CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-build

Use when ANY iOS or macOS build fails, a crash log needs diagnosing, a test run crashes, Xcode misbehaves, or an environment issue blocks work before code is the suspect. Covers build failures, dependency conflicts, simulator diagnostics.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./axiom-cursor/skills/axiom-build/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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.

A well-architected router with explicit routes, a decision tree, and genuinely useful anti-rationalization and conflict-resolution sections, plus concrete diagnostic commands. However, roughly a third of the body is redundant restatement of the routing table, and every referenced detail file is missing from the bundle, leaving the progressive-disclosure structure unverifiable.

Suggestions

Delete or drastically trim the ~120-line 'Example Invocations' section — it restates the Routing Logic triggers one-for-one — and let the Routing Logic and Decision Tree carry the mapping once each.

Fix the disordered section numbering (16 'xclog-ref' appears before 15 'code-signing') and deduplicate guidance stated twice, such as the code-signing 'never code bugs' rationale in section 15 and the Anti-Rationalization table.

Ship the referenced detail files (skills/xcode-debugging.md, skills/build-performance.md, skills/lldb.md, etc.) in the bundle or correct the paths, since the skill currently references files that do not exist alongside it.

DimensionReasoningScore

Conciseness

The 458-line body restates the same trigger-to-route mapping four times — 'When to Use', 'Routing Logic', 'Decision Tree', and a ~120-line 'Example Invocations' section — and the code-signing 'never code bugs' rationale appears in both section 15 and the Anti-Rationalization table. This is noticeably verbose with several padded, redundant sections, beyond the 'could be tightened' level of score 3.

2 / 5

Actionability

Routes carry concrete invoke targets ('skills/xcode-debugging.md', named agents, slash commands) and the diagnostics section gives executable checks like 'command -v axbuild' and 'pgrep -lx xcodebuild'. Not score 5 because the build block relies on unresolved $SCHEME/$DESTINATION variables and some prose guidance ('Discover the actual scheme and destination') lacks the specific step.

4 / 5

Workflow Clarity

The decision tree gives a clear numbered routing sequence, and the diagnostics section has real checkpoints (pgrep exit-code interpretation, 'Read an existing log before considering another build', saved-log fallback). Not score 5 due to disordered section numbering (16 appears before 15) and the absence of any route-match verification step.

4 / 5

Progressive Disclosure

The thin-router-pointing-to-detail-files architecture is the right progressive-disclosure design and every path is clearly signaled, but the bundle contains zero files — none of the referenced skills/*.md targets (e.g. skills/xcode-debugging.md, axiom-shipping's testflight-triage.md) exist alongside SKILL.md, so the split is unverified and the references dangle. This fits 'references present but the organization cannot be confirmed' better than score 4's 'minor organization gaps'.

3 / 5

Total

13

/

20

Passed

Description

61%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 an excellent, explicit 'Use when' trigger clause with natural platform vocabulary, but the capability side is a vague domain listing ('Covers...') that never states the skill's concrete action. Its broad crash/test/dependency scope also overlaps the very subskills it routes to.

Suggestions

Replace 'Covers build failures, dependency conflicts, simulator diagnostics' with a concrete action statement, e.g. 'Diagnoses Xcode build and environment failures and routes them to specialized debugging skills'.

State the router's core function explicitly (e.g. 'Classifies the failure type and delegates to the matching subskill or agent') so the 'what' is as strong as the 'when'.

Add distinguishing qualifiers for the crash-log and dependency-conflict triggers (e.g. 'build-blocking' or 'environment-suspected') to reduce overlap with standalone crash-analysis and SPM-resolution skills.

DimensionReasoningScore

Specificity

The description names the domain ("Covers build failures, dependency conflicts, simulator diagnostics") but states no concrete action the skill performs — whether it diagnoses, routes, or fixes is never said. It matches the anchor 'Names the domain but actions are minimal or generic' rather than score 3, which requires 1-2 concrete actions.

2 / 5

Completeness

Both halves are explicit: a strong "Use when ANY iOS or macOS build fails..." when-clause plus a what-side scope statement. Not score 5 because the what-side ("Covers...") lists domains rather than stating what the skill concretely does.

4 / 5

Trigger Term Quality

Natural phrases like "iOS or macOS build fails", "crash log needs diagnosing", "test run crashes", and "Xcode misbehaves" mirror what users would actually say. Not score 5 because common variations such as "BUILD FAILED", "compile error", or "won't build" are absent.

4 / 5

Distinctiveness Conflict Risk

The Apple platform qualifier gives it a niche, but the broad scope (crash log diagnosing, dependency conflicts, test crashes) overlaps sibling skills the router itself delegates to, such as crash-analyzer and spm-conflict-resolver. Overlap risk with closely related skills is more than minor, so it fits 'Somewhat specific but could still overlap with similar skills' rather than score 4.

3 / 5

Total

13

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

CharlesWiltgen/Axiom

Path

axiom-cursor/skills/axiom-build/SKILL.md

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.