CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-resolve-spm

Use when the user mentions SPM resolution failures, "no such module" errors, duplicate symbol linker errors, version conflicts between packages, or Swift 6 package compatibility issues.

47

Quality

48%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-resolve-spm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 content is highly actionable with concrete detection commands and resolution code, and it is well-structured, but it is notably verbose with padded template/reference sections and lacks explicit validation checkpoints around its destructive reset operations. Splitting reference material into bundle files and trimming known command lists would improve it.

Suggestions

Move the full Output Format template, 'When No Issues Found' template, and Common SPM Commands Reference into separate reference files (e.g. references/output-template.md, references/commands.md) and link to them from SKILL.md.

Add an explicit validation checkpoint after destructive reset steps (e.g. 'After rm -rf .build && swift package resolve, verify with swift build before proceeding').

Trim the Xcode menu-navigation lines and other widely-known SPM commands to reduce token overhead.

DimensionReasoningScore

Conciseness

The body runs ~440 lines and includes padded sections Claude largely already knows — a fully worked Output Format template, a 'When No Issues Found' alternate template, a Common SPM Commands Reference, and Xcode menu navigation — matching 'Noticeably verbose; several unnecessary explanations or padded sections.'

2 / 5

Actionability

Detection sections give concrete executable bash commands and resolution sections include real Swift Package.swift code, but some resolution strategies are advisory numbered lists without commands, leaving minor gaps.

4 / 5

Workflow Clarity

An Audit Process with Steps 1-3 provides a rough sequence, but validation checkpoints are absent from the workflow and destructive reset commands (rm -rf .build, rm Package.resolved) lack inline verification, triggering the destructive-operation cap at 3.

3 / 5

Progressive Disclosure

Headers organize the content, but at ~440 lines everything is inlined in SKILL.md with no bundle files; the output templates and command reference clearly belong in separate reference files but are not split out.

3 / 5

Total

12

/

20

Passed

Description

47%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 has strong, natural trigger terms and a distinct SPM niche, but it omits any statement of what the skill does, relying solely on a 'when' clause. Adding a leading capability clause would materially raise completeness and specificity.

Suggestions

Lead with a 'what' clause before the triggers, e.g. 'Diagnoses and resolves Swift Package Manager dependency conflicts. Use when the user mentions...'.

Add action verbs (diagnose, resolve, repair) so the skill's capability is explicit, not just its triggers.

Consider adding 'Package.swift', 'Package.resolved', or 'could not be resolved' as additional natural trigger phrases.

DimensionReasoningScore

Specificity

The description names the domain (SPM) and lists concrete trigger symptoms, but states no capability/action verbs describing what the skill does (e.g. diagnose or resolve), matching the anchor 'Names the domain but actions are minimal or generic.'

2 / 5

Completeness

It provides an explicit 'when' clause ('Use when the user mentions...') but no 'what' statement of what the skill does, matching the anchor 'only "when" is present without "what".'

2 / 5

Trigger Term Quality

It includes natural terms users actually say and paste, such as 'no such module' errors, 'duplicate symbol linker errors', and 'version conflicts', giving good keyword coverage with only a few natural variants missing (e.g. 'Package.swift', 'could not be resolved').

4 / 5

Distinctiveness Conflict Risk

It targets a clear niche (Swift Package Manager conflicts) with distinct triggers, with only minor overlap risk against a general Swift/build skill (e.g. 'no such module' could arise from non-SPM causes).

4 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CharlesWiltgen/Axiom
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.