coding-agent

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/coding-agent/SKILL.md

Quality

Content

65%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 executable commands and helpful tables, but loses points on conciseness from repeated warnings and asides, and on workflow clarity because batch and destructive operations omit validation checkpoints. Progressive disclosure is middling since everything is inlined into one long file with no references.

Suggestions

Add validation checkpoints to batch/destructive workflows, e.g. verify tests/build pass before 'gh pr create', or review the agent output before posting a PR comment.

Consolidate the PTY guidance into a single stated-once rule and remove playful asides to tighten token usage.

Move the batch PR-review and parallel-issue-fix recipes into a referenced file (e.g. references/batch-workflows.md) so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with reference tables and executable snippets, but the PTY warning is repeated across multiple sections and playful asides ('soul.md', 'Deploy the army', 'Sass works') add padding that could be trimmed.	3 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands for each agent along with parameter and process-action tables, covering the common one-shot, background, and batch cases.	5 / 5
Workflow Clarity	Sequences for background monitoring, batch PR review, and parallel issue fixing are present, but batch/destructive operations (parallel PR reviews, --yolo with commit-and-push) lack validation checkpoints, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist and none are referenced; the ~285-line single file is well-sectioned but inlines bulk content (batch workflows, per-agent sections) that could be split into one-level-deep reference files, leaving structure short of a clear overview-with-references layout.	3 / 5
	Total	14 / 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 is specific and distinctive, naming four concrete coding agents and a clear mechanism (background process for programmatic control). Its main weakness is the absence of an explicit 'Use when...' trigger clause, which limits completeness.

Suggestions

Add an explicit trigger clause such as 'Use when you need to run a coding agent programmatically, review PRs in bulk, or fix issues in parallel.'

Broaden action coverage beyond 'run via background process' to mention review, fix, and build tasks the agents perform.

Dimension	Reasoning	Score
Specificity	Names four concrete coding agents (Codex CLI, Claude Code, OpenCode, Pi) and the specific action of running them via background process for programmatic control, but offers only one core action rather than a comprehensive multi-action list.	4 / 5
Completeness	Has a clear 'what' but no 'Use when...' trigger clause, so per the rubric a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Uses the natural product names a user would say (Codex CLI, Claude Code, OpenCode, Pi Coding Agent), but misses common task phrasings like 'review a PR' or 'run an agent in the background'.	4 / 5
Distinctiveness Conflict Risk	Naming four specific coding agents gives it a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/coding-agent/SKILL.md
Commit: c5e1f97

Reviewed: 2 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.