x-do

Use when the user asks to build, implement, fix, or execute a plan — detects context (existing plan, new feature, bug, quick task, visual input) and routes through brainstorming, planning, debugging, or execution workflows

Quality

74%

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/x-do/SKILL.md

Quality

Content

73%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 well-structured router skill with strong workflow sequencing, explicit validation checkpoints, and good progressive disclosure into real reference files. Its main weakness is conciseness: the router-forbid rule and the hephaestus→codex replacement are restated across several sections, adding tokens that could be consolidated.

Suggestions

Consolidate the router-forbid rule: state it once in 'Role: router' and have the Mode D / post-execution-correction / Backlog Doc Lifecycle exceptions reference that single statement instead of restating the forbid each time.

Mention the hephaestus→--model codex replacement once (in the Bootstrap or OMO routing section) and reference it elsewhere, rather than repeating '(replaces UNAVAILABLE hephaestus)' inline at every delegation site.

Flag the cross-bundle references that resolve outside this skill (../x-shared/*, gotchas.md, steps/step-*.md) so a reader knows which files are local to the bundle versus shared infrastructure — improves navigability of the reference graph.

Dimension	Reasoning	Score
Conciseness	The body is largely dense and discipline-focused, but ~240 lines with repeated restatements of the router-forbid rule (three separate exception sections restating it) and the recurring '(replaces UNAVAILABLE hephaestus) → --model codex' note across multiple sections add padding that could be tightened; it sits at the 'mostly efficient but some unnecessary explanation' anchor rather than the lean 4 or 5.	3 / 5
Actionability	Concrete executable guidance throughout — explicit commands ('npx tsc --noEmit', 'npx eslint <changed-files>', 'git mv docs/backlog/<slug>.md ...', 'Skill: x-skills:x-review <plan-path>'), precise thresholds (single file, <10 lines; ≤3 files), and a verbatim slot-resolution block; minor gaps (the AskUserQuestion option strings are not given as ready templates) keep it at 4 rather than 5.	4 / 5
Workflow Clarity	A MANDATORY Pre-Flight Checklist with checkboxed sub-steps, a Detection table, explicit validation checkpoints (tsc/eslint before claiming done), and a full verdict feedback loop for x-verify (done/failed/needs-user-review/aborted/waiting) with error-recovery branches — this matches the 'clear sequence with explicit validation steps and feedback loops' anchor exactly, including for destructive/batch operations.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with clearly signaled one-level-deep references to real bundle files (references/mode-guidance.md, references/available-tools.md, references/delegation-and-scaling.md, references/iteration-patterns.md, references/omo-routing.md, references/planning-pipeline.md, all present); minor gaps — several references target files outside this bundle (../x-shared/, gotchas.md, steps/step-.md) that are not present here — keep it at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

75%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 strong and well-balanced: it pairs concrete capabilities with explicit 'Use when' trigger phrasing and third-person voice. Its only weakness is breadth — the trigger set is generic enough to risk overlapping with the executor skills it routes to.

Suggestions

Sharpen the trigger clause to signal routing rather than execution, e.g. 'Use when the user wants to start work and the right workflow is unclear — x-do classifies and dispatches rather than executing itself'.

Add 'refactor' and 'debug' to the trigger verb list so the description mirrors the actual Mode A–D detection surface.

Clarify the visual-input trigger ('when the user pastes an image/PDF/screenshot') since it is currently only named as a detected context, not as a user-facing trigger.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('detects context', 'routes through brainstorming, planning, debugging, or execution workflows') and enumerates input categories (existing plan, new feature, bug, quick task, visual input), with only minor coverage gaps — closer to the 'several specific actions' anchor (4) than the comprehensive (5) or the 1-2-action anchor (3).	4 / 5
Completeness	Explicit 'Use when the user asks to build, implement, fix, or execute a plan' gives a clear 'when', and 'detects context ... routes through ... workflows' gives the 'what'; both are present, but the 'when' could be more specific about visual-input and refactor triggers, so it falls just below the 5 anchor.	4 / 5
Trigger Term Quality	'build, implement, fix, or execute a plan' maps to natural user phrasings and includes several synonyms; good coverage but a few natural terms (e.g. 'refactor', 'add a feature', 'debug') are only implied rather than enumerated, so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The router niche ('detects context and routes') is mostly distinct from the executors it dispatches, but the trigger verbs 'build/implement/fix/execute a plan' overlap with sibling skills (x-bugfix, x-review, writing-plans), giving minor overlap risk that keeps it at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: quangtran88/x-skills
Path: skills/x-do/SKILL.md
Commit: 667abc8

Reviewed: 20 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.