devloop

Goal-driven development loop — define objective, write rules with key-results, verify visually, sync to issue tracker.

Quality

65%

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 ./mod/skill0/lib/skill0/core/devloop/SKILL.md

Quality

Content

88%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 a lean, executable workflow with explicit validation checkpoints and a clear five-step sequence, achieving high conciseness and workflow clarity. Minor gaps in actionability and a slight opportunity to externalize the rule.yml schema keep it just short of perfect progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient: short sections, command/code blocks only, and minimal prose that assumes Claude's competence; every line (Setup, Workflow, rule.yml example, verification commands, sync pointer) earns its place with no concept explanations.	5 / 5
Actionability	Mostly executable with concrete commands (`x rule scan/check/audit`, `agent-browser screenshot`, `gh issue create/comment`) and a complete rule.yml example, but a few gaps (e.g. `x env use agent-browser` setup details, exact `agent-browser open` invocation) keep it just below fully copy-paste ready.	4 / 5
Workflow Clarity	A clear five-step sequence (goal → rule.yml → code → verify → issue) with explicit validation checkpoints: before/after screenshots, an AI vision check with an iterate-and-re-screenshot feedback loop, and `x rule scan/check/audit` verification before syncing — satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Well-organized overview with clearly signaled one-level-deep references to sibling skills (rule, score, install, agent-browser, issue, repo, prompt) and a pointer to issue/SKILL.md for sync detail; no bundle files exist, and most content is appropriately inline, with only minor gaps where a dedicated reference could hold the rule.yml schema.	4 / 5
	Total	18 / 20 Passed

Description

42%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 states the skill's purpose and lists concrete actions, but it lacks any explicit 'Use when...' trigger guidance and leans on skill-internal jargon rather than natural user language. Completeness and trigger-term quality are the main weaknesses.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when starting a feature task that needs goal/KR tracking, visual verification, and issue-tracker sync.'

Replace or supplement jargon ('rule.yml', 'key-results') with user-facing phrasing users would actually say, such as 'development tasks', 'track goal progress', 'before/after screenshots'.

Sharpen the 'what' with more concrete verbs (e.g. 'screenshot before/after', 'post goal and KRs to the issue tracker') to lift specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain (goal-driven development loop) and lists several concrete actions (define objective, write rules with key-results, verify visually, sync to issue tracker), but the actions are high-level process verbs rather than fully concrete operations, leaving coverage incomplete.	3 / 5
Completeness	It clearly states what the skill does but provides no explicit 'when' guidance — there is no 'Use when...' clause or equivalent trigger, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	The phrasing relies on skill-internal jargon ('rule.yml', 'key-results', 'sync to issue tracker') rather than natural trigger terms a user would actually say; there is no 'Use when...' clause and only minimal everyday phrasing.	2 / 5
Distinctiveness Conflict Risk	The goal/loop framing is somewhat specific to this toolchain, but 'define objective / verify / sync to issue' overlaps with general development workflows and related sibling skills (rule, issue, agent-browser), so it is somewhat distinct with moderate overlap risk.	3 / 5
	Total	11 / 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
relative_links	Relative link issues: 8 suspicious	Warning

	Total	14 / 16 Passed

Repository: x-cmd/x-cmd
Path: mod/skill0/lib/skill0/core/devloop/SKILL.md
Commit: e18c1ef

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.