CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hephaestus-upload

Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.

Quality

95%

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

88%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 strong, highly operational skill body: exact commands, explicit validation checkpoints, and error-recovery loops for a hard-to-reverse publish operation. The only weaknesses are minor over-explanation of design rationale and spec detail inlined in a single file that could live in a reference.

Suggestions

Trim the design-rationale passages (e.g., why upload is not folded into /hep-network, why pattern checks miss secrets) to one line each, keeping only the behavioral rule.

Move the secret-review verdict JSON schema and the `kind` enumeration into a reference file (e.g., references/secret-review.md) and keep a short inline summary, reducing the body to a tighter overview.

Consider moving the workforce résumé repair details (stable role:*/community:*/skill:*/knowledge:* ID guidance) into the same reference file so the main flow reads as a compact checklist.

DimensionReasoningScore

Conciseness

The body is mostly lean and imperative with no basic-concept explanations, but rationale passages such as "Upload is deliberately NOT folded into /hep-network ... merging them would let 'find me an agent' end in an accidental publish" and "Pattern checks only find secrets someone wrote a pattern for. You read meaning" are justification that could be trimmed. This matches the anchor 'Efficient; minor instances of over-explanation that could be trimmed' rather than the 5 anchor, since a few tokens do not directly advance the upload task.

4 / 5

Actionability

Fully executable guidance throughout: a copy-paste runner-resolution bash loop, exact CLI commands for both destinations with all flags ("hep-upload <agent-folder> --visibility private-link --secret-review <file> --dry-run"), and a concrete JSON verdict schema with enumerated kind values. Specific error codes (package_hash_mismatch, overwrite_confirmation_required, workforce_resume_incomplete) each come with the exact rerun command, matching the 5 anchor 'Fully executable; copy-paste ready code or commands'.

5 / 5

Workflow Clarity

Seven clearly sequenced sections with explicit validation checkpoints (one dry-run, hash/receipt pinning, 'Stop on package_hash_mismatch, upload_receipt_required, or upload_receipt_mismatch') and feedback loops for error recovery (overwrite approval rerun with --overwrite-cloud-id, and 'Rerun the upload and repeat until registration succeeds'). This is a destructive, hard-to-reverse write operation and the required validation and feedback loops are all present, matching the 5 anchor.

5 / 5

Progressive Disclosure

The single file is well organized into seven signaled numbered sections with no nested references, and no bundle files exist to point to. However, at roughly 155 lines with inlined spec detail such as the ~40-line secret-review verdict format, it goes beyond the 'under 50 lines with well-organized sections' case that scores 5, so the best fit is the 4 anchor 'Good structure; most content is appropriately placed; minor organization gaps'.

4 / 5

Total

18

/

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.

An exemplary description: it states what the skill does, when to invoke it with concrete command and natural-language triggers, and the key disambiguation behavior (Cloud vs Hub), all in third person with no fluff. Every dimension lands on the top anchor.

DimensionReasoningScore

Specificity

It lists multiple concrete actions — "upload, publish, or list an Agentlas agent or team" plus "Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate" — comprehensively covering the skill's user-facing capabilities. This matches the 5 anchor ('multiple specific concrete actions; comprehensive coverage') rather than 4, since no user-facing action is missing.

5 / 5

Completeness

It explicitly answers both questions: when via the concrete trigger clause "Use when the user types ... or asks to upload, publish, or list an Agentlas agent or team", and what via "Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate". This is a direct match to the 5 anchor 'Clearly and explicitly answers both what AND when with concrete trigger phrases'.

5 / 5

Trigger Term Quality

Trigger coverage is comprehensive: three exact command spellings ("$hephaestus-upload, /hep-upload, /agentlas-upload"), the natural verbs users would say ("upload, publish, or list"), and the domain nouns "Agentlas agent or team" and "Agentlas Hub". It matches the 5 anchor's 'comprehensive coverage of natural terms including synonyms', with command-alias variants substituting for the file extensions a tool-invocation skill would have.

5 / 5

Distinctiveness Conflict Risk

Named proprietary commands and domain-specific nouns ("Agentlas", "Hephaestus gate", "Agentlas Hub") give it a clear niche with distinct triggers. The only generic verb, "upload", is qualified by "an Agentlas agent or team", keeping conflict risk minimal and matching the 5 anchor.

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

agentlas-ai/Agentlas-OS

Path

codex/plugins/agentlas-core-engine-meta-agent/skills/hephaestus-upload/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.