CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

arn-code-report

This skill should be used when the user says "report issue", "arness code report", "code report", "something went wrong", "report a bug", "file arness code issue", "arness code broke", "report arness code problem", "diagnose issue", "arness doctor", "run doctor", "diagnose arness code", "arn-code-report", or wants to report a problem with an Arness Code workflow skill. Invokes the arn-code-doctor agent to diagnose the issue, then files a GitHub issue on the Arness plugin repository. Do NOT use this for filing issues on the user's own project — use /arn-code-create-issue for that. For Spark issues use /arn-spark-report. For Infra issues use /arn-infra-report.

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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-sequenced, highly actionable workflow with explicit consent validation, comprehensive error-recovery paths, and proper delegation of detail to two real reference files. It is only held back from top marks by minor repetition of the local-file fallback details and small execution gaps around issue title and body construction.

Suggestions

State the issue-title convention explicitly (e.g., "[arn-code-report] <short summary from user_description>") so Step 6 needs no improvisation.

Show how to pass the multi-line issue body safely (e.g., write the draft to a temp file and use `gh issue create --body-file`), since `--body "<body>"` breaks on large markdown bodies.

Consolidate the local-file fallback (filename, location, and when to use it) into one place — e.g., the Error Handling section — and reference it from Steps 3, 5, and 6 to remove the repeated `arness-code-report-<YYYY-MM-DD>.md` blocks.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — no concept explanations, just workflow steps with concrete commands. Minor trimming is possible: the local-file fallback "arness-code-report-<YYYY-MM-DD>.md" is repeated in Step 3, Step 5, Step 6, and Error Handling, and reading `## Arness` from CLAUDE.md appears in both Step 0 and Step 3. This fits anchor 4 (efficient with minor instances that could be trimmed) rather than anchor 5.

4 / 5

Actionability

Guidance is mostly executable: concrete commands like `gh auth status`, `git -C ${CLAUDE_PLUGIN_ROOT} remote get-url origin`, `bash ${CLAUDE_PLUGIN_ROOT}/skills/arn-code-ensure-config/scripts/plugin-version.sh`, and `gh issue create --repo <owner/repo> --title "<title>" --body "<body>" --label "arn-code-report"`, plus exact agent-dispatch and fallback filenames. Minor gaps remain — the title is never specified and passing a large multi-line body via `--body "<body>"` is fragile in practice without a heredoc/temp-file note — so it sits just below the fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The seven steps (Step 0 through Step 6) are clearly numbered and sequenced, with an explicit validation checkpoint ("present the full report draft and obtain explicit user consent before submitting", `gh auth status` check) and genuine feedback loops for error recovery (label missing → "retry without `--label`"; submission fails → save locally; agent fails → minimal issue fallback; a dedicated Error Handling section per failure mode). This matches the anchor for clear sequence with explicit validation, feedback loops, and recovery paths.

5 / 5

Progressive Disclosure

The body is a concise workflow overview that delegates detail one level deep to real bundle files that exist: `references/arness-knowledge-base.md` (delegated to the doctor agent at dispatch) and `references/issue-template.md` (for issue assembly), each referenced with full paths and a clear purpose. Content is appropriately split — the 353-line knowledge base and issue template are not inlined — matching the anchor for a clear overview with well-signaled one-level-deep references.

5 / 5

Total

18

/

20

Passed

Description

91%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.

A strong description that explicitly answers both what the skill does and when to use it, backed by an extensive list of natural trigger phrases and explicit boundary guidance against sibling skills. Its only weakness is a handful of overly generic trigger phrases (e.g., "something went wrong") that could match non-Arness contexts.

DimensionReasoningScore

Specificity

The description names concrete, specific actions — "Invokes the arn-code-doctor agent to diagnose the issue, then files a GitHub issue on the Arness plugin repository" — with the agent and destination named, plus boundary behaviors (routing to /arn-spark-report and /arn-infra-report). It lists several specific behaviors rather than only 1-2 generic ones, but coverage is not fully comprehensive (no mention of the consent review or local-file fallback), which keeps it below anchor 5.

4 / 5

Completeness

Both questions are explicitly answered: what it does ("Invokes the arn-code-doctor agent to diagnose the issue, then files a GitHub issue on the Arness plugin repository") and when to use it ("This skill should be used when the user says..." followed by concrete trigger phrases). This matches the anchor for clearly and explicitly answering both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Thirteen quoted natural trigger phrases are provided — "report issue", "arness code report", "code report", "something went wrong", "report a bug", "arness code broke", "arness doctor", "run doctor", "diagnose arness code", "arn-code-report" — covering synonyms, abbreviations, and the slash-command name. This matches the anchor for comprehensive coverage of natural terms including synonyms; no common variations are missing.

5 / 5

Distinctiveness Conflict Risk

It has a clear niche and explicit disambiguation ("Do NOT use this for filing issues on the user's own project — use /arn-code-create-issue for that. For Spark issues use /arn-spark-report. For Infra issues use /arn-infra-report"), which is stronger than anchor 4's 'minor overlap risk with closely related skills'. However, generic triggers like "something went wrong", "report a bug", and "diagnose issue" could fire in non-Arness contexts, so it does not fully meet anchor 5's 'minimal conflict risk' with distinct triggers.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

AppsVortex/arness

Path

plugins/arn-code/skills/arn-code-report/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.