arn-implementing
This skill should be used when the user says "implementing", "arness implementing", "start implementing", "execute the plan", "build it", "implement this", "run the tasks", "execute", "start building", "implement the feature", "implement the fix", "quick change", "swift", "swift mode", "quick implementation", "standard", "standard mode", "standard implementation", "start execution", "build the feature", "arn-implementing", or wants to execute an implementation plan, run a quick implementation, a standard-tier implementation, or manage the build-simplify-review cycle. Chains to arn-shipping at completion.
50
54%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/arn-code/skills/arn-implementing/SKILL.mdQuality
Discovery
54%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a long list of trigger phrases with almost no explanation of what the skill actually does. While it excels at providing trigger terms for selection, it completely fails to describe concrete capabilities, leaving Claude (and users) unclear about what actions this skill performs. The description reads as a trigger-term dump rather than a useful skill summary.
Suggestions
Add concrete capability descriptions explaining what the skill does, e.g., 'Executes implementation plans by writing code, creating files, and iterating through a build-simplify-review cycle' before the trigger terms.
Reduce the trigger term list to the most distinctive and natural phrases, and consolidate synonyms (e.g., group 'swift mode'/'quick change'/'quick implementation' into one clause).
Explain what 'build-simplify-review cycle' means and what 'chains to arn-shipping' entails, so Claude understands the workflow context and output expectations.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lacks concrete actions. It mentions 'execute an implementation plan', 'run a quick implementation', and 'manage the build-simplify-review cycle' but never specifies what the skill actually does — no concrete capabilities like 'writes code', 'creates files', 'refactors modules', etc. are listed. | 1 / 3 |
Completeness | The 'when' is extensively covered with explicit trigger phrases and use cases. However, the 'what' is extremely weak — it never clearly explains what the skill actually does beyond vague references to 'implementation' and 'build-simplify-review cycle'. The imbalance means it only partially answers both questions. | 2 / 3 |
Trigger Term Quality | The description is heavily loaded with trigger terms and natural phrases users would say: 'implementing', 'build it', 'execute the plan', 'quick change', 'swift mode', 'standard mode', 'implement the feature', 'implement the fix', etc. These cover many natural variations a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Terms like 'implementing', 'build it', 'execute' are very generic and could easily conflict with any coding, development, or task execution skill. The specific terms like 'arn-implementing', 'swift mode', 'standard mode' add some distinctiveness, but the core triggers are broad enough to cause conflicts. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at actionability and workflow clarity — every decision point, state transition, and error case is precisely specified with concrete paths, commands, and branching logic. However, it is severely undermined by its length and lack of progressive disclosure: the preference lookup chain is duplicated verbatim, CHANGE_RECORD.json field specs belong in a template reference, and gate interaction patterns could be templated. The result is a skill that is correct and thorough but consumes far more tokens than necessary.
Suggestions
Extract the repeated two-tier preference lookup chain into a shared reference file (e.g., references/preference-lookup.md) and reference it from G3 and G4 instead of duplicating the full procedure.
Move the CHANGE_RECORD.json field-by-field population instructions to a reference file (e.g., references/change-record-generation.md) — the SKILL.md should just say 'Generate CHANGE_RECORD.json per references/change-record-generation.md'.
Create a gate interaction template reference that defines the standard pattern (AskUserQuestion → options → follow-up → preference write) once, then each gate can reference it with only the gate-specific options and preference key.
Compress the state detection table and gate descriptions to essential routing logic only — remove explanatory prose that restates what the table/options already convey.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~350+ lines. It contains extensive procedural detail that could be dramatically compressed — the preference lookup chain is repeated nearly identically for G3 and G4, the CHANGE_RECORD.json generation section is overly detailed with field-by-field specifications that belong in a reference file, and many gate descriptions repeat patterns (AskUserQuestion, options, follow-up) that could be templated once. | 1 / 3 |
Actionability | The skill provides highly specific, concrete guidance at every decision point: exact artifact paths to check, precise routing logic, specific skill invocations with correct syntax, exact preference key names and file paths, and detailed branching conditions. Every gate has explicit options and outcomes. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally well-sequenced with clear state detection (Step 1 table), numbered gates (G0-G5), explicit progress indicators at each stage, validation/preference checks before actions, error recovery paths, and feedback loops (e.g., review → NEEDS FIXES → re-review). The resume-from-state mechanism is thorough. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files provided. The repeated preference lookup chains, the detailed CHANGE_RECORD.json field specifications, and the gate interaction patterns should all be extracted to reference files. The skill references external paths (preferences-schema.md, step-0-fast-path.md, templates) but keeps enormous amounts of procedural detail inline that should be in separate references. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AppsVortex/arness
- Commit
b9084b6
- Reviewed
Table of Contents
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.