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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Quality

Content

77%

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-engineered router: actionable commands, explicit checklists, verdict-driven feedback loops, and good reference splitting. Its two weak spots are length/inline detail that could move to reference files, and progressive-disclosure gaps where steps/*.md and gotchas.md are referenced but absent from the provided bundle.

Suggestions

Create the missing steps/step-01-gather.md through step-04-execute.md (and gotchas.md) that the body and planning-pipeline.md reference, or remove/redirect those references — several 'see steps/...' and 'Read gotchas.md' instructions currently point at files that do not exist in the bundle.

Move the detailed Backlog Doc Lifecycle (frontmatter flips, the inline git rev-parse worktree-detection shell snippet, and archival git mv choreography) into a references/backlog-lifecycle.md and keep only the trigger condition and one-line summary inline in SKILL.md.

Trim the parenthetical justifications embedded in the Pre-Flight --wt and Backlog sections (e.g., the git ≥ 2.31 / ≥ 2.5 version notes); these are reference-grade rationale that inflate the overview without aiding dispatch.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with no padding about concepts Claude already knows, but it is long (~240 lines) and some inline detail — notably the Backlog Doc Lifecycle with its embedded shell snippet and parenthetical git-version justifications — could be tightened or pushed to a reference file, landing at 'mostly efficient but could be tightened' rather than 'every token earns its place'.	2 / 3
Actionability	It gives concrete, copy-paste-ready guidance throughout: exact commands ('npx tsc --noEmit', 'npx eslint <changed-files>', 'git mv docs/backlog/<slug>.md ...'), precise dispatch syntax ('Skill: x-skills:x-review <plan-path>'), a memory call ('search_notes({ query: ..., page_size: 5 })'), and an observable-signal detection table — fully executable, not pseudocode.	3 / 3
Workflow Clarity	Multi-step flows are explicitly sequenced with validation checkpoints: a MANDATORY Pre-Flight Checklist, a verdict-handling Completion section with feedback loops ('verdict: failed → fire verification-failed reaction'), and a Post-Implementation Verification block that gates done on tsc/eslint passing — matching the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	It structures content well with one-level-deep, clearly signaled references (See references/available-tools.md, mode-guidance.md, delegation-and-scaling.md, omo-routing.md — all present in the bundle), but several referenced paths are missing from the bundle — the steps/step-0[1-4]-*.md files (no steps/ dir) and gotchas.md — and the heavy inline Backlog Doc Lifecycle could itself be split out, so it sits at 'some structure but could be better organized' rather than the clean one-level-deep anchor.	2 / 3
	Total	10 / 12 Passed

Description

92%

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: concise, concrete, third-person, with an explicit 'Use when' trigger and a clear what/when split. Its only weakness is inherent to its role as a universal router — the trigger terms are broad enough to overlap with the very skills it routes to.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('build, implement, fix, or execute a plan', 'routes through brainstorming, planning, debugging, or execution workflows') and the contexts it detects ('existing plan, new feature, bug, quick task, visual input'), matching the multi-action anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly answers both halves — what it does ('detects context ... and routes through brainstorming, planning, debugging, or execution workflows') and when to use it ('Use when the user asks to build, implement, fix, or execute a plan'), matching the anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	Uses natural phrasing a user would actually say ('build', 'implement', 'fix', 'execute a plan', 'new feature', 'bug') with an explicit 'Use when the user asks to' clause, giving good coverage of common variations rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	It is a deliberate universal router, so its triggers ('build, implement, fix, execute a plan') overlap heavily with the dedicated skills it dispatches to (x-bugfix, brainstorming, writing-plans); the niche is somewhat specific but still risks firing for the routed skills, so it sits at the 'somewhat specific, could overlap' anchor rather than the clear-niche anchor.	2 / 3
	Total	11 / 12 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: c765280

Reviewed: 13 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.