CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

harbor-exec

Use when working with Harbor's `harbor exec` CLI workflow: compiling files, directories, or globs into Harbor tasks; running map jobs; configuring artifacts and existence-only verification; using map-reduce; writing or reviewing ExecConfig YAML/JSON/TOML; or debugging command behavior, config validation, and job outputs.

72

Quality

91%

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

78%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-structured, lean overview with concrete commands, sensible defaults, and appropriate offloading of examples to a real reference file. Main gaps: no inline ExecConfig/map-reduce example, no explicit error-recovery loop for failed jobs, and an unpinned-version dependency stated inline.

Suggestions

Add a minimal inline ExecConfig example (YAML) in the Map And Reduce section so the map.compile/map.job/reduce structure is executable without opening the reference file.

Add a validation feedback loop after job execution, e.g. check job output/trial artifacts for failures and how to retry or adjust (validation → fix → re-run) to strengthen workflow clarity for batch runs.

Consider moving or framing the Harbor >=0.17.1 version requirement near the First Checks as an explicit compatibility gate (or deprecation note) so time-sensitive version info doesn't read as evergreen guidance.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no padding or explanations of known concepts, e.g. "Treat `harbor exec` as agentic map-reduce: it turns loose inputs into Harbor tasks, runs Harbor jobs over those tasks". Not 5: the version pin ("Require Harbor `>=0.17.1`...") is time-sensitive information not placed in a deprecation section, which the guidelines penalize.

4 / 5

Actionability

Concrete executable commands are present ("harbor --version", "harbor exec --help", "harbor exec -p ./input -i \"Write /app/answer.json\" -f /app/answer.json") plus specific flag guidance (--scan/--no-scan, --tasks-dir, --jobs-dir). Not 5: the Map And Reduce section describes config keys (map.compile, map.job) without an inline ExecConfig example, deferring all concrete examples to the reference file.

4 / 5

Workflow Clarity

Clear sequence: First Checks (verify version, inspect command surface) → confirm run parameters → execute → verify artifacts ("Should usually define reducer artifacts explicitly, then verify them"), with checkpoints like "show the exact launch command before running it". Not 5: no explicit feedback loop for handling failed or invalid job output (validate → fix → retry) despite this being a batch-execution workflow.

4 / 5

Progressive Disclosure

Well-organized sections with a single, well-signaled one-level-deep reference: "Read `references/examples.md` when writing concrete commands, config files, or map-reduce examples" — the file exists (172 lines of executable examples) and the purpose/condition for reading it is stated. Not 4: there are no organization gaps; the split between overview body and example file is appropriate.

5 / 5

Total

17

/

20

Passed

Description

100%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.

Excellent description: concrete, comprehensive action list, explicit 'Use when' trigger clause, third-person voice, and a clearly distinct niche around the `harbor exec` command. No fluff or over-claims.

DimensionReasoningScore

Specificity

The description enumerates six concrete actions — "compiling files, directories, or globs into Harbor tasks; running map jobs; configuring artifacts and existence-only verification; using map-reduce; writing or reviewing ExecConfig YAML/JSON/TOML; or debugging command behavior, config validation, and job outputs" — spanning the full compile/run/configure/aggregate/debug surface. Not 4: coverage is comprehensive, not 'several actions with minor gaps'.

5 / 5

Completeness

Explicitly answers both: what (the enumerated concrete actions) and when ("Use when working with Harbor's `harbor exec` CLI workflow"). Matches the top anchor with concrete trigger phrases; not 4, since the 'when' clause is explicit and specific rather than improvable.

5 / 5

Trigger Term Quality

Natural terms a Harbor user would say are all present: "harbor exec", "map jobs", "map-reduce", "artifacts", "ExecConfig", plus format extensions ("YAML/JSON/TOML") and input types ("files, directories, or globs"). Matches the anchor's requirement for synonyms and file extensions; nothing obvious is missing.

5 / 5

Distinctiveness Conflict Risk

Scoped narrowly to a single named command ("Harbor's `harbor exec` CLI workflow") with niche-specific triggers (ExecConfig, map-reduce, existence-only verification). Minimal overlap risk with any other skill.

5 / 5

Total

20

/

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

Arize-ai/phoenix

Path

.agents/skills/harbor-exec/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.