow skill with executable input-gathering commands, per-language feedback loops, and explicit safety rules for destructive git operations. It is strong across the board, with only minor tightening and a few more concrete implementation details needed to reach top marks.

Suggestions

Tighten the Lane preamble and Feedback loops sections — the per-language command list and allowlist protocol could be shortened without losing clarity.

Add one concrete example of a 'smallest correct change' or a representative commit message in the Implementation/Commit sections to lift actionability from abstract directive to copy-paste-ready.

Make the iteration lifecycle explicit as a numbered sequence (e.g. Inputs → Select → Explore → Implement → Loops → Commit → Rubric → Housekeeping) so the validation checkpoints are enumerated rather than implied by section order.

Dimension	Reasoning	Score
Conciseness	Largely lean with imperative directives and no over-explanation of concepts Claude knows; the lane-preamble and feedback-loop sections could be trimmed slightly, placing it just below the level-5 'every token earns its place' anchor.	4 / 5
Actionability	Provides executable shell snippets (git log, find with exclusions) and concrete per-language loop commands, but the Exploration and Implementation sections remain directive-abstract ('smallest correct change, then verify'), leaving minor gaps.	4 / 5
Workflow Clarity	Sections follow a clear lifecycle order with validation checkpoints (feedback loops before commit, 'Don't commit a red build', rubric check, hard-rules stop conditions); the destructive/batch cap does not apply since validation is present, though some checkpoints are implicit rather than enumerated.	4 / 5
Progressive Disclosure	A single well-sectioned file with clear headers and one-level references to project tooling (bin/loop.sh, the tdd skill); no bundle files exist and no nested references, so organization is good but it is not the canonical overview-points-to-bundle pattern.	4 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplary description: concrete actions, explicit trigger guidance, clear pipeline positioning, and third-person voice with no fluff. It tells both Claude and the user exactly what it does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'explore, implement (TDD when applicable), run feedback loops, commit, update the issue file' — with comprehensive coverage of the iteration lifecycle, matching the level-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (autonomously work one task end-to-end through explore/commit/update) and 'when' via a clear 'Use only when explicitly asked:' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases users would say — '/work-issues', 'work the issue queue', 'run an AFK iteration', 'do one issue end-to-end' — plus the programmatic-dispatch path; not merely technical jargon.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche as 'Step 3 of the build pipeline' distinct from write-a-prd and prd-to-issues, with guarded explicit-only triggers minimizing overlap with other skills.	5 / 5
	Total	20 / 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: belchman/claude-skills
Path: plugins/agentic-engineering/skills/work-issues/SKILL.md
Commit: 77a9e6b

Reviewed: 11 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.